ZEBO_AI_Emotion_Detection.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "ZEBO.AI_Emotion_Detection.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b9jEfV1BuL-t"
      },
      "source": [
        "### Drive Mounter"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KkX0McPauqiA",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c8143ead-04a4-48f5-e077-5875dd606f3e"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HrNp05O4uzjJ"
      },
      "source": [
        "### Data Preprcessing\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Mwf7Lj6Vu4m6"
      },
      "source": [
        "fldr=\"/content/drive/MyDrive/CK+48\"\n"
      ],
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4CPTeRZFvxnM",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3280bc08-7265-42dd-bbea-78b08dfc421d"
      },
      "source": [
        "import os\n",
        "files = os.listdir(fldr)\n",
        "print(files)"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "['fear', 'disgust', 'anger', 'sadness', 'contempt', 'surprise', 'happy']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rLaJ1-2QwERM"
      },
      "source": [
        "Exp=['fear', 'contempt', 'happy', 'anger', 'surprise', 'disgust', 'sadness']"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YlQuUFH4wHg9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "453eecbc-fa08-4bf2-dca0-a3ae501f9239"
      },
      "source": [
        "import cv2\n",
        "from google.colab.patches import cv2_imshow\n",
        "i=0\n",
        "last=[]\n",
        "images=[]\n",
        "labels=[]\n",
        "for fle in files:\n",
        "  idx=Exp.index(fle)\n",
        "  label=idx\n",
        "  \n",
        "  total=fldr+'/'+fle\n",
        "  files_exp= os.listdir(total)\n",
        "\n",
        "  for fle_2 in files_exp:\n",
        "    file_main=total+'/'+fle_2\n",
        "    print(file_main+\"   \"+str(label))\n",
        "    image= cv2.imread(file_main)\n",
        "\n",
        "    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n",
        "    image= cv2.resize(image,(48,48))\n",
        "    images.append(image)\n",
        "    labels.append(label)\n",
        "    i+=1\n",
        "  last.append(i)\n",
        "\n",
        "\n"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/content/drive/MyDrive/CK+48/fear/S074_001_00000018.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S050_001_00000017.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S117_003_00000012.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S125_006_00000020.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S501_004_00000054.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S091_001_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S055_006_00000008.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S124_003_00000010.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S062_001_00000016.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S059_002_00000017.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S032_004_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S502_004_00000051.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S055_006_00000006.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S074_001_00000020.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S125_006_00000021.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S050_001_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S102_003_00000016.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S117_003_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S132_003_00000023.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S119_003_00000022.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S501_004_00000055.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S046_003_00000016.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S124_003_00000011.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S011_003_00000012.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S102_003_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S091_001_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S102_003_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S119_003_00000023.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S065_002_00000020.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S046_003_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S050_001_00000016.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S501_004_00000056.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S502_004_00000050.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S132_003_00000022.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S138_001_00000012.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S059_002_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S138_001_00000010.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S062_001_00000017.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S055_006_00000007.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S119_003_00000024.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S074_001_00000019.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S124_003_00000009.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S059_002_00000016.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S084_002_00000021.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S046_003_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S068_004_00000009.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S084_002_00000022.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S011_003_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S054_002_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S117_003_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S011_003_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S065_002_00000022.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S062_001_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S138_001_00000011.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S032_004_00000012.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S065_002_00000021.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S091_001_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S068_004_00000008.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S068_004_00000010.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S132_003_00000021.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S032_004_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S125_006_00000022.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S054_002_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S084_002_00000023.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S054_002_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S999_003_00000053.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S999_003_00000055.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S506_004_00000038.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S504_004_00000013.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S506_004_00000036.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S999_003_00000054.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S504_004_00000015.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S506_004_00000037.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S504_004_00000014.png   0\n",
            "/content/drive/MyDrive/CK+48/fear/S502_004_00000052.png   0\n",
            "/content/drive/MyDrive/CK+48/disgust/S011_005_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S032_005_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S046_004_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S056_002_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S032_005_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S022_006_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S005_001_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S057_003_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S005_001_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S052_006_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S046_004_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S022_006_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S022_006_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S044_006_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S035_005_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S054_004_00000022.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S045_004_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S058_006_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S046_004_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S011_005_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S060_005_00000021.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S044_006_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S055_003_00000007.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S060_005_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S005_001_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S054_004_00000023.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S057_003_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S052_006_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S011_005_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S058_006_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S054_004_00000024.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S052_006_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S058_006_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S055_003_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S045_004_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S044_006_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S032_005_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S051_003_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S055_003_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S051_003_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S057_003_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S035_005_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S056_002_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S056_002_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S045_004_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S060_005_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S035_005_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S051_003_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S073_006_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S080_008_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S062_005_00000027.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S069_003_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S073_006_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S065_005_00000007.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S062_005_00000028.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S075_005_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S080_008_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S069_003_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S065_005_00000006.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S061_004_00000021.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S074_004_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S087_004_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S082_007_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S070_005_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S071_006_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S085_004_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S077_006_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S067_006_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S071_006_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S085_004_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S067_006_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S085_004_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S074_004_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S065_005_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S062_005_00000029.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S081_008_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S061_004_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S071_006_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S069_003_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S088_004_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S078_007_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S087_004_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S075_005_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S078_007_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S082_007_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S080_008_00000007.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S068_005_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S078_007_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S081_008_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S074_004_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S079_002_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S070_005_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S077_006_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S068_005_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S067_006_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S061_004_00000022.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S070_005_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S087_004_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S073_006_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S076_005_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S076_005_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S079_002_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S075_005_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S081_008_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S077_006_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S068_005_00000021.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S082_007_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S076_005_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S079_002_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S099_007_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S111_007_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S108_006_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S134_008_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S132_005_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S130_012_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S130_012_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S129_011_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S102_009_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S108_006_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S099_007_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S130_012_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S128_004_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S107_005_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S116_006_00000007.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S124_006_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S090_006_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S095_006_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S099_007_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S098_003_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S097_004_00000029.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S116_006_00000005.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S088_004_00000019.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S090_006_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S096_003_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S095_006_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S124_006_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S129_011_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S102_009_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S106_004_00000007.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S096_003_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S106_004_00000006.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S111_007_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S096_003_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S097_004_00000028.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S088_004_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S105_008_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S106_004_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S134_008_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S125_008_00000008.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S131_010_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S098_003_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S124_006_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S109_005_00000014.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S109_005_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S102_009_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S098_003_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S105_008_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S128_004_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S125_008_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S107_005_00000010.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S129_011_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S108_006_00000020.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S125_008_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S128_004_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S131_010_00000017.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S107_005_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S111_007_00000012.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S131_010_00000018.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S097_004_00000030.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S132_005_00000015.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S105_008_00000009.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S109_005_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S132_005_00000016.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S095_006_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S116_006_00000006.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S090_006_00000011.png   5\n",
            "/content/drive/MyDrive/CK+48/disgust/S134_008_00000013.png   5\n",
            "/content/drive/MyDrive/CK+48/anger/S014_003_00000029.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S042_004_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S058_005_00000008.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S022_005_00000031.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S045_005_00000028.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S032_003_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S050_004_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S028_001_00000024.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S011_004_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S058_005_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S028_001_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S032_003_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S042_004_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S034_003_00000027.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S029_001_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S010_004_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S055_004_00000028.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S037_003_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S011_004_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S037_003_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S050_004_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S034_003_00000025.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S028_001_00000023.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S032_003_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S014_003_00000028.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S029_001_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S055_004_00000026.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S011_004_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S037_003_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S050_004_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S026_003_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S055_004_00000027.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S026_003_00000014.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S045_005_00000030.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S010_004_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S045_005_00000029.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S042_004_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S010_004_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S022_005_00000032.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S014_003_00000030.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S022_005_00000030.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S034_003_00000026.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S026_003_00000013.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S029_001_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S111_006_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S113_008_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S082_005_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S127_010_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S119_008_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S126_008_00000028.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S117_006_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S067_004_00000023.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S092_003_00000014.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S112_005_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S087_007_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S072_005_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S075_008_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S087_007_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S072_005_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S111_006_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S113_008_00000023.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S112_005_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S109_003_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S067_004_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S127_010_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S090_007_00000014.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S089_003_00000035.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S089_003_00000036.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S109_003_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S082_005_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S100_005_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S089_003_00000034.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S113_008_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S100_005_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S075_008_00000012.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S071_004_00000026.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S066_005_00000011.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S071_004_00000028.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S126_008_00000027.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S082_005_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S058_005_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S066_005_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S119_008_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S072_005_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S087_007_00000014.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S090_007_00000013.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S066_005_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S090_007_00000012.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S117_006_00000008.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S109_003_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S112_005_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S111_006_00000008.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S100_005_00000023.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S092_003_00000012.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S092_003_00000013.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S075_008_00000011.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S119_008_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S126_008_00000029.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S117_006_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S071_004_00000027.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S067_004_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S130_007_00000019.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S504_001_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S506_001_00000039.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S999_001_00000017.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S134_003_00000011.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S506_001_00000040.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S127_010_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S129_006_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S999_001_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S133_003_00000046.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S136_005_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S503_001_00000069.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S130_007_00000020.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S501_001_00000065.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S501_001_00000066.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S136_005_00000008.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S129_006_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S133_003_00000047.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S504_001_00000021.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S502_001_00000015.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S134_003_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S502_001_00000014.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S502_001_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S129_006_00000008.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S503_001_00000070.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S501_001_00000067.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S130_007_00000018.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S504_001_00000022.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S136_005_00000010.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S133_003_00000045.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S506_001_00000038.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S134_003_00000009.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S503_001_00000071.png   3\n",
            "/content/drive/MyDrive/CK+48/anger/S999_001_00000016.png   3\n",
            "/content/drive/MyDrive/CK+48/sadness/S046_001_00000024.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S026_002_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S042_002_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S064_004_00000012.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S064_004_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S066_004_00000009.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S066_004_00000008.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S071_002_00000020.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S014_002_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S080_005_00000011.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S066_004_00000010.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S026_002_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S014_002_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S026_002_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S071_002_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S046_001_00000023.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S011_002_00000022.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S046_001_00000025.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S064_004_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S042_002_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S014_002_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S042_002_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S011_002_00000021.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S011_002_00000020.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S071_002_00000019.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S093_001_00000019.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S505_006_00000017.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S136_003_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S106_002_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S125_001_00000012.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S115_004_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S081_002_00000023.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S501_006_00000040.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S138_007_00000011.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S137_005_00000025.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S106_002_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S125_001_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S132_002_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S136_003_00000012.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S095_010_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S080_005_00000012.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S504_006_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S093_001_00000020.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S136_003_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S130_009_00000017.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S095_010_00000012.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S113_003_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S115_004_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S132_002_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S131_003_00000023.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S132_002_00000017.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S081_002_00000022.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S137_005_00000026.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S106_002_00000016.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S113_003_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S504_006_00000017.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S501_006_00000039.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S080_005_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S113_003_00000015.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S108_005_00000022.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S108_005_00000021.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S093_001_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S125_001_00000013.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S081_002_00000024.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S501_006_00000041.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S095_010_00000014.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S130_009_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S504_006_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S131_003_00000022.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S503_006_00000020.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S503_006_00000019.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S503_006_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S137_005_00000027.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S131_003_00000024.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S138_007_00000009.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S115_004_00000017.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S108_005_00000020.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S138_007_00000010.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S130_009_00000019.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S506_006_00000041.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S506_006_00000040.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S505_006_00000019.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S505_006_00000018.png   6\n",
            "/content/drive/MyDrive/CK+48/sadness/S506_006_00000042.png   6\n",
            "/content/drive/MyDrive/CK+48/contempt/S139_002_00000012.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S154_002_00000012.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S154_002_00000013.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S151_002_00000027.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S138_008_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S157_002_00000010.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S147_002_00000013.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S147_002_00000012.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S151_002_00000028.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S139_002_00000013.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S149_002_00000012.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S148_002_00000015.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S157_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S156_002_00000021.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S156_002_00000020.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S155_002_00000010.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S160_006_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S148_002_00000013.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S139_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S138_008_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S155_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S147_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S149_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S156_002_00000019.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S158_002_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S155_002_00000012.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S154_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S148_002_00000014.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S158_002_00000010.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S160_006_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S138_008_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S157_002_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S158_002_00000011.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S151_002_00000029.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S149_002_00000013.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S160_006_00000010.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S505_002_00000020.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S505_002_00000021.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S506_002_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S505_002_00000019.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S504_002_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S504_002_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S506_002_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S895_002_00000005.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S503_002_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S502_002_00000009.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S503_002_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S502_002_00000008.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S503_002_00000006.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S895_002_00000006.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S502_002_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S504_002_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S895_002_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/contempt/S506_002_00000007.png   1\n",
            "/content/drive/MyDrive/CK+48/surprise/S051_002_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S058_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S035_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S044_001_00000024.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S014_001_00000029.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S050_002_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S046_002_00000006.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S011_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S055_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S044_001_00000022.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S053_001_00000022.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S046_002_00000005.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S050_002_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S042_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S022_001_00000030.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S037_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S058_001_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S010_002_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S056_003_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S034_001_00000029.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S052_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S022_001_00000029.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S042_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S026_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S014_001_00000027.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S037_001_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S026_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S058_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S010_002_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S057_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S050_002_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S032_001_00000021.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S053_001_00000021.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S035_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S034_001_00000028.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S056_003_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S051_002_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S055_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S035_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S054_003_00000007.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S032_001_00000022.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S034_001_00000027.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S032_001_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S026_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S011_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S042_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S037_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S010_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S052_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S055_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S054_003_00000006.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S022_001_00000028.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S052_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S014_001_00000028.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S046_002_00000004.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S053_001_00000023.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S051_002_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S057_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S011_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S057_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S056_003_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S054_003_00000005.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S044_001_00000023.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S059_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S070_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S062_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S067_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S061_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S062_002_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S076_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S074_002_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S060_003_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S066_002_00000022.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S080_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S075_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S067_002_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S075_002_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S068_003_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S077_001_00000028.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S079_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S074_002_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S071_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S070_002_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S059_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S062_002_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S078_001_00000033.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S065_003_00000021.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S081_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S060_003_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S073_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S065_003_00000022.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S070_002_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S068_003_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S079_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S066_002_00000021.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S078_001_00000032.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S059_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S080_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S082_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S066_002_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S076_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S073_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S064_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S069_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S073_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S064_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S080_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S071_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S074_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S076_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S065_003_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S081_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S063_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S061_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S061_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S071_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S060_003_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S081_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S063_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S077_001_00000026.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S075_002_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S079_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S078_001_00000031.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S077_001_00000027.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S063_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S069_002_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S064_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S068_003_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S069_002_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S067_002_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S084_001_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S102_002_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S099_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S086_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S092_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S089_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S085_003_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S101_002_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S086_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S092_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S086_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S087_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S094_001_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S097_001_00000021.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S110_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S101_002_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S096_001_00000006.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S114_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S089_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S097_001_00000020.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S102_002_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S107_001_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S107_001_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S097_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S082_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S096_001_00000005.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S088_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S099_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S113_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S101_002_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S089_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S107_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S114_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S090_002_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S114_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S090_002_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S111_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S092_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S115_001_00000007.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S094_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S102_002_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S085_003_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S095_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S111_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S088_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S100_002_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S100_002_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S082_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S100_002_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S096_001_00000007.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S095_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S084_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S110_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S111_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S115_001_00000006.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S085_003_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S087_001_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S087_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S113_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S099_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S084_001_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S090_002_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S113_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S110_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S094_001_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S088_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S095_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S124_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S130_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S126_004_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S117_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S136_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S125_007_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S116_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S130_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S135_001_00000039.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S137_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S131_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S136_001_00000019.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S125_007_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S132_008_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S115_001_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S137_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S116_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S116_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S132_008_00000008.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S122_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S138_004_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S133_009_00000005.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S135_001_00000037.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S124_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S127_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S119_001_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S136_001_00000018.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S126_004_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S137_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S125_007_00000007.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S126_004_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S138_004_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S127_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S124_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S133_009_00000004.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S131_001_00000014.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S130_001_00000017.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S119_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S135_001_00000038.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S132_008_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S133_009_00000006.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S129_002_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S117_001_00000013.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S122_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S119_001_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S127_001_00000015.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S117_001_00000012.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S131_001_00000016.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S129_002_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S129_002_00000009.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S122_001_00000010.png   4\n",
            "/content/drive/MyDrive/CK+48/surprise/S138_004_00000011.png   4\n",
            "/content/drive/MyDrive/CK+48/happy/S057_006_00000032.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S011_006_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S037_006_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S014_005_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S055_005_00000044.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S052_004_00000033.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S037_006_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S053_004_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S053_004_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S042_006_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S057_006_00000031.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S055_005_00000043.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S032_006_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S042_006_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S035_006_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S052_004_00000031.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S034_005_00000009.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S011_006_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S026_006_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S052_004_00000032.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S044_003_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S044_003_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S037_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S034_005_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S055_005_00000045.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S056_004_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S053_004_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S010_006_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S014_005_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S044_003_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S060_002_00000025.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S011_006_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S032_006_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S042_006_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S014_005_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S010_006_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S050_006_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S050_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S032_006_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S056_004_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S050_006_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S010_006_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S026_006_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S026_006_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S056_004_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S035_006_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S034_005_00000008.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S057_006_00000033.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S035_006_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S060_002_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S068_002_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S078_004_00000027.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S066_003_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S065_004_00000026.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S076_006_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S069_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S061_002_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S072_006_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S062_004_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S086_002_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S078_004_00000026.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S069_004_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S061_002_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S070_003_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S069_004_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S060_002_00000026.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S075_006_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S068_002_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S085_002_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S075_006_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S068_002_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S067_005_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S065_004_00000027.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S086_002_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S062_004_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S076_006_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S078_004_00000025.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S074_005_00000041.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S071_005_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S072_006_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S083_003_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S075_006_00000025.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S065_004_00000028.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S071_005_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S085_002_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S063_002_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S061_002_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S087_005_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S062_004_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S064_003_00000025.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S070_003_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S064_003_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S066_003_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S076_006_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S072_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S074_005_00000043.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S086_002_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S067_005_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S079_004_00000026.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S083_003_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S063_002_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S079_004_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S079_004_00000025.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S071_005_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S070_003_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S063_002_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S083_003_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S067_005_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S085_002_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S066_003_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S064_003_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S074_005_00000042.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S092_004_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S095_007_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S098_004_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S116_007_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S125_005_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S114_006_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S094_004_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S094_004_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S124_007_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S127_004_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S089_002_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S125_005_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S096_004_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S114_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S097_006_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S092_004_00000024.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S095_007_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S093_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S098_004_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S128_011_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S099_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S099_004_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S093_004_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S091_003_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S100_006_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S108_008_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S091_003_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S108_008_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S096_004_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S098_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S089_002_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S115_008_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S095_007_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S089_002_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S127_004_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S115_008_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S125_005_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S106_006_00000009.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S109_006_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S106_006_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S115_008_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S091_003_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S099_004_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S096_004_00000009.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S100_006_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S100_006_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S087_005_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S108_008_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S127_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S116_007_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S128_011_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S094_004_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S116_007_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S092_004_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S109_006_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S124_007_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S106_006_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S109_006_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S097_006_00000017.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S087_005_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S124_007_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S097_006_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S114_006_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S093_004_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S131_006_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S137_011_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S129_012_00000011.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S133_010_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S131_006_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S136_006_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S134_004_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S133_010_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S130_013_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S129_012_00000010.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S135_012_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S135_012_00000020.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S132_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S135_012_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S134_004_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S130_013_00000013.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S136_006_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S138_005_00000014.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S133_010_00000012.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S132_006_00000023.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S129_012_00000009.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S137_011_00000018.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S134_004_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S128_011_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S136_006_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S138_005_00000015.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S131_006_00000021.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S137_011_00000019.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S138_005_00000016.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S132_006_00000022.png   2\n",
            "/content/drive/MyDrive/CK+48/happy/S130_013_00000015.png   2\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oBjyfD5245gM"
      },
      "source": [
        "from google.colab.patches import cv2_imshow"
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jRdHutrn48Q8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "937b0a0e-4725-47cf-91dd-b672293901b6"
      },
      "source": [
        "last"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[75, 252, 387, 471, 525, 774, 981]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dm8OGs725qC0"
      },
      "source": [
        "#### Fear"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FQeMquTS5CLY",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "737b1a1f-9435-45c0-f50c-eeb5302bc04e"
      },
      "source": [
        "cv2_imshow(images[24])"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAADAAAAAwCAIAAADYYG7QAAAL0klEQVR4nH1ZWW/bRhflDIc7tVtLpNhKbMQ12qAB2vcGKNAf3vf2qWgNGLHrupIsyZZEiqS4Dvk9HPuGSb5mHgyBEmfO3HvuuYtZv99njDHGoigKw1D5j8UYOzs7m06nuq6bpimEqKpKSpnnOZ4oiiKEMAyDMaaqapZlYRhGUVSWZZZlvu/vdrvHx8cgCKSU/3VKp9MRUkrOOec8z/P/+p2iKKPR6Pz83HVd0zQ1TdN1nT8vwFVVNc9zVVU554wxx3Fc143jOIqiJEkMw3Acp9Vqrddr3/fDMCzL8stT0jQVVVVVVZVl2VcAGYbx5s2bbrdrWZaqqkIIYFJVFdZVFKWqKsMwOOeapjHGYDzDMBqNRpqmeZ4HQRDHcaPRWK/X2+02CIKiKPI8ryN7AlSWZZqm/xcymaff7+MkVVWBxjAMAFIUBXbC3WAhGE8IUZalaZpZlum6nmWZ4zjtdnuz2cxmM8/z4jjOsoyOrqrqyWVfMY+u6ycnJ5ZlCSGEELquk3lwKlBiO9oXKBljRVGUZYkXAU5VVdhSCLFer6WUnwBijJVl+RWiDQaDXq8HHEIIchAtxhj+YivgAyb8JUyapsGEqqqORqOiKNI0LYqiqqqiKJ4AKYoipaTLfbaEEK9evWo2mzAJfASvCSFgA0BUFIUw0XXpK845XKFpGr4yTbPdbvu+DzKVZYkXOaL3K+YZDAa4HO5NVwdty+eF43F7IKuTCdeAl/FBCGHbdrPZdF0XFHyC/hVAuq5fXFy4rgtPVV8ssgosURQFCEHf0iJWkY2B0jRN6AjZUtQ59dmaTqfD4VDTNBIb3JgOwC7EKpgQu9W/UmphCDLhCefcNE3btuvoOb3z2er3+9988009mvAB1pJSMsaEEDB+/dL4MUhGQElCCQpeYYwhXAiT+L+Ajo6Ovv/+e9u2ibmKouB47Fs/VUqpqiqCBfiUZxbjCXkNtwKFq6pC/knTtE5/8aW/h8Phd9995zgOXMsY0zQN2SoIgv1+HwQB+Gjbdq/Xq6qKVApKCN3P85z8CGfhYAQBLKTrOnn5CdBntmk2m2dnZ4ACY6iqGkXR5eXl/f19EARRFMVxbJrmYDAYDoc//PCDbdsQurIswzAkXud5zhgDVjwhTMQwwzA6nc5yufzEZTAjfjEajTRNA+SiKOI49jzvn3/+CYJA13XXdRuNBrwDMuJzWZac8zRNN5tNURT7/X4+n+OVbrfbaDTG47FpmpzzuuM455ZlDQaD9XodBEGSJE8WIkCGYdi2DaJIKe/u7ubzOWOs3+//+OOPg8FASrnf733fR9WhKEoURZZlIR/leb5arVarVRiGi8UiDMM4jqFhx8fH7969a7VaeIsCkHPuuu54PL6/v38CBAvZtn04HBRFIUWuqkrX9fPz8+FwaNs2DoNHpJRBEGiaZhjG/f29bduWZZVlGUURKGIYxmQy2W63nPPhcNhut4UQi8Xi6upKVdXpdNpsNkmuGGOtVsswjI+k5pyPRqPZbKYoClQHugwj+75/fX29Xq/DMISnXNd1XdfzPM65bduDwaDb7YLyvu+7rlsURVEUw+HQcRx822g08jxfLBbz+Xw2mw0GAwg0xSwJm4CiAC9JO0qLKIpubm5ub29N03z//v2vv/4KU202G9d1HcdJkqQoiizLsEMcx2maxnEchiHqtdvb27/++kvX9X6///Lly06nc35+HkURigtit5QyyzKFsn1VVYfDAeGN0HUcxzCM3W6nadrp6SnnPIqio6Oj9XpdVdUvv/wymUz++OMPugySWpZlpEaIj9lshors9vb28vKy1WqdnZ2NRiPbtinQyrJEzlEUZTqdPgEqy7LVakEGDcOwLAtlEIiMS1xcXJycnHDOwzD87bffsKOqqkRq4LMsK4qiZrM5Ho97vd7j4yNj7PT0NIoi3/cvLy+DIHj79q1t2/AswjPLsul0+v79+4/1zYsXLwAZ9bKU0jAM1FPwNArLw+Hg+z5cHMex67qapqVpissA4ng8zrLs7u7u+Pj47du3ZVm2220qTXEHSB0e4tA3b95IKT8qdbPZxK+p4ELyQ9zhZ6ZpWpYF9mw2G1TyCGxIkW3b7XY7jmPLsgzDaDabUHzluUwjvtbLBM756elpu91WVVXgKfJRvcygUoFEHBtxznVdl1JqmgYVRpaF5KAl6na7SZJATdAYIRViE0VRUPYDn6IopmmiKH0Ke8A/HA5FUTiOAzYADRgHqpItkRwQBPCylBLSats2XjFNE4dlWUalJnyKHEdlHbksSZJOpyNoR3yNs6F+OJtMhbQPI6VpivMMw9B1nTA5joM2kroOEhucTQEF7cFDy7LorY+AkiRpNBqoGXBdiCRyMjU9EOIgCIAJz5Xnki1N02az2Ww2VVWFDbADpAG6gHvCfViO46RpappmGIaC0koQBC9fvkQEUrYH+whZWZaqqoZhuNls8jxvtVq9Xs+2bRI3qCIUhMpWfCbvK88lOYwK+/m+r+v6er0WxPM0TbfbLYq3oiiQXOAjCCv46Hne1dUVoqnf7x8dHcFrIIdlWcisvV4PsQ3W53lePK/PmpM4jufzebvdLopiuVwKynBFUXie12q1KO4oLtI0JUPe3d3lee55Hkp03/c7nQ5J1H6/tywLQoWOAj5Fi0JcJjqCGKenp7Zto8gRJOFxHK9WK7gf3qlXkpScYZLNZuN5Hrr3qqqSJLm5uTkcDlVV9ft9zCTQnqOno5EGhRX1dIwxFBHX19dlWQoyIG6JN0kYwQBwCIAcx4HANBoN1EaoCIQQx8fHkE1oDygM7rPndpYSO8UdCpvD4RAEwVOUQe8ph9ATap+pf4DjNU1DMdRqteI4fnx81HV9MplAlJF2yrIEscBIypIUXETzLMsOh8N6vQa7P3YdJNPUo/DnhV3Y85AF0qzruuM41GoRf0k4AJpuy2qtUv3QDx8+PDw8kHYIKijhEVAPjqMJEG6saRqqljzPD4cDtWZIwIhn8JeqHEosqEkIEE7knOd5nqYpQhvOEdQT1XWdLkHlLIXhYrHY7/cUINBGVJg4z7IslG8wHg6jgKUNEWtxHENTPgJSaosxhiIQ7ke6FULkeS6lnM1mv//++7///ntxcfH69evxeLzb7RhjsBbonyTJcrmMosg0zdevX7948QLtETxSz99wNASCmF5V1cfGFOxJkiQIAsMwoKSUetM0hadN0+x0Ohg5MsaOj4/3+z1xYrPZ/Pnnn1dXV9fX18vl8qeffhoMBpAi0BFzSDoxDEMgph0+ChRekFJ6nkcKJqVE3HLOu92uruuDwUDXdUwtfd9/eHgIggADVzQCjUbj22+//fnnn33fX61WSZIABNmGRChJkv1+TxLwRPO6+oE62+32+PjYNE34TlXVJEk4571e7+Tk5Obm5sOHD8vlErgbjUa73cZUBVEjpfR9fz6fv3r1ajKZoNpHoGRZBj/grNVqFUURhfBTw1+XQeW5cd5ut67rQidN08QVq6o6OTnp9/vr9Xq3283ncyHEdru9u7vDi1mWQVQYY0dHR+/evXNdFywuigLqT1msKIr7+3uyGUWSoAisf3h4eJhMJlmWpWna6/XSNIWsFUXRbrcHgwFkPUkSKpvQ3iPrYeqDs1Em0KAdv9c07ebmBo2lUhsjVVUlCGB97BIEwWq1Go/HQRCga0ZNgpshrTYaDfBReW4NKInCVBAk9jxvQAkFiJ7noS8l/aPI5yRC7NM1m80wh8dogtSS9BrXhVFhAAzCAQVnIOvZto1SiYrSv//+G7YkNERiXn06KyU9TNN0sVhkWbZarTzPA1shHphc1TMGuZu6A0xqkT2klGEYojjG/0C22209ddYd94lhKPjxASMSKeVisdjtdsjMlJJolluvx7Msq5cZmAw9Pj5iLkD5n8asrNbVPCk1ocFG9cxXVRUSTVEUq9UKyVzXdVT1pmmiGKJQQFaXzwuJCLfSNC1JEqCnVoL8RVqo0NDzS6QwPmiLG+P/OlEUwQxgFb2IJErjbMZYnue+78dxXFXV4XCgRsyyLOjTZydiq/8BNmpmCwwYPosAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBC4BF9C490>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B88tJpz65aIl",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "cdb2a6aa-c2de-4b1a-9394-89e90abdaa40"
      },
      "source": [
        "cv2_imshow(images[40])"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBC4249F750>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VkzhBnKj5tu5"
      },
      "source": [
        "#### Contempt"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z-k3qsf-5eEO",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "f0643f13-1a04-4969-d41f-991e275c167a"
      },
      "source": [
        "cv2_imshow(images[82])"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBC4249FF90>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yWnfH_p_5zGs"
      },
      "source": [
        "#### Happy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4od79JNf5wXz",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "015cf361-b21a-4bb0-ab8e-859e07db6943"
      },
      "source": [
        "cv2_imshow(images[200])"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAADAAAAAwCAIAAADYYG7QAAAPaElEQVR4nE1YWW/bVhMlLy/3RaQsarcUO3Zqu0XSIkGAoEVf+j/6R4sCQY02aNGki5EFdZxYljdZEsVF3Lfv4aT6yidZtnnnzpw558yw33///atXr1zXLYqCZdm6rnmeZxiG5/ksywghlFJZlkVR3NnZefbsmW3bhmGoqmoYhiRJlmUZhkEIYRimLMs4jvM8x4fVanV7e7tcLieTyV9//eU4jud5SZKUZYmDKKV5nmdZZllWmqY8zxNC6Hw+v7u7q6qK53me5+u6zrIsyzLbtvM8L4pCEIStra1Go/Ho0aN79+4JgmBZliRJmqbJsmwYhiAILMtSSnmebzQaQRDkeS5JEiFElmVJkhzHwffdbvfq6qqqqqIoCCFFUeD+nufxPM9xnCzL9OrqCtExDJPnOcMwoihSSouiiOOYEGJZVrvdlmVZVdUkSZAbpEeWZVmWWZblOI5lWYZhCCGapq3Xa5Zl2+32fD7vdDpxHGua9ueff15cXKiqKghCEARFUVBKOY6rqqosS8uywjCMoojOZjOO4wghVVXhogzDsCxblmVd18PhsNvtsixrWRbP82ma1nVd/vukacpxnKIodV2jCmVZZlmW53mSJMg0cqxp2sHBwWKxIISsVqsoisqyLIpCURSGYfCPDMMwDEOzLNsUCzgoy1KSpLIsVVVtNpvIKs/zZVkikUVR5HmOlOR5nqYpkkQpxavTNA3DMAiCNE2jKEIasiyTJIlhGMMwoihCNVzXbbfbDMOEYYiyUtysqipCCI6s61oUxTiOdV0HbE3TRCjIHwICBlmWTZJkU2hEryhKWZZhGAJYURQJgiCK4uHh4Ww2y7IsjuOyLIMgYBhmk3WWZYuioFVVcRxX13Vd13mey7KcJElVVWmatlqtRqPRbDY1TVMURVVVnucppZRSURTRhgzDcByHWPM8x9t0XY/jWBTFqqoopZqmAQO2bauqulwup9NpGIaAWpZlqqriRLycIkOAGKCD4BCNJEmKomxiQs8rigLo4H6U0iiK6rqWZZnn+U0chBB0kyiKSGGn06nrGhGglGmaapqW57miKEmSUEIIIkiSBCUAIAghjUZDVVVEjG/ASYqi4GBUEMgFSpB2Qoiqqohmc7AoimVZCoJgGEaz2Tw/PxcEIU3TLMsEQSjLEjHRT9imtCgKAFxRFCBUlmVKqSAIm6KoqmqaJqUUvYpCFEWBxsSD1uM4DjGt12sAVJIklNg0zX6/P5lMgiBALsMwBGx4nqcgD1QKB6NpNU0zTVOWZfDVpucppYSQNE2rqkKngBhZlhUEged5wBzAR7YIIYZhyLLsum4cx2maDgaDwWBweXlZliX4syiKIAja7TYtyxJI4jiuKAp0O8uyiqIgoGazads2x3FRFKVp6nleu93O8zwIAvA1IQRJRZ7Qhr7vJ0mi67qiKLZta5oGsEdRtFwuy7JstVobwsuyDJQriiLdkFJVVfgLdGmn0zFNU1GU/7IOy7K+7xNCBEEIw9D3/Uajgfug9FVVXV1dua6LxCyXS9/3GYaZzWbL5dJxnLqubdvWdX1/fx8dDWoAF4iiSDcMi/PQ0kVRNBqNi4uL2WyGLyml7XZ7OBxqmtZqtVRVret6Pp/nef7ZZ5/VdR1F0Wq1yrLs7OwMPDSfz29vb9+8eQOhhMZVVWVZ1s7OzmAw2N7efvfuHcdxoCVRFAkhn24miiKaBSXQNG21Wn348AENDw0/PT2VZbnX6+3u7na73Xa7HUXR33//HYbh/v6+53k//fRTnufdbne1Wp2eni4Wi+l06nkeJKLf7zebTUJIFEUnJyfr9Xo8HgP+kiShS9A6FKyDZhEEAW1VFEWz2ez1erZtl2W5Wq3m8/lisXj37t3V1dVwOHz06JEgCNfX17IsdzodTdO++OKLH3744fz83Pf92WwGkI3H452dnaOjo36/n+c5PMl8PkdBTNMEFUVR1Gq1JEmi8Bscx4miGIYhnEOapoqitFqt3d1d6N9oNGJZ9vr6ejqd+r6/WCx+/vnn7e3tr7/+emdnRxAESZL29vZUVT0+Pn7x4oUgCIeHh/fu3bMsy7IsRVE8z0Of27aNCvI8j/6v61rX9fV6rWkahSajswCgsiw3yv/hw4cwDEVR7Pf729vbdV0TQrrdLjDU7/f/+eefDx8+GIYBzSrLMkkS3DVJkrdv34qiuLe39/DhQ0rp2dnZ3d2dIAjD4RA0u729vVgsgO52u11VFbu1tZXnuaZpDMP4vn/v3r08zzmO63a7aGCO48B1G2cSRRH4hlL61VdfPXv27OHDh7Is39zc/P777ycnJ9fX15B0cFUcxyB6lmVt2yaE5Hm+s7PT7/dPTk5+/PFHQRCm06lpmpqmUUTKMEwcxzgDTOP7fhAEYRjWdd3pdObzeRAEg8Hg4OAgDMP5fD4YDLrd7oMHD3q9HtyS4ziwY7u7u4vF4vj4mBDS6XRubm5msxla5/Xr15qmdTody7IGg4FlWdAi6Hqe55Rl2Y33gMrKsgx9YBgG6iGK4tHR0d7e3nA4lGW5LEu4iAcPHhweHnY6HbhS9JFt2x8/frRt++nTp2i30WhUlqXjOOAzeOKtrS1FUSzLqqrKcRxFUT5hCKQkSRJQBjPaarUgHVVV6bouCIKqqpZlFUWxWq0ajcbR0ZGqqtvb28PhEEXHXOB5Xq/X29ra8jxvvV5DDQDTTqeTpinExLbtRqPRarWqqtra2uI47u7ujmVZSZIoyowrAqo8zyMamOgoitbrteM4s9lsNBqNx2NgFrmklKZpqqoqx3G+73e73SAITk9POY7rdDqwe9PpdLFYpGmq63qz2Wy1WhhdGIZpNpu6rp+dnXEclyRJHMcUtgi2YaMeEPZms9npdBClJEm6ridJAnv64sULjuMEQdjd3Q3DUJZlQgjHcTzP+77/7t276XT63Xff7ezsjMfjMAyhNhzHZVkGykYWoJi6rt/d3YmiaNs2ZVkWSg5XCiURRVFRFEgjZgxZliGBlNKLiwvXdR8/fgyHz/M8SFVRFEj3N9988/79++PjY0mS9vf3TdME5eZ5Xte1ZVmr1Wq5XMK7bW1twSfBhlMYPBAMy7JxHMOXEULiOA7DUNd1uKUkSSRJWq1Wrus+ffr08PAQDl+SJEgvHl3XRVEcjUaO4/zyyy+GYezt7SF/VVXFcQzlwjewALquw6xKkkQQymY+QhfANGKshHDGcYzZz3GcNE2bzSalNI7j09NTeHU8ZVlGUSSKIlrJcZz379+vViv8lhCCvkEuYQllWYaE53keRRHFSRhWgEHcGx6vqqowDLMsMwyjqqogCBaLRVEUp6eny+WSYZjlcslxnGmaKNZsNptMJvP5fDqdtloty7LOzs4GgwEyAXJBA0Euceder3dxcYHC0U11Aaa6rtfrdRzHsJ4QhE9TN6WO40RRNBgMXr16dXl5Ce2Moqjf7+Ow8/Pz58+fTyaTBw8e2LZ9cHDw+vXri4sLwzDQPXmer9frNE1d1wVUXNedzWbwiZ7nfbIfGLOrqqqqynVdx3FgvDFWiqIIlHieJ0lSv98/OzvDXPDrr7+GYfjll1/Cvx4fH3Mc9+23396/f1/TtH6/z7Ls5eXlxcWFruvAK1zser0Ge02n07IsIeGWZVG4a/A1yDrLssViIYoiQiyKAuyMAaPRaIiieP/+fawNms3mYrF48+aNqqoMw+zt7R0cHACCUPXxeAw3kmUZJpD/ztqe593e3iZJAhB7nvdp1oSUAEYMw6xWK9M0kUakTRAE2HtFUViW7fV6T548mUwmgKDrumEY9vv9wWAQx7FpmrZty7IMmA8Gg/Pzc9d1BUEAkDfQvL29hdqjAoIgfJKONE0xaGLqAIwIIRiH4cORKjRdVVXj8di2beAXY2Gz2XRdd3t7u9vtFkURRRGSyvO8aZqr1Qo2ME3TNE2xQ7q6uoJkIR3r9ZoSQkRRxJYJz6YDRVFMkgQcD3YA2pBz0zTH4/FoNNrd3Y2iCANuv98HDcLbY+2CvAZBgFtBIuq6xpiQJAnGm09dBoKGz8doBnXDTAmwI5+AF+5nGIbneR8/fgTfw+w6jvP27dvpdAqWH41GdV17nkcpxboCTosQAnrL89z3/bIsfd/H0XBdFHNdFEXQBzAEooFQY6OF4LIsQ3vDGfq+jw7q9/tYIbRarSAILi4ufvvtt88//xzzGvYNm00LTB9ksaoqrDGQCIr2kWU5CAIMABivMCPDfhuGkSQJVkSXl5fz+TxNU5g4HHB3dzeZTBRF2YzrePvLly95nh+NRoAExkKYkLquISO4sCRJMA6feAh0DvHbrGrwGQBHlCzL3tzcXF1d2bbNsqyqqqPRyDCMbrfbaDSAsCRJgiC4vLycTCbn5+fr9Xp3dzdJErAOEoPOxSgM+q3/ff6//ciyDAPeZoWACJIkcV0XPK4oyv7+/tHRUVVVo9FoNBph6uv3+wBZURSe552cnPT7/eFw+OzZsyRJ5vO553lAD1LCMEwURUEQoBPheVABivbDsifPc/AhNp5xHKPPkyRZr9eUUsMwxuMxz/M3NzevX78+Pz/HHAODxrLscrmM4xibHcMwsINrtVpYO6N5EVAcx77vY7MmiiIyJ0kSFQQBmQRlg+hQJngPQRAgZ7hWo9FYrVZYJFRVdXZ29vLlS+g5uqnX6+m6rqoquK3T6YRh6Hke2AQHIyDP8zCR+b5PKcWUTMDCkE8Qq2maIHi4DpQP03QQBOv1GvYPApymqSAIpmk2Gg0s0bEah1nAihhslCRJGIbg2yiKMMY4jrNpQ7AAhS/BK0Bi2AYlSZIkCVbaAJMsy+v1erlcbkYRlJ/neaz6FEXBAKOqKnRjuVyi3Ggu8Etd10EQuK7red5mzHJdF9MzlSQJvAmSgOzhvfiMJSuWJnDH2AqC/TAtgfvRiTzPY6u8WCyw1gQFbGg2iiLHcRzHwW/LskQoYG2KDGMHGIYhBvssyzbLfMhCURTIH66LhQacIbZViqIgOCwb8RIw8sZK4HjXdefzueM4+H5zeZxIQaCwcGhyOFpYbBDjZq8LGgTvYWsBNRgMBuhT9EcQBEmSYL8JFKJzoW43Nzd3d3dZlj158uSPP/7A3n0TN2FZFv4LP2MOZ1kWFhE9D4KHF0C74QDIZJIkvu87jnNzc3NzcwNHAXHFVgTsDzG/vr5eLBYoYrPZfPz48WZSQAoIagHMboQGIcIAoXBAAAJFxCgTIOg4znK5RA8CyLgPbAmIOE3Ty8vL2WwGHeV5/vnz55Zl6bq+GQaTJPkfav77nBHYKZwAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBC424A8810>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jH0H70hf58OZ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "54f5d757-b261-4c6a-94f6-2f67d8a34d43"
      },
      "source": [
        "cv2_imshow(images[300])"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBC424AE090>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jPDUU8eI7CRB"
      },
      "source": [
        "import tensorflow as tf\n",
        "from sklearn.model_selection import train_test_split"
      ],
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2AazMQza7-KX"
      },
      "source": [
        "import numpy as np\n",
        "images_f=np.array(images)\n",
        "labels_f=np.array(labels)\n",
        "\n",
        "images_f_2=images_f/255\n"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w3aEjV3oFGKs",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 65
        },
        "outputId": "93d2b5a0-59b7-40d0-de88-a14f7d0d918a"
      },
      "source": [
        "cv2_imshow(images[300])"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBFE6EC090>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "urhM93muFJE8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "426d1164-4c98-422e-8ed2-83f8176f35f4"
      },
      "source": [
        "images_f_2.shape"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(981, 48, 48, 3)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9XDADyGeFNEY"
      },
      "source": [
        "num_of_classes=7\n",
        "labels_encoded=tf.keras.utils.to_categorical(labels_f,num_classes=num_of_classes)\n",
        "\n"
      ],
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5BOhWJ44FvH8"
      },
      "source": [
        "X_train, X_test, Y_train, Y_test= train_test_split(images_f_2, labels_encoded,test_size=0.25)\n",
        "\n"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XwP_RGvUGt0h"
      },
      "source": [
        "#### Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YESdhmIpGKAQ"
      },
      "source": [
        "from tensorflow.keras.layers import Dropout\n",
        "from tensorflow.keras.layers import Flatten,BatchNormalization\n",
        "from tensorflow.keras.layers import Dense, MaxPooling2D,Conv2D\n",
        "from tensorflow.keras.layers import Input,Activation,Add\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.regularizers import l2\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "def Convolution(input_tensor,filters):\n",
        "    \n",
        "    x = Conv2D(filters=filters,kernel_size=(3, 3),padding = 'same',strides=(1, 1),kernel_regularizer=l2(0.001))(input_tensor)\n",
        "    x = Dropout(0.1)(x)\n",
        "    x= Activation('relu')(x)\n",
        "\n",
        "    return x\n",
        "def model(input_shape):\n",
        "  inputs = Input((input_shape))\n",
        "  \n",
        "  conv_1= Convolution(inputs,32)\n",
        "  maxp_1 = MaxPooling2D(pool_size = (2,2)) (conv_1)\n",
        "  conv_2 = Convolution(maxp_1,64)\n",
        "  maxp_2 = MaxPooling2D(pool_size = (2, 2)) (conv_2)\n",
        "  conv_3 = Convolution(maxp_2,128)\n",
        "  maxp_3 = MaxPooling2D(pool_size = (2, 2)) (conv_3)\n",
        "  conv_4 = Convolution(maxp_3,256)\n",
        "  maxp_4 = MaxPooling2D(pool_size = (2, 2)) (conv_4)\n",
        "  flatten= Flatten() (maxp_4)\n",
        "  dense_1= Dense(128,activation='relu')(flatten)\n",
        "  drop_1=Dropout(0.2)(dense_1)\n",
        "  output= Dense(7,activation=\"sigmoid\")(drop_1)\n",
        "\n",
        "  model = Model(inputs=[inputs], outputs=[output])\n",
        "\n",
        "  model.compile(loss=\"categorical_crossentropy\", optimizer=\"Adam\",\n",
        "\tmetrics=[\"accuracy\"])\n",
        "  return model"
      ],
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "F6_MmJqTGb4Z"
      },
      "source": [
        "Model=model(input_shape = (48,48,3))"
      ],
      "execution_count": 24,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YP8Y6mNwGl-k",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9ce6579e-d5bb-45de-be56-c7717bd6ad9d"
      },
      "source": [
        "Model.summary()"
      ],
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"model\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "input_1 (InputLayer)         [(None, 48, 48, 3)]       0         \n",
            "_________________________________________________________________\n",
            "conv2d (Conv2D)              (None, 48, 48, 32)        896       \n",
            "_________________________________________________________________\n",
            "dropout (Dropout)            (None, 48, 48, 32)        0         \n",
            "_________________________________________________________________\n",
            "activation (Activation)      (None, 48, 48, 32)        0         \n",
            "_________________________________________________________________\n",
            "max_pooling2d (MaxPooling2D) (None, 24, 24, 32)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_1 (Conv2D)            (None, 24, 24, 64)        18496     \n",
            "_________________________________________________________________\n",
            "dropout_1 (Dropout)          (None, 24, 24, 64)        0         \n",
            "_________________________________________________________________\n",
            "activation_1 (Activation)    (None, 24, 24, 64)        0         \n",
            "_________________________________________________________________\n",
            "max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_2 (Conv2D)            (None, 12, 12, 128)       73856     \n",
            "_________________________________________________________________\n",
            "dropout_2 (Dropout)          (None, 12, 12, 128)       0         \n",
            "_________________________________________________________________\n",
            "activation_2 (Activation)    (None, 12, 12, 128)       0         \n",
            "_________________________________________________________________\n",
            "max_pooling2d_2 (MaxPooling2 (None, 6, 6, 128)         0         \n",
            "_________________________________________________________________\n",
            "conv2d_3 (Conv2D)            (None, 6, 6, 256)         295168    \n",
            "_________________________________________________________________\n",
            "dropout_3 (Dropout)          (None, 6, 6, 256)         0         \n",
            "_________________________________________________________________\n",
            "activation_3 (Activation)    (None, 6, 6, 256)         0         \n",
            "_________________________________________________________________\n",
            "max_pooling2d_3 (MaxPooling2 (None, 3, 3, 256)         0         \n",
            "_________________________________________________________________\n",
            "flatten (Flatten)            (None, 2304)              0         \n",
            "_________________________________________________________________\n",
            "dense (Dense)                (None, 128)               295040    \n",
            "_________________________________________________________________\n",
            "dropout_4 (Dropout)          (None, 128)               0         \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 7)                 903       \n",
            "=================================================================\n",
            "Total params: 684,359\n",
            "Trainable params: 684,359\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Em_s679QGyOs"
      },
      "source": [
        "#### Training"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GPf8o5TRGpZg"
      },
      "source": [
        "from tensorflow.keras.callbacks import ModelCheckpoint"
      ],
      "execution_count": 26,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ltft2Z6bG2eS"
      },
      "source": [
        "fle_s='Emotion_detection.h5'\n",
        "checkpointer = ModelCheckpoint(fle_s, monitor='loss',verbose=1,save_best_only=True,save_weights_only=False, mode='auto',save_freq='epoch')\n",
        "callback_list=[checkpointer]"
      ],
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Tf9ZgmksG96G",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7aadae34-ed91-44df-fceb-f092f85e3afc"
      },
      "source": [
        "History=Model.fit(X_train,Y_train,batch_size=32,validation_data=(X_test,Y_test),epochs=1000,callbacks=[callback_list])"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/1000\n",
            "23/23 [==============================] - 8s 278ms/step - loss: 2.1504 - accuracy: 0.2014 - val_loss: 2.0080 - val_accuracy: 0.2683\n",
            "\n",
            "Epoch 00001: loss improved from inf to 2.09961, saving model to Emotion_detection.h5\n",
            "Epoch 2/1000\n",
            "23/23 [==============================] - 6s 256ms/step - loss: 1.9868 - accuracy: 0.2601 - val_loss: 1.8597 - val_accuracy: 0.3577\n",
            "\n",
            "Epoch 00002: loss improved from 2.09961 to 1.96157, saving model to Emotion_detection.h5\n",
            "Epoch 3/1000\n",
            "23/23 [==============================] - 6s 256ms/step - loss: 1.7726 - accuracy: 0.3739 - val_loss: 1.4449 - val_accuracy: 0.5285\n",
            "\n",
            "Epoch 00003: loss improved from 1.96157 to 1.68548, saving model to Emotion_detection.h5\n",
            "Epoch 4/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 1.2902 - accuracy: 0.5920 - val_loss: 1.1077 - val_accuracy: 0.6341\n",
            "\n",
            "Epoch 00004: loss improved from 1.68548 to 1.24043, saving model to Emotion_detection.h5\n",
            "Epoch 5/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.9971 - accuracy: 0.6490 - val_loss: 0.8810 - val_accuracy: 0.7276\n",
            "\n",
            "Epoch 00005: loss improved from 1.24043 to 0.95942, saving model to Emotion_detection.h5\n",
            "Epoch 6/1000\n",
            "23/23 [==============================] - 6s 257ms/step - loss: 0.8207 - accuracy: 0.7330 - val_loss: 0.7428 - val_accuracy: 0.8374\n",
            "\n",
            "Epoch 00006: loss improved from 0.95942 to 0.78528, saving model to Emotion_detection.h5\n",
            "Epoch 7/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.6481 - accuracy: 0.8226 - val_loss: 0.6334 - val_accuracy: 0.8659\n",
            "\n",
            "Epoch 00007: loss improved from 0.78528 to 0.63037, saving model to Emotion_detection.h5\n",
            "Epoch 8/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.5560 - accuracy: 0.8328 - val_loss: 0.6928 - val_accuracy: 0.8049\n",
            "\n",
            "Epoch 00008: loss improved from 0.63037 to 0.48659, saving model to Emotion_detection.h5\n",
            "Epoch 9/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.5806 - accuracy: 0.8404 - val_loss: 0.4757 - val_accuracy: 0.9024\n",
            "\n",
            "Epoch 00009: loss did not improve from 0.48659\n",
            "Epoch 10/1000\n",
            "23/23 [==============================] - 6s 257ms/step - loss: 0.4120 - accuracy: 0.8974 - val_loss: 0.4278 - val_accuracy: 0.9390\n",
            "\n",
            "Epoch 00010: loss improved from 0.48659 to 0.40580, saving model to Emotion_detection.h5\n",
            "Epoch 11/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.3599 - accuracy: 0.9144 - val_loss: 0.4042 - val_accuracy: 0.9146\n",
            "\n",
            "Epoch 00011: loss improved from 0.40580 to 0.38690, saving model to Emotion_detection.h5\n",
            "Epoch 12/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.3176 - accuracy: 0.9360 - val_loss: 0.4083 - val_accuracy: 0.9309\n",
            "\n",
            "Epoch 00012: loss improved from 0.38690 to 0.31751, saving model to Emotion_detection.h5\n",
            "Epoch 13/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.2758 - accuracy: 0.9532 - val_loss: 0.3509 - val_accuracy: 0.9431\n",
            "\n",
            "Epoch 00013: loss improved from 0.31751 to 0.27076, saving model to Emotion_detection.h5\n",
            "Epoch 14/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.2446 - accuracy: 0.9603 - val_loss: 0.3235 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00014: loss improved from 0.27076 to 0.26722, saving model to Emotion_detection.h5\n",
            "Epoch 15/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.2430 - accuracy: 0.9768 - val_loss: 0.3194 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00015: loss improved from 0.26722 to 0.25054, saving model to Emotion_detection.h5\n",
            "Epoch 16/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.2183 - accuracy: 0.9789 - val_loss: 0.3169 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00016: loss improved from 0.25054 to 0.21452, saving model to Emotion_detection.h5\n",
            "Epoch 17/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.2000 - accuracy: 0.9733 - val_loss: 0.3334 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00017: loss improved from 0.21452 to 0.20712, saving model to Emotion_detection.h5\n",
            "Epoch 18/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.2081 - accuracy: 0.9730 - val_loss: 0.3064 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00018: loss did not improve from 0.20712\n",
            "Epoch 19/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.2447 - accuracy: 0.9560 - val_loss: 0.3260 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00019: loss did not improve from 0.20712\n",
            "Epoch 20/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.2370 - accuracy: 0.9573 - val_loss: 0.3425 - val_accuracy: 0.9431\n",
            "\n",
            "Epoch 00020: loss did not improve from 0.20712\n",
            "Epoch 21/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.2146 - accuracy: 0.9782 - val_loss: 0.3058 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00021: loss did not improve from 0.20712\n",
            "Epoch 22/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1692 - accuracy: 0.9945 - val_loss: 0.2948 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00022: loss improved from 0.20712 to 0.17294, saving model to Emotion_detection.h5\n",
            "Epoch 23/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1670 - accuracy: 0.9842 - val_loss: 0.3355 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00023: loss improved from 0.17294 to 0.16965, saving model to Emotion_detection.h5\n",
            "Epoch 24/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1926 - accuracy: 0.9824 - val_loss: 0.2884 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00024: loss did not improve from 0.16965\n",
            "Epoch 25/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1600 - accuracy: 0.9928 - val_loss: 0.2918 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00025: loss improved from 0.16965 to 0.15640, saving model to Emotion_detection.h5\n",
            "Epoch 26/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.1734 - accuracy: 0.9823 - val_loss: 0.2610 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00026: loss did not improve from 0.15640\n",
            "Epoch 27/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1624 - accuracy: 0.9891 - val_loss: 0.2608 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00027: loss did not improve from 0.15640\n",
            "Epoch 28/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1581 - accuracy: 0.9944 - val_loss: 0.2511 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00028: loss did not improve from 0.15640\n",
            "Epoch 29/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1589 - accuracy: 0.9898 - val_loss: 0.2829 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00029: loss did not improve from 0.15640\n",
            "Epoch 30/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.1554 - accuracy: 0.9837 - val_loss: 0.2754 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00030: loss improved from 0.15640 to 0.14967, saving model to Emotion_detection.h5\n",
            "Epoch 31/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1444 - accuracy: 0.9901 - val_loss: 0.2595 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00031: loss improved from 0.14967 to 0.14954, saving model to Emotion_detection.h5\n",
            "Epoch 32/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1405 - accuracy: 0.9931 - val_loss: 0.2574 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00032: loss improved from 0.14954 to 0.13608, saving model to Emotion_detection.h5\n",
            "Epoch 33/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1252 - accuracy: 0.9992 - val_loss: 0.2704 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00033: loss improved from 0.13608 to 0.12425, saving model to Emotion_detection.h5\n",
            "Epoch 34/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1305 - accuracy: 0.9942 - val_loss: 0.2531 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00034: loss did not improve from 0.12425\n",
            "Epoch 35/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1521 - accuracy: 0.9871 - val_loss: 0.2623 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00035: loss did not improve from 0.12425\n",
            "Epoch 36/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1433 - accuracy: 0.9925 - val_loss: 0.2258 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00036: loss did not improve from 0.12425\n",
            "Epoch 37/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1293 - accuracy: 0.9938 - val_loss: 0.2258 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00037: loss did not improve from 0.12425\n",
            "Epoch 38/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1586 - accuracy: 0.9792 - val_loss: 0.2137 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00038: loss did not improve from 0.12425\n",
            "Epoch 39/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1323 - accuracy: 0.9919 - val_loss: 0.2404 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00039: loss did not improve from 0.12425\n",
            "Epoch 40/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.1228 - accuracy: 0.9961 - val_loss: 0.2388 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00040: loss did not improve from 0.12425\n",
            "Epoch 41/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.1163 - accuracy: 0.9959 - val_loss: 0.2466 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00041: loss did not improve from 0.12425\n",
            "Epoch 42/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1348 - accuracy: 0.9872 - val_loss: 0.2276 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00042: loss did not improve from 0.12425\n",
            "Epoch 43/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1187 - accuracy: 0.9945 - val_loss: 0.2442 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00043: loss improved from 0.12425 to 0.11769, saving model to Emotion_detection.h5\n",
            "Epoch 44/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1098 - accuracy: 0.9964 - val_loss: 0.2285 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00044: loss improved from 0.11769 to 0.10746, saving model to Emotion_detection.h5\n",
            "Epoch 45/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1276 - accuracy: 0.9920 - val_loss: 0.2421 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00045: loss did not improve from 0.10746\n",
            "Epoch 46/1000\n",
            "23/23 [==============================] - 6s 258ms/step - loss: 0.1486 - accuracy: 0.9868 - val_loss: 0.2492 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00046: loss did not improve from 0.10746\n",
            "Epoch 47/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1507 - accuracy: 0.9851 - val_loss: 0.2795 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00047: loss did not improve from 0.10746\n",
            "Epoch 48/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1362 - accuracy: 0.9919 - val_loss: 0.2635 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00048: loss did not improve from 0.10746\n",
            "Epoch 49/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1513 - accuracy: 0.9873 - val_loss: 0.2658 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00049: loss did not improve from 0.10746\n",
            "Epoch 50/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1487 - accuracy: 0.9854 - val_loss: 0.2485 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00050: loss did not improve from 0.10746\n",
            "Epoch 51/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1486 - accuracy: 0.9797 - val_loss: 0.2487 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00051: loss did not improve from 0.10746\n",
            "Epoch 52/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1227 - accuracy: 0.9934 - val_loss: 0.2303 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00052: loss did not improve from 0.10746\n",
            "Epoch 53/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1109 - accuracy: 1.0000 - val_loss: 0.2473 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00053: loss did not improve from 0.10746\n",
            "Epoch 54/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1040 - accuracy: 0.9992 - val_loss: 0.2420 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00054: loss improved from 0.10746 to 0.10578, saving model to Emotion_detection.h5\n",
            "Epoch 55/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1091 - accuracy: 0.9964 - val_loss: 0.2856 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00055: loss did not improve from 0.10578\n",
            "Epoch 56/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1175 - accuracy: 0.9899 - val_loss: 0.2948 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00056: loss did not improve from 0.10578\n",
            "Epoch 57/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1243 - accuracy: 0.9904 - val_loss: 0.2540 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00057: loss did not improve from 0.10578\n",
            "Epoch 58/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1532 - accuracy: 0.9845 - val_loss: 0.2183 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00058: loss did not improve from 0.10578\n",
            "Epoch 59/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1168 - accuracy: 0.9941 - val_loss: 0.2695 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00059: loss did not improve from 0.10578\n",
            "Epoch 60/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1126 - accuracy: 0.9936 - val_loss: 0.2362 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00060: loss did not improve from 0.10578\n",
            "Epoch 61/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1251 - accuracy: 0.9914 - val_loss: 0.3303 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00061: loss did not improve from 0.10578\n",
            "Epoch 62/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.1394 - accuracy: 0.9823 - val_loss: 0.2481 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00062: loss did not improve from 0.10578\n",
            "Epoch 63/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1181 - accuracy: 0.9970 - val_loss: 0.2322 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00063: loss did not improve from 0.10578\n",
            "Epoch 64/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1134 - accuracy: 0.9954 - val_loss: 0.2411 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00064: loss did not improve from 0.10578\n",
            "Epoch 65/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1426 - accuracy: 0.9830 - val_loss: 0.2237 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00065: loss did not improve from 0.10578\n",
            "Epoch 66/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1153 - accuracy: 0.9932 - val_loss: 0.2191 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00066: loss did not improve from 0.10578\n",
            "Epoch 67/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1199 - accuracy: 0.9953 - val_loss: 0.2329 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00067: loss did not improve from 0.10578\n",
            "Epoch 68/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1395 - accuracy: 0.9916 - val_loss: 0.2391 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00068: loss did not improve from 0.10578\n",
            "Epoch 69/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1197 - accuracy: 0.9886 - val_loss: 0.2461 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00069: loss did not improve from 0.10578\n",
            "Epoch 70/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1064 - accuracy: 0.9931 - val_loss: 0.2348 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00070: loss improved from 0.10578 to 0.10569, saving model to Emotion_detection.h5\n",
            "Epoch 71/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1055 - accuracy: 0.9931 - val_loss: 0.2322 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00071: loss improved from 0.10569 to 0.10221, saving model to Emotion_detection.h5\n",
            "Epoch 72/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0910 - accuracy: 1.0000 - val_loss: 0.2600 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00072: loss improved from 0.10221 to 0.09060, saving model to Emotion_detection.h5\n",
            "Epoch 73/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0904 - accuracy: 0.9996 - val_loss: 0.2442 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00073: loss improved from 0.09060 to 0.09007, saving model to Emotion_detection.h5\n",
            "Epoch 74/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0905 - accuracy: 0.9959 - val_loss: 0.2149 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00074: loss improved from 0.09007 to 0.08984, saving model to Emotion_detection.h5\n",
            "Epoch 75/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0858 - accuracy: 1.0000 - val_loss: 0.1991 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00075: loss improved from 0.08984 to 0.08371, saving model to Emotion_detection.h5\n",
            "Epoch 76/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0821 - accuracy: 1.0000 - val_loss: 0.2116 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00076: loss improved from 0.08371 to 0.08125, saving model to Emotion_detection.h5\n",
            "Epoch 77/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0796 - accuracy: 1.0000 - val_loss: 0.2060 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00077: loss improved from 0.08125 to 0.07939, saving model to Emotion_detection.h5\n",
            "Epoch 78/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0784 - accuracy: 0.9990 - val_loss: 0.2229 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00078: loss improved from 0.07939 to 0.07862, saving model to Emotion_detection.h5\n",
            "Epoch 79/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0765 - accuracy: 1.0000 - val_loss: 0.2048 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00079: loss improved from 0.07862 to 0.07640, saving model to Emotion_detection.h5\n",
            "Epoch 80/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0736 - accuracy: 1.0000 - val_loss: 0.2113 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00080: loss improved from 0.07640 to 0.07248, saving model to Emotion_detection.h5\n",
            "Epoch 81/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0706 - accuracy: 1.0000 - val_loss: 0.2107 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00081: loss improved from 0.07248 to 0.07078, saving model to Emotion_detection.h5\n",
            "Epoch 82/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0726 - accuracy: 0.9993 - val_loss: 0.1920 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00082: loss did not improve from 0.07078\n",
            "Epoch 83/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0829 - accuracy: 0.9927 - val_loss: 0.2343 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00083: loss did not improve from 0.07078\n",
            "Epoch 84/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1430 - accuracy: 0.9708 - val_loss: 0.2103 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00084: loss did not improve from 0.07078\n",
            "Epoch 85/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1065 - accuracy: 0.9890 - val_loss: 0.1964 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00085: loss did not improve from 0.07078\n",
            "Epoch 86/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0812 - accuracy: 0.9996 - val_loss: 0.2152 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00086: loss did not improve from 0.07078\n",
            "Epoch 87/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0797 - accuracy: 0.9994 - val_loss: 0.2176 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00087: loss did not improve from 0.07078\n",
            "Epoch 88/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0919 - accuracy: 0.9891 - val_loss: 0.2412 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00088: loss did not improve from 0.07078\n",
            "Epoch 89/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0890 - accuracy: 0.9943 - val_loss: 0.2124 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00089: loss did not improve from 0.07078\n",
            "Epoch 90/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1090 - accuracy: 0.9789 - val_loss: 0.2370 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00090: loss did not improve from 0.07078\n",
            "Epoch 91/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0980 - accuracy: 0.9912 - val_loss: 0.1929 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00091: loss did not improve from 0.07078\n",
            "Epoch 92/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0892 - accuracy: 0.9993 - val_loss: 0.2098 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00092: loss did not improve from 0.07078\n",
            "Epoch 93/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0792 - accuracy: 0.9994 - val_loss: 0.2021 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00093: loss did not improve from 0.07078\n",
            "Epoch 94/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0788 - accuracy: 1.0000 - val_loss: 0.2295 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00094: loss did not improve from 0.07078\n",
            "Epoch 95/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0968 - accuracy: 0.9926 - val_loss: 0.2399 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00095: loss did not improve from 0.07078\n",
            "Epoch 96/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0744 - accuracy: 0.9984 - val_loss: 0.2468 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00096: loss did not improve from 0.07078\n",
            "Epoch 97/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0803 - accuracy: 0.9979 - val_loss: 0.1814 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00097: loss did not improve from 0.07078\n",
            "Epoch 98/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1002 - accuracy: 0.9856 - val_loss: 0.2274 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00098: loss did not improve from 0.07078\n",
            "Epoch 99/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1111 - accuracy: 0.9819 - val_loss: 0.1989 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00099: loss did not improve from 0.07078\n",
            "Epoch 100/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0986 - accuracy: 0.9895 - val_loss: 0.2349 - val_accuracy: 0.9472\n",
            "\n",
            "Epoch 00100: loss did not improve from 0.07078\n",
            "Epoch 101/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1223 - accuracy: 0.9797 - val_loss: 0.2224 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00101: loss did not improve from 0.07078\n",
            "Epoch 102/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.1072 - accuracy: 0.9899 - val_loss: 0.2404 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00102: loss did not improve from 0.07078\n",
            "Epoch 103/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1062 - accuracy: 0.9836 - val_loss: 0.2248 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00103: loss did not improve from 0.07078\n",
            "Epoch 104/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1261 - accuracy: 0.9902 - val_loss: 0.2984 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00104: loss did not improve from 0.07078\n",
            "Epoch 105/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1533 - accuracy: 0.9851 - val_loss: 0.2888 - val_accuracy: 0.9431\n",
            "\n",
            "Epoch 00105: loss did not improve from 0.07078\n",
            "Epoch 106/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1497 - accuracy: 0.9837 - val_loss: 0.3997 - val_accuracy: 0.9268\n",
            "\n",
            "Epoch 00106: loss did not improve from 0.07078\n",
            "Epoch 107/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.1333 - accuracy: 0.9895 - val_loss: 0.2206 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00107: loss did not improve from 0.07078\n",
            "Epoch 108/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1106 - accuracy: 0.9933 - val_loss: 0.2372 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00108: loss did not improve from 0.07078\n",
            "Epoch 109/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1073 - accuracy: 0.9947 - val_loss: 0.2389 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00109: loss did not improve from 0.07078\n",
            "Epoch 110/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0987 - accuracy: 1.0000 - val_loss: 0.2607 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00110: loss did not improve from 0.07078\n",
            "Epoch 111/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0911 - accuracy: 0.9982 - val_loss: 0.2633 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00111: loss did not improve from 0.07078\n",
            "Epoch 112/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0911 - accuracy: 0.9973 - val_loss: 0.2572 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00112: loss did not improve from 0.07078\n",
            "Epoch 113/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0846 - accuracy: 0.9989 - val_loss: 0.2407 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00113: loss did not improve from 0.07078\n",
            "Epoch 114/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0887 - accuracy: 0.9981 - val_loss: 0.2333 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00114: loss did not improve from 0.07078\n",
            "Epoch 115/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0954 - accuracy: 0.9925 - val_loss: 0.2325 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00115: loss did not improve from 0.07078\n",
            "Epoch 116/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0799 - accuracy: 1.0000 - val_loss: 0.2193 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00116: loss did not improve from 0.07078\n",
            "Epoch 117/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0922 - accuracy: 0.9969 - val_loss: 0.2291 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00117: loss did not improve from 0.07078\n",
            "Epoch 118/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0838 - accuracy: 0.9990 - val_loss: 0.2304 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00118: loss did not improve from 0.07078\n",
            "Epoch 119/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0767 - accuracy: 0.9998 - val_loss: 0.2313 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00119: loss did not improve from 0.07078\n",
            "Epoch 120/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0770 - accuracy: 0.9997 - val_loss: 0.2407 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00120: loss did not improve from 0.07078\n",
            "Epoch 121/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0717 - accuracy: 1.0000 - val_loss: 0.2260 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00121: loss improved from 0.07078 to 0.07073, saving model to Emotion_detection.h5\n",
            "Epoch 122/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0689 - accuracy: 1.0000 - val_loss: 0.2393 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00122: loss improved from 0.07073 to 0.06874, saving model to Emotion_detection.h5\n",
            "Epoch 123/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0668 - accuracy: 1.0000 - val_loss: 0.2471 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00123: loss improved from 0.06874 to 0.06709, saving model to Emotion_detection.h5\n",
            "Epoch 124/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0653 - accuracy: 1.0000 - val_loss: 0.2255 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00124: loss improved from 0.06709 to 0.06483, saving model to Emotion_detection.h5\n",
            "Epoch 125/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0654 - accuracy: 0.9996 - val_loss: 0.2050 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00125: loss did not improve from 0.06483\n",
            "Epoch 126/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0664 - accuracy: 0.9991 - val_loss: 0.2278 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00126: loss did not improve from 0.06483\n",
            "Epoch 127/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0748 - accuracy: 0.9952 - val_loss: 0.2520 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00127: loss did not improve from 0.06483\n",
            "Epoch 128/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0811 - accuracy: 0.9892 - val_loss: 0.2377 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00128: loss did not improve from 0.06483\n",
            "Epoch 129/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0677 - accuracy: 0.9973 - val_loss: 0.2397 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00129: loss did not improve from 0.06483\n",
            "Epoch 130/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0740 - accuracy: 0.9929 - val_loss: 0.3107 - val_accuracy: 0.9431\n",
            "\n",
            "Epoch 00130: loss did not improve from 0.06483\n",
            "Epoch 131/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.0952 - accuracy: 0.9760 - val_loss: 0.2056 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00131: loss did not improve from 0.06483\n",
            "Epoch 132/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0749 - accuracy: 0.9944 - val_loss: 0.2147 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00132: loss did not improve from 0.06483\n",
            "Epoch 133/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0852 - accuracy: 0.9897 - val_loss: 0.2299 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00133: loss did not improve from 0.06483\n",
            "Epoch 134/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.1013 - accuracy: 0.9856 - val_loss: 0.2070 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00134: loss did not improve from 0.06483\n",
            "Epoch 135/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1041 - accuracy: 0.9911 - val_loss: 0.2484 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00135: loss did not improve from 0.06483\n",
            "Epoch 136/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0727 - accuracy: 1.0000 - val_loss: 0.2374 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00136: loss did not improve from 0.06483\n",
            "Epoch 137/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0724 - accuracy: 0.9995 - val_loss: 0.2492 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00137: loss did not improve from 0.06483\n",
            "Epoch 138/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0753 - accuracy: 0.9975 - val_loss: 0.2369 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00138: loss did not improve from 0.06483\n",
            "Epoch 139/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0801 - accuracy: 0.9907 - val_loss: 0.2881 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00139: loss did not improve from 0.06483\n",
            "Epoch 140/1000\n",
            "23/23 [==============================] - 6s 261ms/step - loss: 0.1186 - accuracy: 0.9796 - val_loss: 0.2594 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00140: loss did not improve from 0.06483\n",
            "Epoch 141/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.1172 - accuracy: 0.9848 - val_loss: 0.2451 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00141: loss did not improve from 0.06483\n",
            "Epoch 142/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0979 - accuracy: 0.9893 - val_loss: 0.2102 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00142: loss did not improve from 0.06483\n",
            "Epoch 143/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0916 - accuracy: 0.9972 - val_loss: 0.2197 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00143: loss did not improve from 0.06483\n",
            "Epoch 144/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0908 - accuracy: 0.9921 - val_loss: 0.2524 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00144: loss did not improve from 0.06483\n",
            "Epoch 145/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1093 - accuracy: 0.9927 - val_loss: 0.2342 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00145: loss did not improve from 0.06483\n",
            "Epoch 146/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0869 - accuracy: 0.9968 - val_loss: 0.2582 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00146: loss did not improve from 0.06483\n",
            "Epoch 147/1000\n",
            "23/23 [==============================] - 6s 259ms/step - loss: 0.0851 - accuracy: 0.9935 - val_loss: 0.2299 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00147: loss did not improve from 0.06483\n",
            "Epoch 148/1000\n",
            "23/23 [==============================] - 6s 260ms/step - loss: 0.0717 - accuracy: 0.9999 - val_loss: 0.2326 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00148: loss did not improve from 0.06483\n",
            "Epoch 149/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0722 - accuracy: 1.0000 - val_loss: 0.2621 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00149: loss did not improve from 0.06483\n",
            "Epoch 150/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.0696 - accuracy: 1.0000 - val_loss: 0.2544 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00150: loss did not improve from 0.06483\n",
            "Epoch 151/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0677 - accuracy: 1.0000 - val_loss: 0.2615 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00151: loss did not improve from 0.06483\n",
            "Epoch 152/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0645 - accuracy: 1.0000 - val_loss: 0.2549 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00152: loss did not improve from 0.06483\n",
            "Epoch 153/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0634 - accuracy: 1.0000 - val_loss: 0.2723 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00153: loss improved from 0.06483 to 0.06287, saving model to Emotion_detection.h5\n",
            "Epoch 154/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0614 - accuracy: 1.0000 - val_loss: 0.2506 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00154: loss improved from 0.06287 to 0.06112, saving model to Emotion_detection.h5\n",
            "Epoch 155/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0597 - accuracy: 1.0000 - val_loss: 0.2351 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00155: loss improved from 0.06112 to 0.05865, saving model to Emotion_detection.h5\n",
            "Epoch 156/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0642 - accuracy: 0.9964 - val_loss: 0.2313 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00156: loss did not improve from 0.05865\n",
            "Epoch 157/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0562 - accuracy: 1.0000 - val_loss: 0.2312 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00157: loss improved from 0.05865 to 0.05615, saving model to Emotion_detection.h5\n",
            "Epoch 158/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0548 - accuracy: 0.9998 - val_loss: 0.2196 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00158: loss did not improve from 0.05615\n",
            "Epoch 159/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0563 - accuracy: 0.9992 - val_loss: 0.2453 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00159: loss did not improve from 0.05615\n",
            "Epoch 160/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0618 - accuracy: 0.9937 - val_loss: 0.2004 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00160: loss did not improve from 0.05615\n",
            "Epoch 161/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0602 - accuracy: 0.9986 - val_loss: 0.2716 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00161: loss did not improve from 0.05615\n",
            "Epoch 162/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0574 - accuracy: 1.0000 - val_loss: 0.2525 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00162: loss did not improve from 0.05615\n",
            "Epoch 163/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0530 - accuracy: 1.0000 - val_loss: 0.2281 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00163: loss improved from 0.05615 to 0.05318, saving model to Emotion_detection.h5\n",
            "Epoch 164/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0525 - accuracy: 1.0000 - val_loss: 0.2463 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00164: loss improved from 0.05318 to 0.05163, saving model to Emotion_detection.h5\n",
            "Epoch 165/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0512 - accuracy: 0.9998 - val_loss: 0.2214 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00165: loss did not improve from 0.05163\n",
            "Epoch 166/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0647 - accuracy: 0.9940 - val_loss: 0.1882 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00166: loss did not improve from 0.05163\n",
            "Epoch 167/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0642 - accuracy: 0.9976 - val_loss: 0.1796 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00167: loss did not improve from 0.05163\n",
            "Epoch 168/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0553 - accuracy: 0.9974 - val_loss: 0.1768 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00168: loss did not improve from 0.05163\n",
            "Epoch 169/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0516 - accuracy: 1.0000 - val_loss: 0.1939 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00169: loss improved from 0.05163 to 0.05138, saving model to Emotion_detection.h5\n",
            "Epoch 170/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0612 - accuracy: 0.9947 - val_loss: 0.1884 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00170: loss did not improve from 0.05138\n",
            "Epoch 171/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0534 - accuracy: 1.0000 - val_loss: 0.1950 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00171: loss did not improve from 0.05138\n",
            "Epoch 172/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0486 - accuracy: 1.0000 - val_loss: 0.2487 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00172: loss improved from 0.05138 to 0.04840, saving model to Emotion_detection.h5\n",
            "Epoch 173/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0531 - accuracy: 0.9976 - val_loss: 0.2506 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00173: loss did not improve from 0.04840\n",
            "Epoch 174/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.1047 - accuracy: 0.9756 - val_loss: 0.2088 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00174: loss did not improve from 0.04840\n",
            "Epoch 175/1000\n",
            "23/23 [==============================] - 6s 262ms/step - loss: 0.1394 - accuracy: 0.9752 - val_loss: 0.1874 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00175: loss did not improve from 0.04840\n",
            "Epoch 176/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0956 - accuracy: 0.9898 - val_loss: 0.1800 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00176: loss did not improve from 0.04840\n",
            "Epoch 177/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0764 - accuracy: 0.9936 - val_loss: 0.2148 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00177: loss did not improve from 0.04840\n",
            "Epoch 178/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0799 - accuracy: 0.9912 - val_loss: 0.2149 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00178: loss did not improve from 0.04840\n",
            "Epoch 179/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.1139 - accuracy: 0.9827 - val_loss: 0.2281 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00179: loss did not improve from 0.04840\n",
            "Epoch 180/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.1140 - accuracy: 0.9763 - val_loss: 0.2446 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00180: loss did not improve from 0.04840\n",
            "Epoch 181/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.1252 - accuracy: 0.9900 - val_loss: 0.2096 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00181: loss did not improve from 0.04840\n",
            "Epoch 182/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.1251 - accuracy: 0.9747 - val_loss: 0.2075 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00182: loss did not improve from 0.04840\n",
            "Epoch 183/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0760 - accuracy: 0.9991 - val_loss: 0.2654 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00183: loss did not improve from 0.04840\n",
            "Epoch 184/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0928 - accuracy: 0.9934 - val_loss: 0.2077 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00184: loss did not improve from 0.04840\n",
            "Epoch 185/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0849 - accuracy: 0.9961 - val_loss: 0.2163 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00185: loss did not improve from 0.04840\n",
            "Epoch 186/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0748 - accuracy: 0.9998 - val_loss: 0.2300 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00186: loss did not improve from 0.04840\n",
            "Epoch 187/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0759 - accuracy: 0.9983 - val_loss: 0.2299 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00187: loss did not improve from 0.04840\n",
            "Epoch 188/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0727 - accuracy: 0.9993 - val_loss: 0.2435 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00188: loss did not improve from 0.04840\n",
            "Epoch 189/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0736 - accuracy: 0.9987 - val_loss: 0.2380 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00189: loss did not improve from 0.04840\n",
            "Epoch 190/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0680 - accuracy: 1.0000 - val_loss: 0.2535 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00190: loss did not improve from 0.04840\n",
            "Epoch 191/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0660 - accuracy: 0.9993 - val_loss: 0.2260 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00191: loss did not improve from 0.04840\n",
            "Epoch 192/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0670 - accuracy: 1.0000 - val_loss: 0.2689 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00192: loss did not improve from 0.04840\n",
            "Epoch 193/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0624 - accuracy: 1.0000 - val_loss: 0.2286 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00193: loss did not improve from 0.04840\n",
            "Epoch 194/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0609 - accuracy: 1.0000 - val_loss: 0.2364 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00194: loss did not improve from 0.04840\n",
            "Epoch 195/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0586 - accuracy: 1.0000 - val_loss: 0.2539 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00195: loss did not improve from 0.04840\n",
            "Epoch 196/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0584 - accuracy: 1.0000 - val_loss: 0.2549 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00196: loss did not improve from 0.04840\n",
            "Epoch 197/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0599 - accuracy: 0.9951 - val_loss: 0.2804 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00197: loss did not improve from 0.04840\n",
            "Epoch 198/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0552 - accuracy: 1.0000 - val_loss: 0.2257 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00198: loss did not improve from 0.04840\n",
            "Epoch 199/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0532 - accuracy: 1.0000 - val_loss: 0.2404 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00199: loss did not improve from 0.04840\n",
            "Epoch 200/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0528 - accuracy: 1.0000 - val_loss: 0.2373 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00200: loss did not improve from 0.04840\n",
            "Epoch 201/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0503 - accuracy: 1.0000 - val_loss: 0.2395 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00201: loss did not improve from 0.04840\n",
            "Epoch 202/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0500 - accuracy: 1.0000 - val_loss: 0.2359 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00202: loss did not improve from 0.04840\n",
            "Epoch 203/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0487 - accuracy: 1.0000 - val_loss: 0.2363 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00203: loss improved from 0.04840 to 0.04792, saving model to Emotion_detection.h5\n",
            "Epoch 204/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0493 - accuracy: 1.0000 - val_loss: 0.2453 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00204: loss did not improve from 0.04792\n",
            "Epoch 205/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0477 - accuracy: 1.0000 - val_loss: 0.2534 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00205: loss improved from 0.04792 to 0.04783, saving model to Emotion_detection.h5\n",
            "Epoch 206/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0481 - accuracy: 0.9997 - val_loss: 0.2455 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00206: loss did not improve from 0.04783\n",
            "Epoch 207/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0665 - accuracy: 0.9950 - val_loss: 0.2183 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00207: loss did not improve from 0.04783\n",
            "Epoch 208/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0946 - accuracy: 0.9827 - val_loss: 0.2162 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00208: loss did not improve from 0.04783\n",
            "Epoch 209/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0770 - accuracy: 0.9920 - val_loss: 0.2030 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00209: loss did not improve from 0.04783\n",
            "Epoch 210/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0595 - accuracy: 0.9978 - val_loss: 0.2076 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00210: loss did not improve from 0.04783\n",
            "Epoch 211/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0542 - accuracy: 1.0000 - val_loss: 0.2252 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00211: loss did not improve from 0.04783\n",
            "Epoch 212/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0528 - accuracy: 1.0000 - val_loss: 0.2163 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00212: loss did not improve from 0.04783\n",
            "Epoch 213/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0506 - accuracy: 1.0000 - val_loss: 0.2275 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00213: loss did not improve from 0.04783\n",
            "Epoch 214/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0523 - accuracy: 0.9961 - val_loss: 0.2060 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00214: loss did not improve from 0.04783\n",
            "Epoch 215/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0587 - accuracy: 0.9948 - val_loss: 0.2113 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00215: loss did not improve from 0.04783\n",
            "Epoch 216/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0512 - accuracy: 0.9985 - val_loss: 0.2047 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00216: loss did not improve from 0.04783\n",
            "Epoch 217/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0474 - accuracy: 1.0000 - val_loss: 0.2107 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00217: loss improved from 0.04783 to 0.04714, saving model to Emotion_detection.h5\n",
            "Epoch 218/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0460 - accuracy: 1.0000 - val_loss: 0.2035 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00218: loss improved from 0.04714 to 0.04560, saving model to Emotion_detection.h5\n",
            "Epoch 219/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0484 - accuracy: 0.9986 - val_loss: 0.2098 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00219: loss did not improve from 0.04560\n",
            "Epoch 220/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0650 - accuracy: 0.9885 - val_loss: 0.1666 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00220: loss did not improve from 0.04560\n",
            "Epoch 221/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0492 - accuracy: 1.0000 - val_loss: 0.1923 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00221: loss did not improve from 0.04560\n",
            "Epoch 222/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0491 - accuracy: 1.0000 - val_loss: 0.2223 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00222: loss did not improve from 0.04560\n",
            "Epoch 223/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0493 - accuracy: 0.9978 - val_loss: 0.1899 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00223: loss did not improve from 0.04560\n",
            "Epoch 224/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0686 - accuracy: 0.9929 - val_loss: 0.2101 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00224: loss did not improve from 0.04560\n",
            "Epoch 225/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0716 - accuracy: 0.9938 - val_loss: 0.2952 - val_accuracy: 0.9350\n",
            "\n",
            "Epoch 00225: loss did not improve from 0.04560\n",
            "Epoch 226/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.1232 - accuracy: 0.9778 - val_loss: 0.2186 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00226: loss did not improve from 0.04560\n",
            "Epoch 227/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0788 - accuracy: 0.9914 - val_loss: 0.2147 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00227: loss did not improve from 0.04560\n",
            "Epoch 228/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.1394 - accuracy: 0.9715 - val_loss: 0.2225 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00228: loss did not improve from 0.04560\n",
            "Epoch 229/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.1127 - accuracy: 0.9848 - val_loss: 0.2205 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00229: loss did not improve from 0.04560\n",
            "Epoch 230/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0928 - accuracy: 0.9915 - val_loss: 0.1914 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00230: loss did not improve from 0.04560\n",
            "Epoch 231/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0834 - accuracy: 0.9948 - val_loss: 0.2519 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00231: loss did not improve from 0.04560\n",
            "Epoch 232/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0865 - accuracy: 0.9907 - val_loss: 0.2096 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00232: loss did not improve from 0.04560\n",
            "Epoch 233/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0791 - accuracy: 0.9972 - val_loss: 0.2232 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00233: loss did not improve from 0.04560\n",
            "Epoch 234/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0783 - accuracy: 0.9967 - val_loss: 0.1875 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00234: loss did not improve from 0.04560\n",
            "Epoch 235/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0659 - accuracy: 1.0000 - val_loss: 0.2136 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00235: loss did not improve from 0.04560\n",
            "Epoch 236/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0640 - accuracy: 1.0000 - val_loss: 0.2151 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00236: loss did not improve from 0.04560\n",
            "Epoch 237/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0630 - accuracy: 0.9994 - val_loss: 0.2429 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00237: loss did not improve from 0.04560\n",
            "Epoch 238/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0608 - accuracy: 1.0000 - val_loss: 0.2307 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00238: loss did not improve from 0.04560\n",
            "Epoch 239/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0587 - accuracy: 1.0000 - val_loss: 0.2495 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00239: loss did not improve from 0.04560\n",
            "Epoch 240/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0585 - accuracy: 1.0000 - val_loss: 0.2368 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00240: loss did not improve from 0.04560\n",
            "Epoch 241/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0560 - accuracy: 1.0000 - val_loss: 0.2393 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00241: loss did not improve from 0.04560\n",
            "Epoch 242/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0554 - accuracy: 1.0000 - val_loss: 0.2357 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00242: loss did not improve from 0.04560\n",
            "Epoch 243/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0531 - accuracy: 1.0000 - val_loss: 0.2364 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00243: loss did not improve from 0.04560\n",
            "Epoch 244/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0529 - accuracy: 1.0000 - val_loss: 0.2447 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00244: loss did not improve from 0.04560\n",
            "Epoch 245/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0512 - accuracy: 1.0000 - val_loss: 0.2411 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00245: loss did not improve from 0.04560\n",
            "Epoch 246/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0530 - accuracy: 0.9981 - val_loss: 0.2085 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00246: loss did not improve from 0.04560\n",
            "Epoch 247/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0531 - accuracy: 0.9996 - val_loss: 0.2248 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00247: loss did not improve from 0.04560\n",
            "Epoch 248/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0565 - accuracy: 0.9986 - val_loss: 0.2249 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00248: loss did not improve from 0.04560\n",
            "Epoch 249/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0582 - accuracy: 0.9974 - val_loss: 0.2028 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00249: loss did not improve from 0.04560\n",
            "Epoch 250/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0586 - accuracy: 0.9942 - val_loss: 0.1938 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00250: loss did not improve from 0.04560\n",
            "Epoch 251/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0735 - accuracy: 0.9901 - val_loss: 0.2782 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00251: loss did not improve from 0.04560\n",
            "Epoch 252/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0853 - accuracy: 0.9928 - val_loss: 0.2064 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00252: loss did not improve from 0.04560\n",
            "Epoch 253/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0593 - accuracy: 0.9982 - val_loss: 0.2104 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00253: loss did not improve from 0.04560\n",
            "Epoch 254/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0554 - accuracy: 0.9996 - val_loss: 0.1948 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00254: loss did not improve from 0.04560\n",
            "Epoch 255/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0579 - accuracy: 0.9958 - val_loss: 0.1935 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00255: loss did not improve from 0.04560\n",
            "Epoch 256/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0561 - accuracy: 0.9997 - val_loss: 0.1911 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00256: loss did not improve from 0.04560\n",
            "Epoch 257/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.1200 - accuracy: 0.9800 - val_loss: 0.2551 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00257: loss did not improve from 0.04560\n",
            "Epoch 258/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0872 - accuracy: 0.9919 - val_loss: 0.2116 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00258: loss did not improve from 0.04560\n",
            "Epoch 259/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0584 - accuracy: 1.0000 - val_loss: 0.2541 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00259: loss did not improve from 0.04560\n",
            "Epoch 260/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0549 - accuracy: 1.0000 - val_loss: 0.2385 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00260: loss did not improve from 0.04560\n",
            "Epoch 261/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0559 - accuracy: 1.0000 - val_loss: 0.2491 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00261: loss did not improve from 0.04560\n",
            "Epoch 262/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0530 - accuracy: 1.0000 - val_loss: 0.2457 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00262: loss did not improve from 0.04560\n",
            "Epoch 263/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0518 - accuracy: 0.9996 - val_loss: 0.2674 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00263: loss did not improve from 0.04560\n",
            "Epoch 264/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0529 - accuracy: 1.0000 - val_loss: 0.1896 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00264: loss did not improve from 0.04560\n",
            "Epoch 265/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0550 - accuracy: 0.9963 - val_loss: 0.2116 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00265: loss did not improve from 0.04560\n",
            "Epoch 266/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0521 - accuracy: 0.9995 - val_loss: 0.1830 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00266: loss did not improve from 0.04560\n",
            "Epoch 267/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0545 - accuracy: 0.9978 - val_loss: 0.1906 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00267: loss did not improve from 0.04560\n",
            "Epoch 268/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0630 - accuracy: 0.9940 - val_loss: 0.2009 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00268: loss did not improve from 0.04560\n",
            "Epoch 269/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0678 - accuracy: 0.9944 - val_loss: 0.1746 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00269: loss did not improve from 0.04560\n",
            "Epoch 270/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0552 - accuracy: 0.9979 - val_loss: 0.2523 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00270: loss did not improve from 0.04560\n",
            "Epoch 271/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0722 - accuracy: 0.9970 - val_loss: 0.2015 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00271: loss did not improve from 0.04560\n",
            "Epoch 272/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0551 - accuracy: 0.9990 - val_loss: 0.2185 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00272: loss did not improve from 0.04560\n",
            "Epoch 273/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0854 - accuracy: 0.9891 - val_loss: 0.2865 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00273: loss did not improve from 0.04560\n",
            "Epoch 274/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0844 - accuracy: 0.9911 - val_loss: 0.2124 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00274: loss did not improve from 0.04560\n",
            "Epoch 275/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0803 - accuracy: 0.9866 - val_loss: 0.3042 - val_accuracy: 0.9390\n",
            "\n",
            "Epoch 00275: loss did not improve from 0.04560\n",
            "Epoch 276/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.1097 - accuracy: 0.9745 - val_loss: 0.2092 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00276: loss did not improve from 0.04560\n",
            "Epoch 277/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0632 - accuracy: 0.9997 - val_loss: 0.2157 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00277: loss did not improve from 0.04560\n",
            "Epoch 278/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0572 - accuracy: 1.0000 - val_loss: 0.2021 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00278: loss did not improve from 0.04560\n",
            "Epoch 279/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0568 - accuracy: 1.0000 - val_loss: 0.2205 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00279: loss did not improve from 0.04560\n",
            "Epoch 280/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0549 - accuracy: 1.0000 - val_loss: 0.2439 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00280: loss did not improve from 0.04560\n",
            "Epoch 281/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0541 - accuracy: 1.0000 - val_loss: 0.2408 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00281: loss did not improve from 0.04560\n",
            "Epoch 282/1000\n",
            "23/23 [==============================] - 6s 263ms/step - loss: 0.0527 - accuracy: 1.0000 - val_loss: 0.2407 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00282: loss did not improve from 0.04560\n",
            "Epoch 283/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0511 - accuracy: 1.0000 - val_loss: 0.2407 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00283: loss did not improve from 0.04560\n",
            "Epoch 284/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0499 - accuracy: 1.0000 - val_loss: 0.2365 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00284: loss did not improve from 0.04560\n",
            "Epoch 285/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0491 - accuracy: 1.0000 - val_loss: 0.2366 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00285: loss did not improve from 0.04560\n",
            "Epoch 286/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0479 - accuracy: 1.0000 - val_loss: 0.2330 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00286: loss did not improve from 0.04560\n",
            "Epoch 287/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0503 - accuracy: 0.9990 - val_loss: 0.2277 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00287: loss did not improve from 0.04560\n",
            "Epoch 288/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0579 - accuracy: 0.9951 - val_loss: 0.2481 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00288: loss did not improve from 0.04560\n",
            "Epoch 289/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0735 - accuracy: 0.9888 - val_loss: 0.2696 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00289: loss did not improve from 0.04560\n",
            "Epoch 290/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0685 - accuracy: 0.9970 - val_loss: 0.2437 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00290: loss did not improve from 0.04560\n",
            "Epoch 291/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0522 - accuracy: 1.0000 - val_loss: 0.2672 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00291: loss did not improve from 0.04560\n",
            "Epoch 292/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0547 - accuracy: 0.9973 - val_loss: 0.2190 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00292: loss did not improve from 0.04560\n",
            "Epoch 293/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0511 - accuracy: 1.0000 - val_loss: 0.2430 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00293: loss did not improve from 0.04560\n",
            "Epoch 294/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0500 - accuracy: 1.0000 - val_loss: 0.2707 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00294: loss did not improve from 0.04560\n",
            "Epoch 295/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0477 - accuracy: 1.0000 - val_loss: 0.2516 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00295: loss did not improve from 0.04560\n",
            "Epoch 296/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0483 - accuracy: 0.9995 - val_loss: 0.2655 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00296: loss did not improve from 0.04560\n",
            "Epoch 297/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0634 - accuracy: 0.9944 - val_loss: 0.2052 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00297: loss did not improve from 0.04560\n",
            "Epoch 298/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0627 - accuracy: 0.9964 - val_loss: 0.2365 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00298: loss did not improve from 0.04560\n",
            "Epoch 299/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0501 - accuracy: 1.0000 - val_loss: 0.2061 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00299: loss did not improve from 0.04560\n",
            "Epoch 300/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0509 - accuracy: 0.9995 - val_loss: 0.2227 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00300: loss did not improve from 0.04560\n",
            "Epoch 301/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0501 - accuracy: 1.0000 - val_loss: 0.2384 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00301: loss did not improve from 0.04560\n",
            "Epoch 302/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0479 - accuracy: 0.9997 - val_loss: 0.2275 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00302: loss did not improve from 0.04560\n",
            "Epoch 303/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0470 - accuracy: 0.9989 - val_loss: 0.2443 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00303: loss did not improve from 0.04560\n",
            "Epoch 304/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0765 - accuracy: 0.9924 - val_loss: 0.2360 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00304: loss did not improve from 0.04560\n",
            "Epoch 305/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0590 - accuracy: 0.9961 - val_loss: 0.2133 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00305: loss did not improve from 0.04560\n",
            "Epoch 306/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0490 - accuracy: 1.0000 - val_loss: 0.2456 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00306: loss did not improve from 0.04560\n",
            "Epoch 307/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0476 - accuracy: 0.9992 - val_loss: 0.2775 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00307: loss did not improve from 0.04560\n",
            "Epoch 308/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0535 - accuracy: 0.9991 - val_loss: 0.2008 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00308: loss did not improve from 0.04560\n",
            "Epoch 309/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0557 - accuracy: 0.9959 - val_loss: 0.2341 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00309: loss did not improve from 0.04560\n",
            "Epoch 310/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0463 - accuracy: 0.9985 - val_loss: 0.2399 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00310: loss did not improve from 0.04560\n",
            "Epoch 311/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0432 - accuracy: 1.0000 - val_loss: 0.2350 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00311: loss improved from 0.04560 to 0.04316, saving model to Emotion_detection.h5\n",
            "Epoch 312/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0438 - accuracy: 1.0000 - val_loss: 0.2470 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00312: loss improved from 0.04316 to 0.04263, saving model to Emotion_detection.h5\n",
            "Epoch 313/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0420 - accuracy: 1.0000 - val_loss: 0.2385 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00313: loss improved from 0.04263 to 0.04203, saving model to Emotion_detection.h5\n",
            "Epoch 314/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0404 - accuracy: 1.0000 - val_loss: 0.2360 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00314: loss improved from 0.04203 to 0.04043, saving model to Emotion_detection.h5\n",
            "Epoch 315/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0394 - accuracy: 1.0000 - val_loss: 0.2409 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00315: loss improved from 0.04043 to 0.03965, saving model to Emotion_detection.h5\n",
            "Epoch 316/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0391 - accuracy: 1.0000 - val_loss: 0.2444 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00316: loss improved from 0.03965 to 0.03896, saving model to Emotion_detection.h5\n",
            "Epoch 317/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0388 - accuracy: 1.0000 - val_loss: 0.2396 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00317: loss improved from 0.03896 to 0.03875, saving model to Emotion_detection.h5\n",
            "Epoch 318/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0394 - accuracy: 0.9999 - val_loss: 0.2307 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00318: loss did not improve from 0.03875\n",
            "Epoch 319/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0390 - accuracy: 1.0000 - val_loss: 0.2370 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00319: loss did not improve from 0.03875\n",
            "Epoch 320/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0547 - accuracy: 0.9926 - val_loss: 0.2218 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00320: loss did not improve from 0.03875\n",
            "Epoch 321/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0492 - accuracy: 0.9958 - val_loss: 0.2269 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00321: loss did not improve from 0.03875\n",
            "Epoch 322/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0587 - accuracy: 0.9957 - val_loss: 0.2211 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00322: loss did not improve from 0.03875\n",
            "Epoch 323/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0452 - accuracy: 0.9995 - val_loss: 0.2248 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00323: loss did not improve from 0.03875\n",
            "Epoch 324/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0458 - accuracy: 0.9992 - val_loss: 0.2085 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00324: loss did not improve from 0.03875\n",
            "Epoch 325/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0476 - accuracy: 0.9978 - val_loss: 0.2256 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00325: loss did not improve from 0.03875\n",
            "Epoch 326/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0466 - accuracy: 0.9984 - val_loss: 0.2005 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00326: loss did not improve from 0.03875\n",
            "Epoch 327/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0444 - accuracy: 0.9986 - val_loss: 0.2148 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00327: loss did not improve from 0.03875\n",
            "Epoch 328/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0500 - accuracy: 0.9967 - val_loss: 0.2220 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00328: loss did not improve from 0.03875\n",
            "Epoch 329/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0475 - accuracy: 0.9997 - val_loss: 0.2409 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00329: loss did not improve from 0.03875\n",
            "Epoch 330/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0517 - accuracy: 0.9960 - val_loss: 0.2755 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00330: loss did not improve from 0.03875\n",
            "Epoch 331/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0496 - accuracy: 0.9970 - val_loss: 0.2473 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00331: loss did not improve from 0.03875\n",
            "Epoch 332/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0436 - accuracy: 0.9997 - val_loss: 0.2520 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00332: loss did not improve from 0.03875\n",
            "Epoch 333/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0656 - accuracy: 0.9907 - val_loss: 0.2602 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00333: loss did not improve from 0.03875\n",
            "Epoch 334/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0797 - accuracy: 0.9897 - val_loss: 0.2505 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00334: loss did not improve from 0.03875\n",
            "Epoch 335/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0656 - accuracy: 0.9955 - val_loss: 0.2257 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00335: loss did not improve from 0.03875\n",
            "Epoch 336/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0539 - accuracy: 0.9968 - val_loss: 0.2594 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00336: loss did not improve from 0.03875\n",
            "Epoch 337/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0610 - accuracy: 0.9933 - val_loss: 0.2765 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00337: loss did not improve from 0.03875\n",
            "Epoch 338/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0597 - accuracy: 0.9963 - val_loss: 0.2428 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00338: loss did not improve from 0.03875\n",
            "Epoch 339/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0698 - accuracy: 0.9911 - val_loss: 0.2402 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00339: loss did not improve from 0.03875\n",
            "Epoch 340/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0538 - accuracy: 0.9984 - val_loss: 0.1955 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00340: loss did not improve from 0.03875\n",
            "Epoch 341/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0601 - accuracy: 0.9978 - val_loss: 0.2187 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00341: loss did not improve from 0.03875\n",
            "Epoch 342/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0582 - accuracy: 0.9976 - val_loss: 0.2165 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00342: loss did not improve from 0.03875\n",
            "Epoch 343/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0576 - accuracy: 0.9981 - val_loss: 0.2385 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00343: loss did not improve from 0.03875\n",
            "Epoch 344/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0895 - accuracy: 0.9939 - val_loss: 0.2148 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00344: loss did not improve from 0.03875\n",
            "Epoch 345/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0618 - accuracy: 0.9938 - val_loss: 0.2591 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00345: loss did not improve from 0.03875\n",
            "Epoch 346/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0508 - accuracy: 0.9999 - val_loss: 0.2766 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00346: loss did not improve from 0.03875\n",
            "Epoch 347/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0526 - accuracy: 1.0000 - val_loss: 0.2542 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00347: loss did not improve from 0.03875\n",
            "Epoch 348/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0508 - accuracy: 1.0000 - val_loss: 0.2471 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00348: loss did not improve from 0.03875\n",
            "Epoch 349/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0474 - accuracy: 1.0000 - val_loss: 0.2513 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00349: loss did not improve from 0.03875\n",
            "Epoch 350/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0461 - accuracy: 1.0000 - val_loss: 0.2355 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00350: loss did not improve from 0.03875\n",
            "Epoch 351/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0462 - accuracy: 1.0000 - val_loss: 0.2628 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00351: loss did not improve from 0.03875\n",
            "Epoch 352/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0440 - accuracy: 1.0000 - val_loss: 0.2575 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00352: loss did not improve from 0.03875\n",
            "Epoch 353/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0436 - accuracy: 1.0000 - val_loss: 0.2311 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00353: loss did not improve from 0.03875\n",
            "Epoch 354/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0462 - accuracy: 0.9969 - val_loss: 0.2552 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00354: loss did not improve from 0.03875\n",
            "Epoch 355/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0457 - accuracy: 1.0000 - val_loss: 0.1920 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00355: loss did not improve from 0.03875\n",
            "Epoch 356/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0542 - accuracy: 0.9934 - val_loss: 0.1950 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00356: loss did not improve from 0.03875\n",
            "Epoch 357/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0788 - accuracy: 0.9852 - val_loss: 0.2612 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00357: loss did not improve from 0.03875\n",
            "Epoch 358/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0594 - accuracy: 0.9950 - val_loss: 0.2177 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00358: loss did not improve from 0.03875\n",
            "Epoch 359/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0529 - accuracy: 0.9979 - val_loss: 0.2105 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00359: loss did not improve from 0.03875\n",
            "Epoch 360/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0585 - accuracy: 0.9961 - val_loss: 0.2461 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00360: loss did not improve from 0.03875\n",
            "Epoch 361/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0554 - accuracy: 0.9977 - val_loss: 0.2189 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00361: loss did not improve from 0.03875\n",
            "Epoch 362/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0516 - accuracy: 0.9993 - val_loss: 0.2886 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00362: loss did not improve from 0.03875\n",
            "Epoch 363/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0610 - accuracy: 0.9954 - val_loss: 0.2274 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00363: loss did not improve from 0.03875\n",
            "Epoch 364/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0530 - accuracy: 0.9975 - val_loss: 0.2383 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00364: loss did not improve from 0.03875\n",
            "Epoch 365/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0496 - accuracy: 1.0000 - val_loss: 0.2268 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00365: loss did not improve from 0.03875\n",
            "Epoch 366/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0506 - accuracy: 0.9964 - val_loss: 0.2316 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00366: loss did not improve from 0.03875\n",
            "Epoch 367/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0469 - accuracy: 1.0000 - val_loss: 0.2340 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00367: loss did not improve from 0.03875\n",
            "Epoch 368/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0451 - accuracy: 1.0000 - val_loss: 0.2568 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00368: loss did not improve from 0.03875\n",
            "Epoch 369/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0438 - accuracy: 1.0000 - val_loss: 0.2666 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00369: loss did not improve from 0.03875\n",
            "Epoch 370/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0435 - accuracy: 1.0000 - val_loss: 0.2717 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00370: loss did not improve from 0.03875\n",
            "Epoch 371/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0436 - accuracy: 1.0000 - val_loss: 0.2425 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00371: loss did not improve from 0.03875\n",
            "Epoch 372/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0415 - accuracy: 1.0000 - val_loss: 0.2289 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00372: loss did not improve from 0.03875\n",
            "Epoch 373/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0446 - accuracy: 0.9983 - val_loss: 0.2248 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00373: loss did not improve from 0.03875\n",
            "Epoch 374/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0426 - accuracy: 0.9991 - val_loss: 0.2495 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00374: loss did not improve from 0.03875\n",
            "Epoch 375/1000\n",
            "23/23 [==============================] - 6s 264ms/step - loss: 0.0414 - accuracy: 1.0000 - val_loss: 0.2723 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00375: loss did not improve from 0.03875\n",
            "Epoch 376/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0400 - accuracy: 1.0000 - val_loss: 0.2363 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00376: loss did not improve from 0.03875\n",
            "Epoch 377/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0407 - accuracy: 1.0000 - val_loss: 0.2894 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00377: loss did not improve from 0.03875\n",
            "Epoch 378/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0414 - accuracy: 0.9989 - val_loss: 0.2250 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00378: loss did not improve from 0.03875\n",
            "Epoch 379/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0443 - accuracy: 0.9954 - val_loss: 0.2548 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00379: loss did not improve from 0.03875\n",
            "Epoch 380/1000\n",
            "23/23 [==============================] - 6s 265ms/step - loss: 0.0592 - accuracy: 0.9934 - val_loss: 0.2370 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00380: loss did not improve from 0.03875\n",
            "Epoch 381/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0554 - accuracy: 0.9944 - val_loss: 0.2498 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00381: loss did not improve from 0.03875\n",
            "Epoch 382/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0570 - accuracy: 0.9947 - val_loss: 0.2259 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00382: loss did not improve from 0.03875\n",
            "Epoch 383/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0631 - accuracy: 0.9903 - val_loss: 0.2862 - val_accuracy: 0.9472\n",
            "\n",
            "Epoch 00383: loss did not improve from 0.03875\n",
            "Epoch 384/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0663 - accuracy: 0.9886 - val_loss: 0.2316 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00384: loss did not improve from 0.03875\n",
            "Epoch 385/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0547 - accuracy: 0.9934 - val_loss: 0.2098 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00385: loss did not improve from 0.03875\n",
            "Epoch 386/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0527 - accuracy: 0.9981 - val_loss: 0.2105 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00386: loss did not improve from 0.03875\n",
            "Epoch 387/1000\n",
            "23/23 [==============================] - 6s 266ms/step - loss: 0.0476 - accuracy: 0.9985 - val_loss: 0.2276 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00387: loss did not improve from 0.03875\n",
            "Epoch 388/1000\n",
            "23/23 [==============================] - 6s 267ms/step - loss: 0.0467 - accuracy: 1.0000 - val_loss: 0.2154 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00388: loss did not improve from 0.03875\n",
            "Epoch 389/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0421 - accuracy: 1.0000 - val_loss: 0.2274 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00389: loss did not improve from 0.03875\n",
            "Epoch 390/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0450 - accuracy: 1.0000 - val_loss: 0.2574 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00390: loss did not improve from 0.03875\n",
            "Epoch 391/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0411 - accuracy: 1.0000 - val_loss: 0.2293 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00391: loss did not improve from 0.03875\n",
            "Epoch 392/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0412 - accuracy: 1.0000 - val_loss: 0.2435 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00392: loss did not improve from 0.03875\n",
            "Epoch 393/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0398 - accuracy: 1.0000 - val_loss: 0.2433 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00393: loss did not improve from 0.03875\n",
            "Epoch 394/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0403 - accuracy: 1.0000 - val_loss: 0.2489 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00394: loss did not improve from 0.03875\n",
            "Epoch 395/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0387 - accuracy: 1.0000 - val_loss: 0.2401 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00395: loss improved from 0.03875 to 0.03858, saving model to Emotion_detection.h5\n",
            "Epoch 396/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0389 - accuracy: 1.0000 - val_loss: 0.2446 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00396: loss improved from 0.03858 to 0.03813, saving model to Emotion_detection.h5\n",
            "Epoch 397/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0372 - accuracy: 1.0000 - val_loss: 0.2570 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00397: loss improved from 0.03813 to 0.03742, saving model to Emotion_detection.h5\n",
            "Epoch 398/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0690 - accuracy: 0.9927 - val_loss: 0.1757 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00398: loss did not improve from 0.03742\n",
            "Epoch 399/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0470 - accuracy: 0.9975 - val_loss: 0.1942 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00399: loss did not improve from 0.03742\n",
            "Epoch 400/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0417 - accuracy: 0.9986 - val_loss: 0.2071 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00400: loss did not improve from 0.03742\n",
            "Epoch 401/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0370 - accuracy: 1.0000 - val_loss: 0.2175 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00401: loss improved from 0.03742 to 0.03694, saving model to Emotion_detection.h5\n",
            "Epoch 402/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0382 - accuracy: 0.9988 - val_loss: 0.2956 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00402: loss did not improve from 0.03694\n",
            "Epoch 403/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0360 - accuracy: 1.0000 - val_loss: 0.2760 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00403: loss improved from 0.03694 to 0.03575, saving model to Emotion_detection.h5\n",
            "Epoch 404/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0359 - accuracy: 1.0000 - val_loss: 0.2627 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00404: loss improved from 0.03575 to 0.03537, saving model to Emotion_detection.h5\n",
            "Epoch 405/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0345 - accuracy: 1.0000 - val_loss: 0.2460 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00405: loss improved from 0.03537 to 0.03439, saving model to Emotion_detection.h5\n",
            "Epoch 406/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0338 - accuracy: 1.0000 - val_loss: 0.2196 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00406: loss improved from 0.03439 to 0.03404, saving model to Emotion_detection.h5\n",
            "Epoch 407/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0334 - accuracy: 1.0000 - val_loss: 0.2292 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00407: loss improved from 0.03404 to 0.03323, saving model to Emotion_detection.h5\n",
            "Epoch 408/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0329 - accuracy: 1.0000 - val_loss: 0.2329 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00408: loss improved from 0.03323 to 0.03285, saving model to Emotion_detection.h5\n",
            "Epoch 409/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0337 - accuracy: 1.0000 - val_loss: 0.2360 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00409: loss did not improve from 0.03285\n",
            "Epoch 410/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0335 - accuracy: 1.0000 - val_loss: 0.2391 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00410: loss did not improve from 0.03285\n",
            "Epoch 411/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0321 - accuracy: 1.0000 - val_loss: 0.2140 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00411: loss improved from 0.03285 to 0.03227, saving model to Emotion_detection.h5\n",
            "Epoch 412/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0323 - accuracy: 1.0000 - val_loss: 0.2301 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00412: loss did not improve from 0.03227\n",
            "Epoch 413/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2363 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00413: loss improved from 0.03227 to 0.03066, saving model to Emotion_detection.h5\n",
            "Epoch 414/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0306 - accuracy: 1.0000 - val_loss: 0.2203 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00414: loss improved from 0.03066 to 0.03048, saving model to Emotion_detection.h5\n",
            "Epoch 415/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0306 - accuracy: 1.0000 - val_loss: 0.2740 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00415: loss did not improve from 0.03048\n",
            "Epoch 416/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0305 - accuracy: 1.0000 - val_loss: 0.2295 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00416: loss improved from 0.03048 to 0.03007, saving model to Emotion_detection.h5\n",
            "Epoch 417/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0330 - accuracy: 0.9989 - val_loss: 0.1781 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00417: loss did not improve from 0.03007\n",
            "Epoch 418/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0413 - accuracy: 0.9958 - val_loss: 0.1648 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00418: loss did not improve from 0.03007\n",
            "Epoch 419/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0398 - accuracy: 0.9974 - val_loss: 0.2029 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00419: loss did not improve from 0.03007\n",
            "Epoch 420/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0376 - accuracy: 1.0000 - val_loss: 0.2343 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00420: loss did not improve from 0.03007\n",
            "Epoch 421/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0404 - accuracy: 0.9984 - val_loss: 0.2145 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00421: loss did not improve from 0.03007\n",
            "Epoch 422/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0563 - accuracy: 0.9957 - val_loss: 0.2160 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00422: loss did not improve from 0.03007\n",
            "Epoch 423/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0722 - accuracy: 0.9865 - val_loss: 0.2137 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00423: loss did not improve from 0.03007\n",
            "Epoch 424/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0641 - accuracy: 0.9918 - val_loss: 0.2627 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00424: loss did not improve from 0.03007\n",
            "Epoch 425/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.1061 - accuracy: 0.9792 - val_loss: 0.2254 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00425: loss did not improve from 0.03007\n",
            "Epoch 426/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0506 - accuracy: 0.9979 - val_loss: 0.2707 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00426: loss did not improve from 0.03007\n",
            "Epoch 427/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0549 - accuracy: 0.9999 - val_loss: 0.3054 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00427: loss did not improve from 0.03007\n",
            "Epoch 428/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0495 - accuracy: 0.9976 - val_loss: 0.3321 - val_accuracy: 0.9472\n",
            "\n",
            "Epoch 00428: loss did not improve from 0.03007\n",
            "Epoch 429/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.1021 - accuracy: 0.9788 - val_loss: 0.3601 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00429: loss did not improve from 0.03007\n",
            "Epoch 430/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0623 - accuracy: 0.9937 - val_loss: 0.2174 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00430: loss did not improve from 0.03007\n",
            "Epoch 431/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0515 - accuracy: 0.9971 - val_loss: 0.2037 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00431: loss did not improve from 0.03007\n",
            "Epoch 432/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0545 - accuracy: 0.9947 - val_loss: 0.2055 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00432: loss did not improve from 0.03007\n",
            "Epoch 433/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0538 - accuracy: 0.9948 - val_loss: 0.2550 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00433: loss did not improve from 0.03007\n",
            "Epoch 434/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0764 - accuracy: 0.9924 - val_loss: 0.2392 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00434: loss did not improve from 0.03007\n",
            "Epoch 435/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0595 - accuracy: 0.9914 - val_loss: 0.2775 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00435: loss did not improve from 0.03007\n",
            "Epoch 436/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0767 - accuracy: 0.9882 - val_loss: 0.2445 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00436: loss did not improve from 0.03007\n",
            "Epoch 437/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0501 - accuracy: 0.9975 - val_loss: 0.2207 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00437: loss did not improve from 0.03007\n",
            "Epoch 438/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0657 - accuracy: 0.9897 - val_loss: 0.1971 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00438: loss did not improve from 0.03007\n",
            "Epoch 439/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0500 - accuracy: 0.9964 - val_loss: 0.1958 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00439: loss did not improve from 0.03007\n",
            "Epoch 440/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0484 - accuracy: 1.0000 - val_loss: 0.2520 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00440: loss did not improve from 0.03007\n",
            "Epoch 441/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0438 - accuracy: 1.0000 - val_loss: 0.2277 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00441: loss did not improve from 0.03007\n",
            "Epoch 442/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0433 - accuracy: 1.0000 - val_loss: 0.2254 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00442: loss did not improve from 0.03007\n",
            "Epoch 443/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0429 - accuracy: 0.9994 - val_loss: 0.3033 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00443: loss did not improve from 0.03007\n",
            "Epoch 444/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0441 - accuracy: 1.0000 - val_loss: 0.2444 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00444: loss did not improve from 0.03007\n",
            "Epoch 445/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0415 - accuracy: 1.0000 - val_loss: 0.2458 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00445: loss did not improve from 0.03007\n",
            "Epoch 446/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0413 - accuracy: 1.0000 - val_loss: 0.2498 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00446: loss did not improve from 0.03007\n",
            "Epoch 447/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0409 - accuracy: 0.9992 - val_loss: 0.2258 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00447: loss did not improve from 0.03007\n",
            "Epoch 448/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0420 - accuracy: 0.9996 - val_loss: 0.2409 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00448: loss did not improve from 0.03007\n",
            "Epoch 449/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0455 - accuracy: 0.9969 - val_loss: 0.2543 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00449: loss did not improve from 0.03007\n",
            "Epoch 450/1000\n",
            "23/23 [==============================] - 6s 268ms/step - loss: 0.0438 - accuracy: 0.9961 - val_loss: 0.2831 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00450: loss did not improve from 0.03007\n",
            "Epoch 451/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0412 - accuracy: 1.0000 - val_loss: 0.2611 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00451: loss did not improve from 0.03007\n",
            "Epoch 452/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0396 - accuracy: 1.0000 - val_loss: 0.2473 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00452: loss did not improve from 0.03007\n",
            "Epoch 453/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0380 - accuracy: 1.0000 - val_loss: 0.2517 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00453: loss did not improve from 0.03007\n",
            "Epoch 454/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0375 - accuracy: 1.0000 - val_loss: 0.2770 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00454: loss did not improve from 0.03007\n",
            "Epoch 455/1000\n",
            "23/23 [==============================] - 6s 269ms/step - loss: 0.0374 - accuracy: 1.0000 - val_loss: 0.3001 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00455: loss did not improve from 0.03007\n",
            "Epoch 456/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0363 - accuracy: 1.0000 - val_loss: 0.2875 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00456: loss did not improve from 0.03007\n",
            "Epoch 457/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0360 - accuracy: 1.0000 - val_loss: 0.2680 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00457: loss did not improve from 0.03007\n",
            "Epoch 458/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0351 - accuracy: 1.0000 - val_loss: 0.2636 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00458: loss did not improve from 0.03007\n",
            "Epoch 459/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0341 - accuracy: 1.0000 - val_loss: 0.2644 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00459: loss did not improve from 0.03007\n",
            "Epoch 460/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0339 - accuracy: 1.0000 - val_loss: 0.2819 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00460: loss did not improve from 0.03007\n",
            "Epoch 461/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0349 - accuracy: 0.9997 - val_loss: 0.2560 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00461: loss did not improve from 0.03007\n",
            "Epoch 462/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0378 - accuracy: 0.9989 - val_loss: 0.2245 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00462: loss did not improve from 0.03007\n",
            "Epoch 463/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0366 - accuracy: 1.0000 - val_loss: 0.2174 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00463: loss did not improve from 0.03007\n",
            "Epoch 464/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0353 - accuracy: 1.0000 - val_loss: 0.2272 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00464: loss did not improve from 0.03007\n",
            "Epoch 465/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0338 - accuracy: 1.0000 - val_loss: 0.2438 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00465: loss did not improve from 0.03007\n",
            "Epoch 466/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0334 - accuracy: 1.0000 - val_loss: 0.2428 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00466: loss did not improve from 0.03007\n",
            "Epoch 467/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0327 - accuracy: 1.0000 - val_loss: 0.2405 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00467: loss did not improve from 0.03007\n",
            "Epoch 468/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0323 - accuracy: 1.0000 - val_loss: 0.2500 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00468: loss did not improve from 0.03007\n",
            "Epoch 469/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0332 - accuracy: 1.0000 - val_loss: 0.2457 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00469: loss did not improve from 0.03007\n",
            "Epoch 470/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2393 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00470: loss did not improve from 0.03007\n",
            "Epoch 471/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0307 - accuracy: 1.0000 - val_loss: 0.2469 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00471: loss did not improve from 0.03007\n",
            "Epoch 472/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0485 - accuracy: 0.9872 - val_loss: 0.2517 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00472: loss did not improve from 0.03007\n",
            "Epoch 473/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0371 - accuracy: 1.0000 - val_loss: 0.2458 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00473: loss did not improve from 0.03007\n",
            "Epoch 474/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0412 - accuracy: 0.9967 - val_loss: 0.2294 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00474: loss did not improve from 0.03007\n",
            "Epoch 475/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0388 - accuracy: 1.0000 - val_loss: 0.2765 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00475: loss did not improve from 0.03007\n",
            "Epoch 476/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0359 - accuracy: 0.9988 - val_loss: 0.2344 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00476: loss did not improve from 0.03007\n",
            "Epoch 477/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0342 - accuracy: 1.0000 - val_loss: 0.2113 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00477: loss did not improve from 0.03007\n",
            "Epoch 478/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0339 - accuracy: 1.0000 - val_loss: 0.2159 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00478: loss did not improve from 0.03007\n",
            "Epoch 479/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0374 - accuracy: 0.9956 - val_loss: 0.2048 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00479: loss did not improve from 0.03007\n",
            "Epoch 480/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0395 - accuracy: 0.9970 - val_loss: 0.1941 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00480: loss did not improve from 0.03007\n",
            "Epoch 481/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0370 - accuracy: 1.0000 - val_loss: 0.2333 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00481: loss did not improve from 0.03007\n",
            "Epoch 482/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0333 - accuracy: 1.0000 - val_loss: 0.2778 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00482: loss did not improve from 0.03007\n",
            "Epoch 483/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0526 - accuracy: 0.9926 - val_loss: 0.1834 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00483: loss did not improve from 0.03007\n",
            "Epoch 484/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0391 - accuracy: 1.0000 - val_loss: 0.2031 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00484: loss did not improve from 0.03007\n",
            "Epoch 485/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0377 - accuracy: 0.9988 - val_loss: 0.1835 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00485: loss did not improve from 0.03007\n",
            "Epoch 486/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0390 - accuracy: 0.9968 - val_loss: 0.2499 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00486: loss did not improve from 0.03007\n",
            "Epoch 487/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0356 - accuracy: 1.0000 - val_loss: 0.2254 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00487: loss did not improve from 0.03007\n",
            "Epoch 488/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0359 - accuracy: 1.0000 - val_loss: 0.2359 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00488: loss did not improve from 0.03007\n",
            "Epoch 489/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0328 - accuracy: 1.0000 - val_loss: 0.2272 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00489: loss did not improve from 0.03007\n",
            "Epoch 490/1000\n",
            "23/23 [==============================] - 6s 270ms/step - loss: 0.0325 - accuracy: 1.0000 - val_loss: 0.2226 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00490: loss did not improve from 0.03007\n",
            "Epoch 491/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0345 - accuracy: 1.0000 - val_loss: 0.2143 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00491: loss did not improve from 0.03007\n",
            "Epoch 492/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0360 - accuracy: 0.9981 - val_loss: 0.2267 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00492: loss did not improve from 0.03007\n",
            "Epoch 493/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0314 - accuracy: 1.0000 - val_loss: 0.2263 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00493: loss did not improve from 0.03007\n",
            "Epoch 494/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0317 - accuracy: 1.0000 - val_loss: 0.2754 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00494: loss did not improve from 0.03007\n",
            "Epoch 495/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0312 - accuracy: 1.0000 - val_loss: 0.2338 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00495: loss did not improve from 0.03007\n",
            "Epoch 496/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0300 - accuracy: 1.0000 - val_loss: 0.2485 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00496: loss did not improve from 0.03007\n",
            "Epoch 497/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0314 - accuracy: 0.9991 - val_loss: 0.2560 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00497: loss did not improve from 0.03007\n",
            "Epoch 498/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0328 - accuracy: 0.9979 - val_loss: 0.2205 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00498: loss did not improve from 0.03007\n",
            "Epoch 499/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0337 - accuracy: 1.0000 - val_loss: 0.1912 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00499: loss did not improve from 0.03007\n",
            "Epoch 500/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0335 - accuracy: 1.0000 - val_loss: 0.2236 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00500: loss did not improve from 0.03007\n",
            "Epoch 501/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0290 - accuracy: 1.0000 - val_loss: 0.2131 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00501: loss improved from 0.03007 to 0.02925, saving model to Emotion_detection.h5\n",
            "Epoch 502/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0293 - accuracy: 1.0000 - val_loss: 0.2174 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00502: loss did not improve from 0.02925\n",
            "Epoch 503/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0289 - accuracy: 1.0000 - val_loss: 0.2079 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00503: loss did not improve from 0.02925\n",
            "Epoch 504/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0517 - accuracy: 0.9907 - val_loss: 0.2387 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00504: loss did not improve from 0.02925\n",
            "Epoch 505/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0461 - accuracy: 0.9920 - val_loss: 0.2146 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00505: loss did not improve from 0.02925\n",
            "Epoch 506/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0615 - accuracy: 0.9905 - val_loss: 0.2528 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00506: loss did not improve from 0.02925\n",
            "Epoch 507/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0552 - accuracy: 0.9937 - val_loss: 0.2557 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00507: loss did not improve from 0.02925\n",
            "Epoch 508/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0765 - accuracy: 0.9898 - val_loss: 0.2238 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00508: loss did not improve from 0.02925\n",
            "Epoch 509/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0463 - accuracy: 0.9970 - val_loss: 0.2228 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00509: loss did not improve from 0.02925\n",
            "Epoch 510/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0606 - accuracy: 0.9970 - val_loss: 0.2380 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00510: loss did not improve from 0.02925\n",
            "Epoch 511/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0530 - accuracy: 0.9936 - val_loss: 0.2295 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00511: loss did not improve from 0.02925\n",
            "Epoch 512/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0626 - accuracy: 0.9926 - val_loss: 0.1849 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00512: loss did not improve from 0.02925\n",
            "Epoch 513/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0530 - accuracy: 0.9956 - val_loss: 0.2057 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00513: loss did not improve from 0.02925\n",
            "Epoch 514/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0431 - accuracy: 0.9990 - val_loss: 0.1933 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00514: loss did not improve from 0.02925\n",
            "Epoch 515/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0698 - accuracy: 0.9936 - val_loss: 0.2920 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00515: loss did not improve from 0.02925\n",
            "Epoch 516/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0939 - accuracy: 0.9837 - val_loss: 0.2441 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00516: loss did not improve from 0.02925\n",
            "Epoch 517/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0608 - accuracy: 0.9925 - val_loss: 0.2007 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00517: loss did not improve from 0.02925\n",
            "Epoch 518/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0487 - accuracy: 0.9966 - val_loss: 0.2226 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00518: loss did not improve from 0.02925\n",
            "Epoch 519/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0443 - accuracy: 1.0000 - val_loss: 0.2185 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00519: loss did not improve from 0.02925\n",
            "Epoch 520/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0410 - accuracy: 1.0000 - val_loss: 0.2303 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00520: loss did not improve from 0.02925\n",
            "Epoch 521/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0429 - accuracy: 0.9991 - val_loss: 0.2109 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00521: loss did not improve from 0.02925\n",
            "Epoch 522/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0528 - accuracy: 0.9925 - val_loss: 0.2052 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00522: loss did not improve from 0.02925\n",
            "Epoch 523/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0412 - accuracy: 1.0000 - val_loss: 0.2169 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00523: loss did not improve from 0.02925\n",
            "Epoch 524/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0399 - accuracy: 1.0000 - val_loss: 0.2236 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00524: loss did not improve from 0.02925\n",
            "Epoch 525/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0424 - accuracy: 1.0000 - val_loss: 0.1964 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00525: loss did not improve from 0.02925\n",
            "Epoch 526/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0412 - accuracy: 0.9991 - val_loss: 0.2213 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00526: loss did not improve from 0.02925\n",
            "Epoch 527/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0423 - accuracy: 0.9981 - val_loss: 0.2639 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00527: loss did not improve from 0.02925\n",
            "Epoch 528/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0387 - accuracy: 0.9994 - val_loss: 0.2317 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00528: loss did not improve from 0.02925\n",
            "Epoch 529/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0465 - accuracy: 0.9955 - val_loss: 0.2304 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00529: loss did not improve from 0.02925\n",
            "Epoch 530/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0601 - accuracy: 0.9914 - val_loss: 0.1850 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00530: loss did not improve from 0.02925\n",
            "Epoch 531/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0609 - accuracy: 0.9931 - val_loss: 0.1668 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00531: loss did not improve from 0.02925\n",
            "Epoch 532/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0465 - accuracy: 0.9956 - val_loss: 0.2080 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00532: loss did not improve from 0.02925\n",
            "Epoch 533/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0451 - accuracy: 0.9976 - val_loss: 0.1869 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00533: loss did not improve from 0.02925\n",
            "Epoch 534/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0520 - accuracy: 0.9957 - val_loss: 0.1909 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00534: loss did not improve from 0.02925\n",
            "Epoch 535/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0431 - accuracy: 0.9986 - val_loss: 0.2225 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00535: loss did not improve from 0.02925\n",
            "Epoch 536/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0444 - accuracy: 0.9989 - val_loss: 0.2096 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00536: loss did not improve from 0.02925\n",
            "Epoch 537/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0417 - accuracy: 1.0000 - val_loss: 0.2454 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00537: loss did not improve from 0.02925\n",
            "Epoch 538/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0405 - accuracy: 1.0000 - val_loss: 0.2229 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00538: loss did not improve from 0.02925\n",
            "Epoch 539/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0376 - accuracy: 1.0000 - val_loss: 0.2235 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00539: loss did not improve from 0.02925\n",
            "Epoch 540/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0380 - accuracy: 0.9994 - val_loss: 0.2649 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00540: loss did not improve from 0.02925\n",
            "Epoch 541/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0382 - accuracy: 1.0000 - val_loss: 0.2578 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00541: loss did not improve from 0.02925\n",
            "Epoch 542/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0383 - accuracy: 0.9996 - val_loss: 0.2360 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00542: loss did not improve from 0.02925\n",
            "Epoch 543/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0408 - accuracy: 0.9978 - val_loss: 0.2311 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00543: loss did not improve from 0.02925\n",
            "Epoch 544/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0360 - accuracy: 1.0000 - val_loss: 0.2179 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00544: loss did not improve from 0.02925\n",
            "Epoch 545/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0352 - accuracy: 1.0000 - val_loss: 0.2197 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00545: loss did not improve from 0.02925\n",
            "Epoch 546/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0379 - accuracy: 1.0000 - val_loss: 0.2129 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00546: loss did not improve from 0.02925\n",
            "Epoch 547/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0348 - accuracy: 1.0000 - val_loss: 0.2110 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00547: loss did not improve from 0.02925\n",
            "Epoch 548/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0342 - accuracy: 1.0000 - val_loss: 0.2230 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00548: loss did not improve from 0.02925\n",
            "Epoch 549/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0333 - accuracy: 0.9999 - val_loss: 0.2308 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00549: loss did not improve from 0.02925\n",
            "Epoch 550/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0335 - accuracy: 1.0000 - val_loss: 0.2149 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00550: loss did not improve from 0.02925\n",
            "Epoch 551/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0332 - accuracy: 1.0000 - val_loss: 0.2295 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00551: loss did not improve from 0.02925\n",
            "Epoch 552/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0327 - accuracy: 1.0000 - val_loss: 0.2681 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00552: loss did not improve from 0.02925\n",
            "Epoch 553/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0354 - accuracy: 0.9982 - val_loss: 0.2345 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00553: loss did not improve from 0.02925\n",
            "Epoch 554/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0365 - accuracy: 1.0000 - val_loss: 0.3157 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00554: loss did not improve from 0.02925\n",
            "Epoch 555/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0326 - accuracy: 1.0000 - val_loss: 0.2770 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00555: loss did not improve from 0.02925\n",
            "Epoch 556/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0337 - accuracy: 1.0000 - val_loss: 0.2879 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00556: loss did not improve from 0.02925\n",
            "Epoch 557/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0314 - accuracy: 1.0000 - val_loss: 0.2677 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00557: loss did not improve from 0.02925\n",
            "Epoch 558/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0324 - accuracy: 0.9988 - val_loss: 0.2642 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00558: loss did not improve from 0.02925\n",
            "Epoch 559/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0566 - accuracy: 0.9899 - val_loss: 0.1817 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00559: loss did not improve from 0.02925\n",
            "Epoch 560/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0394 - accuracy: 0.9970 - val_loss: 0.2206 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00560: loss did not improve from 0.02925\n",
            "Epoch 561/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0344 - accuracy: 0.9991 - val_loss: 0.1927 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00561: loss did not improve from 0.02925\n",
            "Epoch 562/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0334 - accuracy: 1.0000 - val_loss: 0.1914 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00562: loss did not improve from 0.02925\n",
            "Epoch 563/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0322 - accuracy: 1.0000 - val_loss: 0.2091 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00563: loss did not improve from 0.02925\n",
            "Epoch 564/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0328 - accuracy: 1.0000 - val_loss: 0.2526 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00564: loss did not improve from 0.02925\n",
            "Epoch 565/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0327 - accuracy: 0.9988 - val_loss: 0.2380 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00565: loss did not improve from 0.02925\n",
            "Epoch 566/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0349 - accuracy: 0.9988 - val_loss: 0.2236 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00566: loss did not improve from 0.02925\n",
            "Epoch 567/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0422 - accuracy: 0.9947 - val_loss: 0.2228 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00567: loss did not improve from 0.02925\n",
            "Epoch 568/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0570 - accuracy: 0.9920 - val_loss: 0.2759 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00568: loss did not improve from 0.02925\n",
            "Epoch 569/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0519 - accuracy: 0.9946 - val_loss: 0.2343 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00569: loss did not improve from 0.02925\n",
            "Epoch 570/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0405 - accuracy: 0.9967 - val_loss: 0.1952 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00570: loss did not improve from 0.02925\n",
            "Epoch 571/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0581 - accuracy: 0.9914 - val_loss: 0.1855 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00571: loss did not improve from 0.02925\n",
            "Epoch 572/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0461 - accuracy: 0.9962 - val_loss: 0.2367 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00572: loss did not improve from 0.02925\n",
            "Epoch 573/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0371 - accuracy: 1.0000 - val_loss: 0.2265 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00573: loss did not improve from 0.02925\n",
            "Epoch 574/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0339 - accuracy: 0.9996 - val_loss: 0.2108 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00574: loss did not improve from 0.02925\n",
            "Epoch 575/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0399 - accuracy: 0.9951 - val_loss: 0.2321 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00575: loss did not improve from 0.02925\n",
            "Epoch 576/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0402 - accuracy: 0.9941 - val_loss: 0.2395 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00576: loss did not improve from 0.02925\n",
            "Epoch 577/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0338 - accuracy: 1.0000 - val_loss: 0.2645 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00577: loss did not improve from 0.02925\n",
            "Epoch 578/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0330 - accuracy: 1.0000 - val_loss: 0.2502 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00578: loss did not improve from 0.02925\n",
            "Epoch 579/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0317 - accuracy: 1.0000 - val_loss: 0.2528 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00579: loss did not improve from 0.02925\n",
            "Epoch 580/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0311 - accuracy: 1.0000 - val_loss: 0.2562 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00580: loss did not improve from 0.02925\n",
            "Epoch 581/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2574 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00581: loss did not improve from 0.02925\n",
            "Epoch 582/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0304 - accuracy: 1.0000 - val_loss: 0.2573 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00582: loss did not improve from 0.02925\n",
            "Epoch 583/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0302 - accuracy: 1.0000 - val_loss: 0.2546 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00583: loss did not improve from 0.02925\n",
            "Epoch 584/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0298 - accuracy: 1.0000 - val_loss: 0.2519 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00584: loss did not improve from 0.02925\n",
            "Epoch 585/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0296 - accuracy: 1.0000 - val_loss: 0.2671 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00585: loss did not improve from 0.02925\n",
            "Epoch 586/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0290 - accuracy: 1.0000 - val_loss: 0.2502 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00586: loss did not improve from 0.02925\n",
            "Epoch 587/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0303 - accuracy: 0.9978 - val_loss: 0.2526 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00587: loss did not improve from 0.02925\n",
            "Epoch 588/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0303 - accuracy: 1.0000 - val_loss: 0.2373 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00588: loss did not improve from 0.02925\n",
            "Epoch 589/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2466 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00589: loss improved from 0.02925 to 0.02787, saving model to Emotion_detection.h5\n",
            "Epoch 590/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0286 - accuracy: 0.9999 - val_loss: 0.2313 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00590: loss did not improve from 0.02787\n",
            "Epoch 591/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0460 - accuracy: 0.9953 - val_loss: 0.2168 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00591: loss did not improve from 0.02787\n",
            "Epoch 592/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0485 - accuracy: 0.9938 - val_loss: 0.2446 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00592: loss did not improve from 0.02787\n",
            "Epoch 593/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0725 - accuracy: 0.9859 - val_loss: 0.2117 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00593: loss did not improve from 0.02787\n",
            "Epoch 594/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0607 - accuracy: 0.9951 - val_loss: 0.2276 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00594: loss did not improve from 0.02787\n",
            "Epoch 595/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0583 - accuracy: 0.9905 - val_loss: 0.2757 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00595: loss did not improve from 0.02787\n",
            "Epoch 596/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0610 - accuracy: 0.9873 - val_loss: 0.2367 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00596: loss did not improve from 0.02787\n",
            "Epoch 597/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0542 - accuracy: 0.9951 - val_loss: 0.2797 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00597: loss did not improve from 0.02787\n",
            "Epoch 598/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0370 - accuracy: 1.0000 - val_loss: 0.2822 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00598: loss did not improve from 0.02787\n",
            "Epoch 599/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0429 - accuracy: 0.9981 - val_loss: 0.2996 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00599: loss did not improve from 0.02787\n",
            "Epoch 600/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0405 - accuracy: 0.9998 - val_loss: 0.2747 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00600: loss did not improve from 0.02787\n",
            "Epoch 601/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0423 - accuracy: 0.9970 - val_loss: 0.2675 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00601: loss did not improve from 0.02787\n",
            "Epoch 602/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0402 - accuracy: 1.0000 - val_loss: 0.2778 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00602: loss did not improve from 0.02787\n",
            "Epoch 603/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0474 - accuracy: 0.9990 - val_loss: 0.2993 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00603: loss did not improve from 0.02787\n",
            "Epoch 604/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0384 - accuracy: 0.9998 - val_loss: 0.2447 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00604: loss did not improve from 0.02787\n",
            "Epoch 605/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0390 - accuracy: 0.9990 - val_loss: 0.2067 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00605: loss did not improve from 0.02787\n",
            "Epoch 606/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0444 - accuracy: 0.9923 - val_loss: 0.2468 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00606: loss did not improve from 0.02787\n",
            "Epoch 607/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0403 - accuracy: 0.9989 - val_loss: 0.2688 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00607: loss did not improve from 0.02787\n",
            "Epoch 608/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0386 - accuracy: 0.9970 - val_loss: 0.2857 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00608: loss did not improve from 0.02787\n",
            "Epoch 609/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0357 - accuracy: 1.0000 - val_loss: 0.2691 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00609: loss did not improve from 0.02787\n",
            "Epoch 610/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0340 - accuracy: 1.0000 - val_loss: 0.2710 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00610: loss did not improve from 0.02787\n",
            "Epoch 611/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0338 - accuracy: 1.0000 - val_loss: 0.2685 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00611: loss did not improve from 0.02787\n",
            "Epoch 612/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0335 - accuracy: 1.0000 - val_loss: 0.2484 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00612: loss did not improve from 0.02787\n",
            "Epoch 613/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0334 - accuracy: 1.0000 - val_loss: 0.2437 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00613: loss did not improve from 0.02787\n",
            "Epoch 614/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0330 - accuracy: 0.9996 - val_loss: 0.2581 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00614: loss did not improve from 0.02787\n",
            "Epoch 615/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0488 - accuracy: 0.9956 - val_loss: 0.2047 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00615: loss did not improve from 0.02787\n",
            "Epoch 616/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0397 - accuracy: 0.9978 - val_loss: 0.2545 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00616: loss did not improve from 0.02787\n",
            "Epoch 617/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0359 - accuracy: 0.9975 - val_loss: 0.2820 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00617: loss did not improve from 0.02787\n",
            "Epoch 618/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0339 - accuracy: 1.0000 - val_loss: 0.2769 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00618: loss did not improve from 0.02787\n",
            "Epoch 619/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0341 - accuracy: 0.9996 - val_loss: 0.2580 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00619: loss did not improve from 0.02787\n",
            "Epoch 620/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0377 - accuracy: 0.9974 - val_loss: 0.2779 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00620: loss did not improve from 0.02787\n",
            "Epoch 621/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0381 - accuracy: 1.0000 - val_loss: 0.2455 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00621: loss did not improve from 0.02787\n",
            "Epoch 622/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0326 - accuracy: 0.9998 - val_loss: 0.2719 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00622: loss did not improve from 0.02787\n",
            "Epoch 623/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0372 - accuracy: 0.9977 - val_loss: 0.2679 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00623: loss did not improve from 0.02787\n",
            "Epoch 624/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0389 - accuracy: 0.9970 - val_loss: 0.2704 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00624: loss did not improve from 0.02787\n",
            "Epoch 625/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0336 - accuracy: 1.0000 - val_loss: 0.2592 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00625: loss did not improve from 0.02787\n",
            "Epoch 626/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0326 - accuracy: 0.9997 - val_loss: 0.2657 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00626: loss did not improve from 0.02787\n",
            "Epoch 627/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0322 - accuracy: 1.0000 - val_loss: 0.2952 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00627: loss did not improve from 0.02787\n",
            "Epoch 628/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0312 - accuracy: 1.0000 - val_loss: 0.2753 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00628: loss did not improve from 0.02787\n",
            "Epoch 629/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2492 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00629: loss did not improve from 0.02787\n",
            "Epoch 630/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0307 - accuracy: 1.0000 - val_loss: 0.2586 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00630: loss did not improve from 0.02787\n",
            "Epoch 631/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0297 - accuracy: 1.0000 - val_loss: 0.2597 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00631: loss did not improve from 0.02787\n",
            "Epoch 632/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0291 - accuracy: 1.0000 - val_loss: 0.2588 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00632: loss did not improve from 0.02787\n",
            "Epoch 633/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0291 - accuracy: 1.0000 - val_loss: 0.2505 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00633: loss did not improve from 0.02787\n",
            "Epoch 634/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0301 - accuracy: 1.0000 - val_loss: 0.2858 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00634: loss did not improve from 0.02787\n",
            "Epoch 635/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0367 - accuracy: 0.9939 - val_loss: 0.2546 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00635: loss did not improve from 0.02787\n",
            "Epoch 636/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0420 - accuracy: 0.9974 - val_loss: 0.2415 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00636: loss did not improve from 0.02787\n",
            "Epoch 637/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0391 - accuracy: 0.9981 - val_loss: 0.2517 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00637: loss did not improve from 0.02787\n",
            "Epoch 638/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0432 - accuracy: 0.9951 - val_loss: 0.2490 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00638: loss did not improve from 0.02787\n",
            "Epoch 639/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0456 - accuracy: 0.9957 - val_loss: 0.2345 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00639: loss did not improve from 0.02787\n",
            "Epoch 640/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0445 - accuracy: 0.9970 - val_loss: 0.2577 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00640: loss did not improve from 0.02787\n",
            "Epoch 641/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0372 - accuracy: 0.9970 - val_loss: 0.2783 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00641: loss did not improve from 0.02787\n",
            "Epoch 642/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0642 - accuracy: 0.9912 - val_loss: 0.2333 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00642: loss did not improve from 0.02787\n",
            "Epoch 643/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0398 - accuracy: 0.9982 - val_loss: 0.2231 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00643: loss did not improve from 0.02787\n",
            "Epoch 644/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0473 - accuracy: 0.9953 - val_loss: 0.2223 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00644: loss did not improve from 0.02787\n",
            "Epoch 645/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0428 - accuracy: 0.9957 - val_loss: 0.2255 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00645: loss did not improve from 0.02787\n",
            "Epoch 646/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0375 - accuracy: 1.0000 - val_loss: 0.1878 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00646: loss did not improve from 0.02787\n",
            "Epoch 647/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0356 - accuracy: 0.9992 - val_loss: 0.1904 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00647: loss did not improve from 0.02787\n",
            "Epoch 648/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0437 - accuracy: 0.9955 - val_loss: 0.3698 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00648: loss did not improve from 0.02787\n",
            "Epoch 649/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0822 - accuracy: 0.9837 - val_loss: 0.2597 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00649: loss did not improve from 0.02787\n",
            "Epoch 650/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0499 - accuracy: 0.9957 - val_loss: 0.2230 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00650: loss did not improve from 0.02787\n",
            "Epoch 651/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0408 - accuracy: 1.0000 - val_loss: 0.2397 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00651: loss did not improve from 0.02787\n",
            "Epoch 652/1000\n",
            "23/23 [==============================] - 6s 271ms/step - loss: 0.0382 - accuracy: 0.9996 - val_loss: 0.2345 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00652: loss did not improve from 0.02787\n",
            "Epoch 653/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0781 - accuracy: 0.9919 - val_loss: 0.2318 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00653: loss did not improve from 0.02787\n",
            "Epoch 654/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0555 - accuracy: 0.9955 - val_loss: 0.1917 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00654: loss did not improve from 0.02787\n",
            "Epoch 655/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0429 - accuracy: 0.9972 - val_loss: 0.2315 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00655: loss did not improve from 0.02787\n",
            "Epoch 656/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0382 - accuracy: 0.9992 - val_loss: 0.2218 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00656: loss did not improve from 0.02787\n",
            "Epoch 657/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0405 - accuracy: 0.9989 - val_loss: 0.2185 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00657: loss did not improve from 0.02787\n",
            "Epoch 658/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0528 - accuracy: 0.9962 - val_loss: 0.1915 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00658: loss did not improve from 0.02787\n",
            "Epoch 659/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0405 - accuracy: 0.9974 - val_loss: 0.2432 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00659: loss did not improve from 0.02787\n",
            "Epoch 660/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0356 - accuracy: 1.0000 - val_loss: 0.2595 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00660: loss did not improve from 0.02787\n",
            "Epoch 661/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0367 - accuracy: 1.0000 - val_loss: 0.2481 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00661: loss did not improve from 0.02787\n",
            "Epoch 662/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0344 - accuracy: 1.0000 - val_loss: 0.2583 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00662: loss did not improve from 0.02787\n",
            "Epoch 663/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0350 - accuracy: 1.0000 - val_loss: 0.2809 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00663: loss did not improve from 0.02787\n",
            "Epoch 664/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0352 - accuracy: 0.9996 - val_loss: 0.2417 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00664: loss did not improve from 0.02787\n",
            "Epoch 665/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0704 - accuracy: 0.9864 - val_loss: 0.1947 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00665: loss did not improve from 0.02787\n",
            "Epoch 666/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0506 - accuracy: 0.9941 - val_loss: 0.2209 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00666: loss did not improve from 0.02787\n",
            "Epoch 667/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0445 - accuracy: 0.9976 - val_loss: 0.2186 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00667: loss did not improve from 0.02787\n",
            "Epoch 668/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0410 - accuracy: 0.9964 - val_loss: 0.2419 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00668: loss did not improve from 0.02787\n",
            "Epoch 669/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0390 - accuracy: 0.9978 - val_loss: 0.2582 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00669: loss did not improve from 0.02787\n",
            "Epoch 670/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0368 - accuracy: 1.0000 - val_loss: 0.2149 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00670: loss did not improve from 0.02787\n",
            "Epoch 671/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0375 - accuracy: 0.9970 - val_loss: 0.2354 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00671: loss did not improve from 0.02787\n",
            "Epoch 672/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0354 - accuracy: 1.0000 - val_loss: 0.2268 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00672: loss did not improve from 0.02787\n",
            "Epoch 673/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0347 - accuracy: 0.9985 - val_loss: 0.2622 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00673: loss did not improve from 0.02787\n",
            "Epoch 674/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0357 - accuracy: 0.9986 - val_loss: 0.2276 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00674: loss did not improve from 0.02787\n",
            "Epoch 675/1000\n",
            "23/23 [==============================] - 6s 272ms/step - loss: 0.0331 - accuracy: 1.0000 - val_loss: 0.2293 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00675: loss did not improve from 0.02787\n",
            "Epoch 676/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0323 - accuracy: 1.0000 - val_loss: 0.2347 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00676: loss did not improve from 0.02787\n",
            "Epoch 677/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0319 - accuracy: 1.0000 - val_loss: 0.2354 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00677: loss did not improve from 0.02787\n",
            "Epoch 678/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0314 - accuracy: 1.0000 - val_loss: 0.2323 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00678: loss did not improve from 0.02787\n",
            "Epoch 679/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0313 - accuracy: 1.0000 - val_loss: 0.2374 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00679: loss did not improve from 0.02787\n",
            "Epoch 680/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0307 - accuracy: 1.0000 - val_loss: 0.2389 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00680: loss did not improve from 0.02787\n",
            "Epoch 681/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0305 - accuracy: 1.0000 - val_loss: 0.2473 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00681: loss did not improve from 0.02787\n",
            "Epoch 682/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0301 - accuracy: 1.0000 - val_loss: 0.2410 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00682: loss did not improve from 0.02787\n",
            "Epoch 683/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0294 - accuracy: 1.0000 - val_loss: 0.2383 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00683: loss did not improve from 0.02787\n",
            "Epoch 684/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0307 - accuracy: 1.0000 - val_loss: 0.2441 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00684: loss did not improve from 0.02787\n",
            "Epoch 685/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0291 - accuracy: 1.0000 - val_loss: 0.2352 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00685: loss did not improve from 0.02787\n",
            "Epoch 686/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0284 - accuracy: 1.0000 - val_loss: 0.2318 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00686: loss did not improve from 0.02787\n",
            "Epoch 687/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0281 - accuracy: 1.0000 - val_loss: 0.2355 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00687: loss did not improve from 0.02787\n",
            "Epoch 688/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2361 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00688: loss improved from 0.02787 to 0.02779, saving model to Emotion_detection.h5\n",
            "Epoch 689/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0275 - accuracy: 1.0000 - val_loss: 0.2443 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00689: loss improved from 0.02779 to 0.02743, saving model to Emotion_detection.h5\n",
            "Epoch 690/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0270 - accuracy: 1.0000 - val_loss: 0.2387 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00690: loss improved from 0.02743 to 0.02705, saving model to Emotion_detection.h5\n",
            "Epoch 691/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0266 - accuracy: 1.0000 - val_loss: 0.2376 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00691: loss improved from 0.02705 to 0.02654, saving model to Emotion_detection.h5\n",
            "Epoch 692/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0263 - accuracy: 1.0000 - val_loss: 0.2399 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00692: loss improved from 0.02654 to 0.02634, saving model to Emotion_detection.h5\n",
            "Epoch 693/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2396 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00693: loss improved from 0.02634 to 0.02613, saving model to Emotion_detection.h5\n",
            "Epoch 694/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0263 - accuracy: 0.9998 - val_loss: 0.2782 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00694: loss did not improve from 0.02613\n",
            "Epoch 695/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0306 - accuracy: 0.9985 - val_loss: 0.2140 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00695: loss did not improve from 0.02613\n",
            "Epoch 696/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0296 - accuracy: 1.0000 - val_loss: 0.2116 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00696: loss did not improve from 0.02613\n",
            "Epoch 697/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0276 - accuracy: 1.0000 - val_loss: 0.2088 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00697: loss did not improve from 0.02613\n",
            "Epoch 698/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0432 - accuracy: 0.9945 - val_loss: 0.2295 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00698: loss did not improve from 0.02613\n",
            "Epoch 699/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0346 - accuracy: 0.9984 - val_loss: 0.2235 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00699: loss did not improve from 0.02613\n",
            "Epoch 700/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0338 - accuracy: 0.9992 - val_loss: 0.2701 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00700: loss did not improve from 0.02613\n",
            "Epoch 701/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0315 - accuracy: 0.9998 - val_loss: 0.2328 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00701: loss did not improve from 0.02613\n",
            "Epoch 702/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0311 - accuracy: 0.9994 - val_loss: 0.2768 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00702: loss did not improve from 0.02613\n",
            "Epoch 703/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0411 - accuracy: 0.9975 - val_loss: 0.2785 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00703: loss did not improve from 0.02613\n",
            "Epoch 704/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0309 - accuracy: 1.0000 - val_loss: 0.2103 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00704: loss did not improve from 0.02613\n",
            "Epoch 705/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0299 - accuracy: 0.9998 - val_loss: 0.2537 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00705: loss did not improve from 0.02613\n",
            "Epoch 706/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0313 - accuracy: 0.9978 - val_loss: 0.4081 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00706: loss did not improve from 0.02613\n",
            "Epoch 707/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0288 - accuracy: 1.0000 - val_loss: 0.2816 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00707: loss did not improve from 0.02613\n",
            "Epoch 708/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0291 - accuracy: 0.9978 - val_loss: 0.2506 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00708: loss did not improve from 0.02613\n",
            "Epoch 709/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0371 - accuracy: 0.9954 - val_loss: 0.2881 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00709: loss did not improve from 0.02613\n",
            "Epoch 710/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0318 - accuracy: 0.9998 - val_loss: 0.2770 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00710: loss did not improve from 0.02613\n",
            "Epoch 711/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0500 - accuracy: 0.9905 - val_loss: 0.2611 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00711: loss did not improve from 0.02613\n",
            "Epoch 712/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0826 - accuracy: 0.9837 - val_loss: 0.2071 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00712: loss did not improve from 0.02613\n",
            "Epoch 713/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0708 - accuracy: 0.9841 - val_loss: 0.2728 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00713: loss did not improve from 0.02613\n",
            "Epoch 714/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0457 - accuracy: 0.9943 - val_loss: 0.2752 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00714: loss did not improve from 0.02613\n",
            "Epoch 715/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0362 - accuracy: 1.0000 - val_loss: 0.2308 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00715: loss did not improve from 0.02613\n",
            "Epoch 716/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0344 - accuracy: 1.0000 - val_loss: 0.2821 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00716: loss did not improve from 0.02613\n",
            "Epoch 717/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0331 - accuracy: 1.0000 - val_loss: 0.2596 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00717: loss did not improve from 0.02613\n",
            "Epoch 718/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0321 - accuracy: 1.0000 - val_loss: 0.2491 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00718: loss did not improve from 0.02613\n",
            "Epoch 719/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0317 - accuracy: 1.0000 - val_loss: 0.2498 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00719: loss did not improve from 0.02613\n",
            "Epoch 720/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0312 - accuracy: 1.0000 - val_loss: 0.2566 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00720: loss did not improve from 0.02613\n",
            "Epoch 721/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0309 - accuracy: 1.0000 - val_loss: 0.2516 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00721: loss did not improve from 0.02613\n",
            "Epoch 722/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0303 - accuracy: 1.0000 - val_loss: 0.2495 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00722: loss did not improve from 0.02613\n",
            "Epoch 723/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0298 - accuracy: 1.0000 - val_loss: 0.2356 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00723: loss did not improve from 0.02613\n",
            "Epoch 724/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0299 - accuracy: 1.0000 - val_loss: 0.2433 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00724: loss did not improve from 0.02613\n",
            "Epoch 725/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0322 - accuracy: 0.9981 - val_loss: 0.2297 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00725: loss did not improve from 0.02613\n",
            "Epoch 726/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0320 - accuracy: 1.0000 - val_loss: 0.2806 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00726: loss did not improve from 0.02613\n",
            "Epoch 727/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0313 - accuracy: 0.9998 - val_loss: 0.2526 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00727: loss did not improve from 0.02613\n",
            "Epoch 728/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0300 - accuracy: 1.0000 - val_loss: 0.2445 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00728: loss did not improve from 0.02613\n",
            "Epoch 729/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0299 - accuracy: 1.0000 - val_loss: 0.2714 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00729: loss did not improve from 0.02613\n",
            "Epoch 730/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0291 - accuracy: 1.0000 - val_loss: 0.2565 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00730: loss did not improve from 0.02613\n",
            "Epoch 731/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0294 - accuracy: 1.0000 - val_loss: 0.2649 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00731: loss did not improve from 0.02613\n",
            "Epoch 732/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2663 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00732: loss did not improve from 0.02613\n",
            "Epoch 733/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0274 - accuracy: 1.0000 - val_loss: 0.2700 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00733: loss did not improve from 0.02613\n",
            "Epoch 734/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0271 - accuracy: 1.0000 - val_loss: 0.2726 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00734: loss did not improve from 0.02613\n",
            "Epoch 735/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0268 - accuracy: 1.0000 - val_loss: 0.2744 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00735: loss did not improve from 0.02613\n",
            "Epoch 736/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0263 - accuracy: 1.0000 - val_loss: 0.2697 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00736: loss did not improve from 0.02613\n",
            "Epoch 737/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0275 - accuracy: 0.9994 - val_loss: 0.2962 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00737: loss did not improve from 0.02613\n",
            "Epoch 738/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0268 - accuracy: 1.0000 - val_loss: 0.2464 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00738: loss did not improve from 0.02613\n",
            "Epoch 739/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0268 - accuracy: 1.0000 - val_loss: 0.3320 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00739: loss did not improve from 0.02613\n",
            "Epoch 740/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0315 - accuracy: 0.9979 - val_loss: 0.2300 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00740: loss did not improve from 0.02613\n",
            "Epoch 741/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0395 - accuracy: 0.9971 - val_loss: 0.2351 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00741: loss did not improve from 0.02613\n",
            "Epoch 742/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0366 - accuracy: 0.9975 - val_loss: 0.2004 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00742: loss did not improve from 0.02613\n",
            "Epoch 743/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0516 - accuracy: 0.9910 - val_loss: 0.1788 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00743: loss did not improve from 0.02613\n",
            "Epoch 744/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0352 - accuracy: 0.9992 - val_loss: 0.2196 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00744: loss did not improve from 0.02613\n",
            "Epoch 745/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0375 - accuracy: 0.9948 - val_loss: 0.2119 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00745: loss did not improve from 0.02613\n",
            "Epoch 746/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0387 - accuracy: 0.9975 - val_loss: 0.1814 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00746: loss did not improve from 0.02613\n",
            "Epoch 747/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0314 - accuracy: 0.9986 - val_loss: 0.2272 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00747: loss did not improve from 0.02613\n",
            "Epoch 748/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0294 - accuracy: 1.0000 - val_loss: 0.2540 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00748: loss did not improve from 0.02613\n",
            "Epoch 749/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0307 - accuracy: 1.0000 - val_loss: 0.2592 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00749: loss did not improve from 0.02613\n",
            "Epoch 750/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0282 - accuracy: 1.0000 - val_loss: 0.2528 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00750: loss did not improve from 0.02613\n",
            "Epoch 751/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0279 - accuracy: 1.0000 - val_loss: 0.2621 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00751: loss did not improve from 0.02613\n",
            "Epoch 752/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0335 - accuracy: 0.9992 - val_loss: 0.2406 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00752: loss did not improve from 0.02613\n",
            "Epoch 753/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0413 - accuracy: 0.9913 - val_loss: 0.2524 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00753: loss did not improve from 0.02613\n",
            "Epoch 754/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0326 - accuracy: 0.9981 - val_loss: 0.2409 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00754: loss did not improve from 0.02613\n",
            "Epoch 755/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0297 - accuracy: 1.0000 - val_loss: 0.2563 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00755: loss did not improve from 0.02613\n",
            "Epoch 756/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0274 - accuracy: 1.0000 - val_loss: 0.2678 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00756: loss did not improve from 0.02613\n",
            "Epoch 757/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0269 - accuracy: 1.0000 - val_loss: 0.2708 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00757: loss did not improve from 0.02613\n",
            "Epoch 758/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0265 - accuracy: 1.0000 - val_loss: 0.2647 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00758: loss did not improve from 0.02613\n",
            "Epoch 759/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0263 - accuracy: 1.0000 - val_loss: 0.2715 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00759: loss did not improve from 0.02613\n",
            "Epoch 760/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2832 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00760: loss improved from 0.02613 to 0.02600, saving model to Emotion_detection.h5\n",
            "Epoch 761/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0255 - accuracy: 1.0000 - val_loss: 0.2796 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00761: loss improved from 0.02600 to 0.02554, saving model to Emotion_detection.h5\n",
            "Epoch 762/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0253 - accuracy: 1.0000 - val_loss: 0.2747 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00762: loss improved from 0.02554 to 0.02510, saving model to Emotion_detection.h5\n",
            "Epoch 763/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0253 - accuracy: 1.0000 - val_loss: 0.2721 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00763: loss improved from 0.02510 to 0.02493, saving model to Emotion_detection.h5\n",
            "Epoch 764/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2551 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00764: loss did not improve from 0.02493\n",
            "Epoch 765/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0246 - accuracy: 1.0000 - val_loss: 0.2526 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00765: loss improved from 0.02493 to 0.02455, saving model to Emotion_detection.h5\n",
            "Epoch 766/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0305 - accuracy: 0.9944 - val_loss: 0.2687 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00766: loss did not improve from 0.02455\n",
            "Epoch 767/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0497 - accuracy: 0.9890 - val_loss: 0.2090 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00767: loss did not improve from 0.02455\n",
            "Epoch 768/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0367 - accuracy: 0.9973 - val_loss: 0.2388 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00768: loss did not improve from 0.02455\n",
            "Epoch 769/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0355 - accuracy: 0.9986 - val_loss: 0.2157 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00769: loss did not improve from 0.02455\n",
            "Epoch 770/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0418 - accuracy: 0.9963 - val_loss: 0.3180 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00770: loss did not improve from 0.02455\n",
            "Epoch 771/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0341 - accuracy: 0.9993 - val_loss: 0.2341 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00771: loss did not improve from 0.02455\n",
            "Epoch 772/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0374 - accuracy: 0.9943 - val_loss: 0.2820 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00772: loss did not improve from 0.02455\n",
            "Epoch 773/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0365 - accuracy: 0.9964 - val_loss: 0.2435 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00773: loss did not improve from 0.02455\n",
            "Epoch 774/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0295 - accuracy: 1.0000 - val_loss: 0.2495 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00774: loss did not improve from 0.02455\n",
            "Epoch 775/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2513 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00775: loss did not improve from 0.02455\n",
            "Epoch 776/1000\n",
            "23/23 [==============================] - 6s 273ms/step - loss: 0.0288 - accuracy: 0.9989 - val_loss: 0.2094 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00776: loss did not improve from 0.02455\n",
            "Epoch 777/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0290 - accuracy: 1.0000 - val_loss: 0.3048 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00777: loss did not improve from 0.02455\n",
            "Epoch 778/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0282 - accuracy: 0.9996 - val_loss: 0.2296 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00778: loss did not improve from 0.02455\n",
            "Epoch 779/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0284 - accuracy: 0.9989 - val_loss: 0.2200 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00779: loss did not improve from 0.02455\n",
            "Epoch 780/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0388 - accuracy: 0.9927 - val_loss: 0.2587 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00780: loss did not improve from 0.02455\n",
            "Epoch 781/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0389 - accuracy: 0.9964 - val_loss: 0.2444 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00781: loss did not improve from 0.02455\n",
            "Epoch 782/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0450 - accuracy: 0.9958 - val_loss: 0.2247 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00782: loss did not improve from 0.02455\n",
            "Epoch 783/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0447 - accuracy: 0.9954 - val_loss: 0.2305 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00783: loss did not improve from 0.02455\n",
            "Epoch 784/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0575 - accuracy: 0.9916 - val_loss: 0.2329 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00784: loss did not improve from 0.02455\n",
            "Epoch 785/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0359 - accuracy: 0.9997 - val_loss: 0.2775 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00785: loss did not improve from 0.02455\n",
            "Epoch 786/1000\n",
            "23/23 [==============================] - 6s 274ms/step - loss: 0.0376 - accuracy: 0.9992 - val_loss: 0.2234 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00786: loss did not improve from 0.02455\n",
            "Epoch 787/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0348 - accuracy: 1.0000 - val_loss: 0.2569 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00787: loss did not improve from 0.02455\n",
            "Epoch 788/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2544 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00788: loss did not improve from 0.02455\n",
            "Epoch 789/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0298 - accuracy: 1.0000 - val_loss: 0.2604 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00789: loss did not improve from 0.02455\n",
            "Epoch 790/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0295 - accuracy: 1.0000 - val_loss: 0.2548 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00790: loss did not improve from 0.02455\n",
            "Epoch 791/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0286 - accuracy: 1.0000 - val_loss: 0.2482 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00791: loss did not improve from 0.02455\n",
            "Epoch 792/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0287 - accuracy: 1.0000 - val_loss: 0.2448 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00792: loss did not improve from 0.02455\n",
            "Epoch 793/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0285 - accuracy: 1.0000 - val_loss: 0.2477 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00793: loss did not improve from 0.02455\n",
            "Epoch 794/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0281 - accuracy: 1.0000 - val_loss: 0.2695 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00794: loss did not improve from 0.02455\n",
            "Epoch 795/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0275 - accuracy: 1.0000 - val_loss: 0.2886 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00795: loss did not improve from 0.02455\n",
            "Epoch 796/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0272 - accuracy: 1.0000 - val_loss: 0.2887 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00796: loss did not improve from 0.02455\n",
            "Epoch 797/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0269 - accuracy: 1.0000 - val_loss: 0.2632 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00797: loss did not improve from 0.02455\n",
            "Epoch 798/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0267 - accuracy: 1.0000 - val_loss: 0.2651 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00798: loss did not improve from 0.02455\n",
            "Epoch 799/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0267 - accuracy: 1.0000 - val_loss: 0.2704 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00799: loss did not improve from 0.02455\n",
            "Epoch 800/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2629 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00800: loss did not improve from 0.02455\n",
            "Epoch 801/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0259 - accuracy: 1.0000 - val_loss: 0.2528 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00801: loss did not improve from 0.02455\n",
            "Epoch 802/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2510 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00802: loss did not improve from 0.02455\n",
            "Epoch 803/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0268 - accuracy: 0.9998 - val_loss: 0.2390 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00803: loss did not improve from 0.02455\n",
            "Epoch 804/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0267 - accuracy: 1.0000 - val_loss: 0.3172 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00804: loss did not improve from 0.02455\n",
            "Epoch 805/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0251 - accuracy: 1.0000 - val_loss: 0.3169 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00805: loss did not improve from 0.02455\n",
            "Epoch 806/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0250 - accuracy: 1.0000 - val_loss: 0.2787 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00806: loss did not improve from 0.02455\n",
            "Epoch 807/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0254 - accuracy: 1.0000 - val_loss: 0.2706 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00807: loss did not improve from 0.02455\n",
            "Epoch 808/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0250 - accuracy: 1.0000 - val_loss: 0.3029 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00808: loss did not improve from 0.02455\n",
            "Epoch 809/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0251 - accuracy: 0.9996 - val_loss: 0.2649 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00809: loss did not improve from 0.02455\n",
            "Epoch 810/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0269 - accuracy: 1.0000 - val_loss: 0.3133 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00810: loss did not improve from 0.02455\n",
            "Epoch 811/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0282 - accuracy: 0.9993 - val_loss: 0.2196 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00811: loss did not improve from 0.02455\n",
            "Epoch 812/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2631 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00812: loss did not improve from 0.02455\n",
            "Epoch 813/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2751 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00813: loss did not improve from 0.02455\n",
            "Epoch 814/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0333 - accuracy: 0.9980 - val_loss: 0.2762 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00814: loss did not improve from 0.02455\n",
            "Epoch 815/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0403 - accuracy: 0.9941 - val_loss: 0.3009 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00815: loss did not improve from 0.02455\n",
            "Epoch 816/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0426 - accuracy: 0.9951 - val_loss: 0.2370 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00816: loss did not improve from 0.02455\n",
            "Epoch 817/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0277 - accuracy: 1.0000 - val_loss: 0.2590 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00817: loss did not improve from 0.02455\n",
            "Epoch 818/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0265 - accuracy: 1.0000 - val_loss: 0.2643 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00818: loss did not improve from 0.02455\n",
            "Epoch 819/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0353 - accuracy: 0.9976 - val_loss: 0.2425 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00819: loss did not improve from 0.02455\n",
            "Epoch 820/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0881 - accuracy: 0.9835 - val_loss: 0.6605 - val_accuracy: 0.8008\n",
            "\n",
            "Epoch 00820: loss did not improve from 0.02455\n",
            "Epoch 821/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.1145 - accuracy: 0.9683 - val_loss: 0.2169 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00821: loss did not improve from 0.02455\n",
            "Epoch 822/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0354 - accuracy: 0.9992 - val_loss: 0.2525 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00822: loss did not improve from 0.02455\n",
            "Epoch 823/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0319 - accuracy: 1.0000 - val_loss: 0.2629 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00823: loss did not improve from 0.02455\n",
            "Epoch 824/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0308 - accuracy: 1.0000 - val_loss: 0.2409 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00824: loss did not improve from 0.02455\n",
            "Epoch 825/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0301 - accuracy: 1.0000 - val_loss: 0.2394 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00825: loss did not improve from 0.02455\n",
            "Epoch 826/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0292 - accuracy: 1.0000 - val_loss: 0.2627 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00826: loss did not improve from 0.02455\n",
            "Epoch 827/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0321 - accuracy: 0.9989 - val_loss: 0.2548 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00827: loss did not improve from 0.02455\n",
            "Epoch 828/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0296 - accuracy: 1.0000 - val_loss: 0.2375 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00828: loss did not improve from 0.02455\n",
            "Epoch 829/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0290 - accuracy: 1.0000 - val_loss: 0.2774 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00829: loss did not improve from 0.02455\n",
            "Epoch 830/1000\n",
            "23/23 [==============================] - 6s 282ms/step - loss: 0.0279 - accuracy: 1.0000 - val_loss: 0.2517 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00830: loss did not improve from 0.02455\n",
            "Epoch 831/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0386 - accuracy: 0.9970 - val_loss: 0.2263 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00831: loss did not improve from 0.02455\n",
            "Epoch 832/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0472 - accuracy: 0.9953 - val_loss: 0.2520 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00832: loss did not improve from 0.02455\n",
            "Epoch 833/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0344 - accuracy: 0.9975 - val_loss: 0.2537 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00833: loss did not improve from 0.02455\n",
            "Epoch 834/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0345 - accuracy: 0.9980 - val_loss: 0.2862 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00834: loss did not improve from 0.02455\n",
            "Epoch 835/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0313 - accuracy: 1.0000 - val_loss: 0.2615 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00835: loss did not improve from 0.02455\n",
            "Epoch 836/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0343 - accuracy: 0.9979 - val_loss: 0.2482 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00836: loss did not improve from 0.02455\n",
            "Epoch 837/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0354 - accuracy: 0.9981 - val_loss: 0.2565 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00837: loss did not improve from 0.02455\n",
            "Epoch 838/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0306 - accuracy: 1.0000 - val_loss: 0.2939 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00838: loss did not improve from 0.02455\n",
            "Epoch 839/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0293 - accuracy: 1.0000 - val_loss: 0.2653 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00839: loss did not improve from 0.02455\n",
            "Epoch 840/1000\n",
            "23/23 [==============================] - 6s 282ms/step - loss: 0.0293 - accuracy: 1.0000 - val_loss: 0.2587 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00840: loss did not improve from 0.02455\n",
            "Epoch 841/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0286 - accuracy: 1.0000 - val_loss: 0.2485 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00841: loss did not improve from 0.02455\n",
            "Epoch 842/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0277 - accuracy: 1.0000 - val_loss: 0.2449 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00842: loss did not improve from 0.02455\n",
            "Epoch 843/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0277 - accuracy: 1.0000 - val_loss: 0.2507 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00843: loss did not improve from 0.02455\n",
            "Epoch 844/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0277 - accuracy: 1.0000 - val_loss: 0.2563 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00844: loss did not improve from 0.02455\n",
            "Epoch 845/1000\n",
            "23/23 [==============================] - 6s 282ms/step - loss: 0.0272 - accuracy: 1.0000 - val_loss: 0.2747 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00845: loss did not improve from 0.02455\n",
            "Epoch 846/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0270 - accuracy: 1.0000 - val_loss: 0.2778 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00846: loss did not improve from 0.02455\n",
            "Epoch 847/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0262 - accuracy: 1.0000 - val_loss: 0.2764 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00847: loss did not improve from 0.02455\n",
            "Epoch 848/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2870 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00848: loss did not improve from 0.02455\n",
            "Epoch 849/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2805 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00849: loss did not improve from 0.02455\n",
            "Epoch 850/1000\n",
            "23/23 [==============================] - 6s 282ms/step - loss: 0.0262 - accuracy: 1.0000 - val_loss: 0.2721 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00850: loss did not improve from 0.02455\n",
            "Epoch 851/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0249 - accuracy: 1.0000 - val_loss: 0.2716 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00851: loss did not improve from 0.02455\n",
            "Epoch 852/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0248 - accuracy: 1.0000 - val_loss: 0.2729 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00852: loss did not improve from 0.02455\n",
            "Epoch 853/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0243 - accuracy: 1.0000 - val_loss: 0.2726 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00853: loss improved from 0.02455 to 0.02425, saving model to Emotion_detection.h5\n",
            "Epoch 854/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0242 - accuracy: 1.0000 - val_loss: 0.2832 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00854: loss improved from 0.02425 to 0.02420, saving model to Emotion_detection.h5\n",
            "Epoch 855/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0236 - accuracy: 1.0000 - val_loss: 0.2866 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00855: loss improved from 0.02420 to 0.02358, saving model to Emotion_detection.h5\n",
            "Epoch 856/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0242 - accuracy: 1.0000 - val_loss: 0.2735 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00856: loss did not improve from 0.02358\n",
            "Epoch 857/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0239 - accuracy: 1.0000 - val_loss: 0.2852 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00857: loss did not improve from 0.02358\n",
            "Epoch 858/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0287 - accuracy: 0.9966 - val_loss: 0.3564 - val_accuracy: 0.9553\n",
            "\n",
            "Epoch 00858: loss did not improve from 0.02358\n",
            "Epoch 859/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0462 - accuracy: 0.9934 - val_loss: 0.2089 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00859: loss did not improve from 0.02358\n",
            "Epoch 860/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0678 - accuracy: 0.9822 - val_loss: 0.1861 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00860: loss did not improve from 0.02358\n",
            "Epoch 861/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0605 - accuracy: 0.9930 - val_loss: 0.2238 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00861: loss did not improve from 0.02358\n",
            "Epoch 862/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0534 - accuracy: 0.9965 - val_loss: 0.2101 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00862: loss did not improve from 0.02358\n",
            "Epoch 863/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0479 - accuracy: 0.9951 - val_loss: 0.2630 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00863: loss did not improve from 0.02358\n",
            "Epoch 864/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0371 - accuracy: 0.9981 - val_loss: 0.2656 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00864: loss did not improve from 0.02358\n",
            "Epoch 865/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0315 - accuracy: 1.0000 - val_loss: 0.2445 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00865: loss did not improve from 0.02358\n",
            "Epoch 866/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0306 - accuracy: 1.0000 - val_loss: 0.2571 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00866: loss did not improve from 0.02358\n",
            "Epoch 867/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0300 - accuracy: 1.0000 - val_loss: 0.2613 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00867: loss did not improve from 0.02358\n",
            "Epoch 868/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0299 - accuracy: 1.0000 - val_loss: 0.2940 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00868: loss did not improve from 0.02358\n",
            "Epoch 869/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0298 - accuracy: 0.9991 - val_loss: 0.2601 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00869: loss did not improve from 0.02358\n",
            "Epoch 870/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0351 - accuracy: 0.9984 - val_loss: 0.3257 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00870: loss did not improve from 0.02358\n",
            "Epoch 871/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0350 - accuracy: 0.9961 - val_loss: 0.2401 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00871: loss did not improve from 0.02358\n",
            "Epoch 872/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0348 - accuracy: 0.9992 - val_loss: 0.2941 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00872: loss did not improve from 0.02358\n",
            "Epoch 873/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0452 - accuracy: 0.9945 - val_loss: 0.2668 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00873: loss did not improve from 0.02358\n",
            "Epoch 874/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0311 - accuracy: 1.0000 - val_loss: 0.2829 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00874: loss did not improve from 0.02358\n",
            "Epoch 875/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0283 - accuracy: 1.0000 - val_loss: 0.2952 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00875: loss did not improve from 0.02358\n",
            "Epoch 876/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2935 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00876: loss did not improve from 0.02358\n",
            "Epoch 877/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0274 - accuracy: 1.0000 - val_loss: 0.2978 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00877: loss did not improve from 0.02358\n",
            "Epoch 878/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0268 - accuracy: 1.0000 - val_loss: 0.2922 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00878: loss did not improve from 0.02358\n",
            "Epoch 879/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0264 - accuracy: 1.0000 - val_loss: 0.2922 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00879: loss did not improve from 0.02358\n",
            "Epoch 880/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2966 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00880: loss did not improve from 0.02358\n",
            "Epoch 881/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0259 - accuracy: 1.0000 - val_loss: 0.2992 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00881: loss did not improve from 0.02358\n",
            "Epoch 882/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0257 - accuracy: 1.0000 - val_loss: 0.2962 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00882: loss did not improve from 0.02358\n",
            "Epoch 883/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0254 - accuracy: 1.0000 - val_loss: 0.2976 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00883: loss did not improve from 0.02358\n",
            "Epoch 884/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0254 - accuracy: 1.0000 - val_loss: 0.2923 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00884: loss did not improve from 0.02358\n",
            "Epoch 885/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0340 - accuracy: 0.9971 - val_loss: 0.2457 - val_accuracy: 0.9593\n",
            "\n",
            "Epoch 00885: loss did not improve from 0.02358\n",
            "Epoch 886/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.1199 - accuracy: 0.9645 - val_loss: 0.1864 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00886: loss did not improve from 0.02358\n",
            "Epoch 887/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0479 - accuracy: 0.9917 - val_loss: 0.2093 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00887: loss did not improve from 0.02358\n",
            "Epoch 888/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0491 - accuracy: 0.9894 - val_loss: 0.2450 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00888: loss did not improve from 0.02358\n",
            "Epoch 889/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0313 - accuracy: 1.0000 - val_loss: 0.2018 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00889: loss did not improve from 0.02358\n",
            "Epoch 890/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0341 - accuracy: 0.9981 - val_loss: 0.2686 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00890: loss did not improve from 0.02358\n",
            "Epoch 891/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0300 - accuracy: 0.9991 - val_loss: 0.2781 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00891: loss did not improve from 0.02358\n",
            "Epoch 892/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0295 - accuracy: 1.0000 - val_loss: 0.2607 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00892: loss did not improve from 0.02358\n",
            "Epoch 893/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0284 - accuracy: 1.0000 - val_loss: 0.2604 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00893: loss did not improve from 0.02358\n",
            "Epoch 894/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0288 - accuracy: 1.0000 - val_loss: 0.2570 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00894: loss did not improve from 0.02358\n",
            "Epoch 895/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0282 - accuracy: 1.0000 - val_loss: 0.2473 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00895: loss did not improve from 0.02358\n",
            "Epoch 896/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0284 - accuracy: 1.0000 - val_loss: 0.2725 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00896: loss did not improve from 0.02358\n",
            "Epoch 897/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0275 - accuracy: 1.0000 - val_loss: 0.2714 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00897: loss did not improve from 0.02358\n",
            "Epoch 898/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0271 - accuracy: 1.0000 - val_loss: 0.2795 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00898: loss did not improve from 0.02358\n",
            "Epoch 899/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0271 - accuracy: 1.0000 - val_loss: 0.2876 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00899: loss did not improve from 0.02358\n",
            "Epoch 900/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0313 - accuracy: 0.9967 - val_loss: 0.2748 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00900: loss did not improve from 0.02358\n",
            "Epoch 901/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0621 - accuracy: 0.9902 - val_loss: 0.2359 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00901: loss did not improve from 0.02358\n",
            "Epoch 902/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0321 - accuracy: 0.9982 - val_loss: 0.2217 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00902: loss did not improve from 0.02358\n",
            "Epoch 903/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0364 - accuracy: 0.9986 - val_loss: 0.2530 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00903: loss did not improve from 0.02358\n",
            "Epoch 904/1000\n",
            "23/23 [==============================] - 6s 275ms/step - loss: 0.0290 - accuracy: 1.0000 - val_loss: 0.2681 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00904: loss did not improve from 0.02358\n",
            "Epoch 905/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0279 - accuracy: 1.0000 - val_loss: 0.2554 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00905: loss did not improve from 0.02358\n",
            "Epoch 906/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0281 - accuracy: 0.9987 - val_loss: 0.2774 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00906: loss did not improve from 0.02358\n",
            "Epoch 907/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0341 - accuracy: 0.9968 - val_loss: 0.2299 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00907: loss did not improve from 0.02358\n",
            "Epoch 908/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0292 - accuracy: 1.0000 - val_loss: 0.2306 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00908: loss did not improve from 0.02358\n",
            "Epoch 909/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0286 - accuracy: 0.9978 - val_loss: 0.2339 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00909: loss did not improve from 0.02358\n",
            "Epoch 910/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0278 - accuracy: 1.0000 - val_loss: 0.2429 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00910: loss did not improve from 0.02358\n",
            "Epoch 911/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0289 - accuracy: 0.9986 - val_loss: 0.2642 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00911: loss did not improve from 0.02358\n",
            "Epoch 912/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0283 - accuracy: 0.9987 - val_loss: 0.2313 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00912: loss did not improve from 0.02358\n",
            "Epoch 913/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0337 - accuracy: 0.9971 - val_loss: 0.2240 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00913: loss did not improve from 0.02358\n",
            "Epoch 914/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0341 - accuracy: 0.9985 - val_loss: 0.2722 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00914: loss did not improve from 0.02358\n",
            "Epoch 915/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0326 - accuracy: 1.0000 - val_loss: 0.2565 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00915: loss did not improve from 0.02358\n",
            "Epoch 916/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0279 - accuracy: 1.0000 - val_loss: 0.2946 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00916: loss did not improve from 0.02358\n",
            "Epoch 917/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0273 - accuracy: 1.0000 - val_loss: 0.2726 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00917: loss did not improve from 0.02358\n",
            "Epoch 918/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0264 - accuracy: 1.0000 - val_loss: 0.2794 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00918: loss did not improve from 0.02358\n",
            "Epoch 919/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0260 - accuracy: 1.0000 - val_loss: 0.2828 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00919: loss did not improve from 0.02358\n",
            "Epoch 920/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0256 - accuracy: 1.0000 - val_loss: 0.2830 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00920: loss did not improve from 0.02358\n",
            "Epoch 921/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0256 - accuracy: 1.0000 - val_loss: 0.2983 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00921: loss did not improve from 0.02358\n",
            "Epoch 922/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0251 - accuracy: 1.0000 - val_loss: 0.3095 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00922: loss did not improve from 0.02358\n",
            "Epoch 923/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0251 - accuracy: 1.0000 - val_loss: 0.3019 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00923: loss did not improve from 0.02358\n",
            "Epoch 924/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0246 - accuracy: 1.0000 - val_loss: 0.2917 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00924: loss did not improve from 0.02358\n",
            "Epoch 925/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0263 - accuracy: 0.9975 - val_loss: 0.2817 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00925: loss did not improve from 0.02358\n",
            "Epoch 926/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0263 - accuracy: 0.9991 - val_loss: 0.3096 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00926: loss did not improve from 0.02358\n",
            "Epoch 927/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0557 - accuracy: 0.9881 - val_loss: 0.2444 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00927: loss did not improve from 0.02358\n",
            "Epoch 928/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0516 - accuracy: 0.9876 - val_loss: 0.3063 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00928: loss did not improve from 0.02358\n",
            "Epoch 929/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0381 - accuracy: 0.9961 - val_loss: 0.2610 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00929: loss did not improve from 0.02358\n",
            "Epoch 930/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0324 - accuracy: 0.9984 - val_loss: 0.2177 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00930: loss did not improve from 0.02358\n",
            "Epoch 931/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0411 - accuracy: 0.9943 - val_loss: 0.2171 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00931: loss did not improve from 0.02358\n",
            "Epoch 932/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0371 - accuracy: 0.9978 - val_loss: 0.2749 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00932: loss did not improve from 0.02358\n",
            "Epoch 933/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0294 - accuracy: 0.9993 - val_loss: 0.2467 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00933: loss did not improve from 0.02358\n",
            "Epoch 934/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0403 - accuracy: 0.9947 - val_loss: 0.2726 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00934: loss did not improve from 0.02358\n",
            "Epoch 935/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0336 - accuracy: 0.9951 - val_loss: 0.2973 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00935: loss did not improve from 0.02358\n",
            "Epoch 936/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0311 - accuracy: 0.9997 - val_loss: 0.2976 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00936: loss did not improve from 0.02358\n",
            "Epoch 937/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0272 - accuracy: 1.0000 - val_loss: 0.2629 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00937: loss did not improve from 0.02358\n",
            "Epoch 938/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0280 - accuracy: 1.0000 - val_loss: 0.2739 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00938: loss did not improve from 0.02358\n",
            "Epoch 939/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0311 - accuracy: 0.9978 - val_loss: 0.3266 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00939: loss did not improve from 0.02358\n",
            "Epoch 940/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0363 - accuracy: 0.9983 - val_loss: 0.2740 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00940: loss did not improve from 0.02358\n",
            "Epoch 941/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0346 - accuracy: 0.9984 - val_loss: 0.3124 - val_accuracy: 0.9634\n",
            "\n",
            "Epoch 00941: loss did not improve from 0.02358\n",
            "Epoch 942/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0460 - accuracy: 0.9971 - val_loss: 0.4101 - val_accuracy: 0.9512\n",
            "\n",
            "Epoch 00942: loss did not improve from 0.02358\n",
            "Epoch 943/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0446 - accuracy: 0.9922 - val_loss: 0.2361 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00943: loss did not improve from 0.02358\n",
            "Epoch 944/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0286 - accuracy: 1.0000 - val_loss: 0.2644 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00944: loss did not improve from 0.02358\n",
            "Epoch 945/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0285 - accuracy: 1.0000 - val_loss: 0.2989 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00945: loss did not improve from 0.02358\n",
            "Epoch 946/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0275 - accuracy: 1.0000 - val_loss: 0.3069 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00946: loss did not improve from 0.02358\n",
            "Epoch 947/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0276 - accuracy: 1.0000 - val_loss: 0.2758 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00947: loss did not improve from 0.02358\n",
            "Epoch 948/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0299 - accuracy: 0.9970 - val_loss: 0.2357 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00948: loss did not improve from 0.02358\n",
            "Epoch 949/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0275 - accuracy: 1.0000 - val_loss: 0.2555 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00949: loss did not improve from 0.02358\n",
            "Epoch 950/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0270 - accuracy: 1.0000 - val_loss: 0.2530 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00950: loss did not improve from 0.02358\n",
            "Epoch 951/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0283 - accuracy: 1.0000 - val_loss: 0.2603 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00951: loss did not improve from 0.02358\n",
            "Epoch 952/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0266 - accuracy: 1.0000 - val_loss: 0.2698 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00952: loss did not improve from 0.02358\n",
            "Epoch 953/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0272 - accuracy: 1.0000 - val_loss: 0.2555 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00953: loss did not improve from 0.02358\n",
            "Epoch 954/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0269 - accuracy: 0.9992 - val_loss: 0.2408 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00954: loss did not improve from 0.02358\n",
            "Epoch 955/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0337 - accuracy: 0.9976 - val_loss: 0.2959 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00955: loss did not improve from 0.02358\n",
            "Epoch 956/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0464 - accuracy: 0.9930 - val_loss: 0.2246 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00956: loss did not improve from 0.02358\n",
            "Epoch 957/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0374 - accuracy: 0.9988 - val_loss: 0.2612 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00957: loss did not improve from 0.02358\n",
            "Epoch 958/1000\n",
            "23/23 [==============================] - 6s 276ms/step - loss: 0.0327 - accuracy: 0.9997 - val_loss: 0.2492 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00958: loss did not improve from 0.02358\n",
            "Epoch 959/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0297 - accuracy: 1.0000 - val_loss: 0.2369 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00959: loss did not improve from 0.02358\n",
            "Epoch 960/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0311 - accuracy: 0.9969 - val_loss: 0.2464 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00960: loss did not improve from 0.02358\n",
            "Epoch 961/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0305 - accuracy: 0.9991 - val_loss: 0.2641 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00961: loss did not improve from 0.02358\n",
            "Epoch 962/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0312 - accuracy: 0.9988 - val_loss: 0.2395 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00962: loss did not improve from 0.02358\n",
            "Epoch 963/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0328 - accuracy: 0.9996 - val_loss: 0.3296 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00963: loss did not improve from 0.02358\n",
            "Epoch 964/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0290 - accuracy: 0.9992 - val_loss: 0.2307 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00964: loss did not improve from 0.02358\n",
            "Epoch 965/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0498 - accuracy: 0.9901 - val_loss: 0.2719 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00965: loss did not improve from 0.02358\n",
            "Epoch 966/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0301 - accuracy: 1.0000 - val_loss: 0.2712 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00966: loss did not improve from 0.02358\n",
            "Epoch 967/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0276 - accuracy: 1.0000 - val_loss: 0.2462 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00967: loss did not improve from 0.02358\n",
            "Epoch 968/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0270 - accuracy: 1.0000 - val_loss: 0.2520 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00968: loss did not improve from 0.02358\n",
            "Epoch 969/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0290 - accuracy: 0.9983 - val_loss: 0.2590 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00969: loss did not improve from 0.02358\n",
            "Epoch 970/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0282 - accuracy: 1.0000 - val_loss: 0.2654 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00970: loss did not improve from 0.02358\n",
            "Epoch 971/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0267 - accuracy: 1.0000 - val_loss: 0.2614 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00971: loss did not improve from 0.02358\n",
            "Epoch 972/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0261 - accuracy: 1.0000 - val_loss: 0.2584 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00972: loss did not improve from 0.02358\n",
            "Epoch 973/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0280 - accuracy: 0.9982 - val_loss: 0.2926 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00973: loss did not improve from 0.02358\n",
            "Epoch 974/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0271 - accuracy: 1.0000 - val_loss: 0.2535 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00974: loss did not improve from 0.02358\n",
            "Epoch 975/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0266 - accuracy: 1.0000 - val_loss: 0.2838 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00975: loss did not improve from 0.02358\n",
            "Epoch 976/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0250 - accuracy: 1.0000 - val_loss: 0.2899 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00976: loss did not improve from 0.02358\n",
            "Epoch 977/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0249 - accuracy: 1.0000 - val_loss: 0.2780 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00977: loss did not improve from 0.02358\n",
            "Epoch 978/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0245 - accuracy: 1.0000 - val_loss: 0.2685 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00978: loss did not improve from 0.02358\n",
            "Epoch 979/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0242 - accuracy: 1.0000 - val_loss: 0.2727 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00979: loss did not improve from 0.02358\n",
            "Epoch 980/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0240 - accuracy: 1.0000 - val_loss: 0.2682 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00980: loss did not improve from 0.02358\n",
            "Epoch 981/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0238 - accuracy: 1.0000 - val_loss: 0.2685 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00981: loss did not improve from 0.02358\n",
            "Epoch 982/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0240 - accuracy: 1.0000 - val_loss: 0.2870 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00982: loss did not improve from 0.02358\n",
            "Epoch 983/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0234 - accuracy: 1.0000 - val_loss: 0.2851 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 00983: loss improved from 0.02358 to 0.02347, saving model to Emotion_detection.h5\n",
            "Epoch 984/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0229 - accuracy: 1.0000 - val_loss: 0.2721 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00984: loss improved from 0.02347 to 0.02294, saving model to Emotion_detection.h5\n",
            "Epoch 985/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0227 - accuracy: 1.0000 - val_loss: 0.2693 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00985: loss improved from 0.02294 to 0.02268, saving model to Emotion_detection.h5\n",
            "Epoch 986/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0224 - accuracy: 1.0000 - val_loss: 0.2738 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00986: loss improved from 0.02268 to 0.02254, saving model to Emotion_detection.h5\n",
            "Epoch 987/1000\n",
            "23/23 [==============================] - 6s 281ms/step - loss: 0.0233 - accuracy: 0.9988 - val_loss: 0.3231 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00987: loss did not improve from 0.02254\n",
            "Epoch 988/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0233 - accuracy: 1.0000 - val_loss: 0.2600 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00988: loss did not improve from 0.02254\n",
            "Epoch 989/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0219 - accuracy: 1.0000 - val_loss: 0.2566 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00989: loss improved from 0.02254 to 0.02187, saving model to Emotion_detection.h5\n",
            "Epoch 990/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0223 - accuracy: 1.0000 - val_loss: 0.2602 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00990: loss did not improve from 0.02187\n",
            "Epoch 991/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0248 - accuracy: 0.9986 - val_loss: 0.3314 - val_accuracy: 0.9675\n",
            "\n",
            "Epoch 00991: loss did not improve from 0.02187\n",
            "Epoch 992/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0340 - accuracy: 0.9951 - val_loss: 0.2082 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00992: loss did not improve from 0.02187\n",
            "Epoch 993/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0444 - accuracy: 0.9915 - val_loss: 0.2658 - val_accuracy: 0.9715\n",
            "\n",
            "Epoch 00993: loss did not improve from 0.02187\n",
            "Epoch 994/1000\n",
            "23/23 [==============================] - 6s 279ms/step - loss: 0.0368 - accuracy: 0.9949 - val_loss: 0.2120 - val_accuracy: 0.9837\n",
            "\n",
            "Epoch 00994: loss did not improve from 0.02187\n",
            "Epoch 995/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0667 - accuracy: 0.9845 - val_loss: 0.2073 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00995: loss did not improve from 0.02187\n",
            "Epoch 996/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0346 - accuracy: 0.9982 - val_loss: 0.2352 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00996: loss did not improve from 0.02187\n",
            "Epoch 997/1000\n",
            "23/23 [==============================] - 6s 278ms/step - loss: 0.0374 - accuracy: 0.9966 - val_loss: 0.2333 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00997: loss did not improve from 0.02187\n",
            "Epoch 998/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0455 - accuracy: 0.9953 - val_loss: 0.2204 - val_accuracy: 0.9878\n",
            "\n",
            "Epoch 00998: loss did not improve from 0.02187\n",
            "Epoch 999/1000\n",
            "23/23 [==============================] - 6s 280ms/step - loss: 0.0419 - accuracy: 0.9975 - val_loss: 0.2186 - val_accuracy: 0.9756\n",
            "\n",
            "Epoch 00999: loss did not improve from 0.02187\n",
            "Epoch 1000/1000\n",
            "23/23 [==============================] - 6s 277ms/step - loss: 0.0289 - accuracy: 0.9998 - val_loss: 0.2544 - val_accuracy: 0.9797\n",
            "\n",
            "Epoch 01000: loss did not improve from 0.02187\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ONp4QSBfQQG0"
      },
      "source": [
        "### Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zGBB-gJfTl4h",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8af279b4-56f4-40d4-e404-56dd3dc509f5"
      },
      "source": [
        "score = Model.evaluate(X_train, Y_train)"
      ],
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "23/23 [==============================] - 1s 56ms/step - loss: 0.0265 - accuracy: 1.0000\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "u5zEPcF3I9Hz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8a77cde2-b97a-45d9-a4be-a232a6531994"
      },
      "source": [
        "score = Model.evaluate(X_test, Y_test)"
      ],
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "8/8 [==============================] - 0s 54ms/step - loss: 0.2544 - accuracy: 0.9797\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JQW8rjpGJHUh"
      },
      "source": [
        "Pred=Model.predict(X_test)"
      ],
      "execution_count": 31,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tQMFS78EJgyf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7dfb10eb-d361-4829-c62c-ace74f57560a"
      },
      "source": [
        "Pred"
      ],
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[1.9061863e-03, 1.9664186e-12, 6.8733894e-09, ..., 1.0000000e+00,\n",
              "        2.2312981e-06, 7.5254142e-03],\n",
              "       [5.8472157e-04, 2.0951221e-09, 1.8953681e-03, ..., 4.3186545e-04,\n",
              "        9.9959815e-01, 1.0602742e-02],\n",
              "       [4.8848331e-02, 2.8886938e-01, 9.9999845e-01, ..., 9.3090527e-08,\n",
              "        5.5994093e-03, 1.9739013e-11],\n",
              "       ...,\n",
              "       [1.4455318e-03, 7.2671091e-11, 1.3976296e-08, ..., 1.0000000e+00,\n",
              "        2.0530526e-06, 1.9629747e-02],\n",
              "       [2.2560358e-04, 1.6532990e-01, 1.7569375e-05, ..., 1.5139580e-04,\n",
              "        1.0479044e-05, 9.3320936e-02],\n",
              "       [9.7874999e-02, 9.9504399e-01, 9.5754564e-03, ..., 1.5609860e-03,\n",
              "        2.4074316e-04, 4.4285089e-02]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "y5UbFqk3Jjin",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2381a9e1-1fcd-4904-f9f8-8ad7a86c1128"
      },
      "source": [
        "Y_test"
      ],
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0., 0., 0., ..., 1., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 1., 0.],\n",
              "       [0., 0., 1., ..., 0., 0., 0.],\n",
              "       ...,\n",
              "       [0., 0., 0., ..., 1., 0., 0.],\n",
              "       [0., 0., 0., ..., 0., 0., 0.],\n",
              "       [0., 1., 0., ..., 0., 0., 0.]], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lumQfISRJmF8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f122ff14-b1ca-4f9d-e7ed-3c80f8542310"
      },
      "source": [
        "len(Pred)"
      ],
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "246"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U3WmRMWhNxVh"
      },
      "source": [
        "def test_image(ind,images_f,images_f_2,Model):\n",
        "  cv2_imshow(images_f[ind])\n",
        "  image_test=images_f_2[ind]\n",
        "  print(\"Label actual:  \" + Exp[labels[ind]]  )\n",
        "  pred_1=Model.predict(np.array([image_test]))\n",
        "  #print(pred_1)\n",
        "  pred_class=Exp[int(np.argmax(pred_1))]\n",
        "  print(\"Predicted Label: \"+ pred_class)\n",
        "\n"
      ],
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R-k9IW1dOgyz",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "5bf9e49f-10ab-456e-9b51-3695e43522c7"
      },
      "source": [
        "test_image(72,images_f,images_f_2,Model)"
      ],
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF5985C10>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  fear\n",
            "Predicted Label: fear\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AcleDEVuNpvX",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "d52c6b2f-3d49-4bbf-9298-ebe65fa5de0e"
      },
      "source": [
        "test_image(36,images_f,images_f_2,Model)"
      ],
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF59F1E90>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  fear\n",
            "Predicted Label: fear\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dcwbyrEgO3YK",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "76965551-9098-42cc-ff94-53319815863f"
      },
      "source": [
        "test_image(122,images_f,images_f_2,Model)"
      ],
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF6A6AE90>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  disgust\n",
            "Predicted Label: disgust\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vgLf7NGWP7bm",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "a7ca7d45-d28a-41e8-9295-b514eb509f44"
      },
      "source": [
        "test_image(132,images_f,images_f_2,Model)"
      ],
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF6A1A6D0>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  disgust\n",
            "Predicted Label: disgust\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B6bdhwOhP-li",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "f5b12e18-1a30-40fa-c8d3-0dc368a87c5a"
      },
      "source": [
        "test_image(147,images_f,images_f_2,Model)"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF6A6ECD0>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  disgust\n",
            "Predicted Label: disgust\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4k4ELPe5QBhc",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "37b46180-7e82-4d99-969c-b87f3af81e21"
      },
      "source": [
        "test_image(369,images_f,images_f_2,Model)"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF69E6650>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  anger\n",
            "Predicted Label: anger\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fpz-wzUCQGX-",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "77c96daa-6a07-4bde-da24-b5575dfd38f7"
      },
      "source": [
        "test_image(502,images_f,images_f_2,Model)"
      ],
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF6983D10>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  contempt\n",
            "Predicted Label: contempt\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YA8uKPvGQJfC",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 98
        },
        "outputId": "94120174-19ee-4925-d0f0-cd9da5039bf2"
      },
      "source": [
        "test_image(800,images_f,images_f_2,Model)"
      ],
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=48x48 at 0x7FBBF5A55ED0>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Label actual:  happy\n",
            "Predicted Label: happy\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Tyx5ao4dQgMQ"
      },
      "source": [
        "import matplotlib.pyplot as plt\n"
      ],
      "execution_count": 44,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XQ5pvdm4QNtF",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 366
        },
        "outputId": "a1d40680-785c-4872-d7e8-b9d31a3c634d"
      },
      "source": [
        "plt.plot(History.history['loss'])\n",
        "plt.plot(History.history['val_loss'])\n",
        "plt.title('Model loss')\n",
        "plt.ylabel('Loss')\n",
        "plt.xlabel('Epoch')\n",
        "plt.legend(['Train', 'Validation'], loc='upper left')\n",
        "plt.subplots_adjust(top=1.00, bottom=0.0, left=0.0, right=0.95, hspace=0.25,\n",
        "                        wspace=0.35)"
      ],
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UycVjuzdQlW8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 366
        },
        "outputId": "253351c9-3a4a-4bb4-cf1a-17aa05968779"
      },
      "source": [
        "plt.plot(History.history['accuracy'])\n",
        "plt.plot(History.history['val_accuracy'])\n",
        "plt.title('Model accuracy')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.xlabel('Epoch')\n",
        "plt.legend(['Train', 'Validation'], loc='upper left')\n",
        "plt.subplots_adjust(top=1.00, bottom=0.0, left=0.0, right=0.95, hspace=0.25,\n",
        "                        wspace=0.35)"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9pAhlICdRUgG"
      },
      "source": [
        "from sklearn.metrics import confusion_matrix \n",
        "\n",
        "from sklearn.metrics import classification_report "
      ],
      "execution_count": 47,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Je6eHsWERabS"
      },
      "source": [
        "i=0\n",
        "Y_test_l=[]\n",
        "Pred_l=[]\n",
        "while(i<len(Pred)):\n",
        "  Y_test_l.append(int(np.argmax(Y_test[i])))\n",
        "  Pred_l.append(int(np.argmax(Pred[i])))\n",
        "  i+=1\n"
      ],
      "execution_count": 48,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IGRVFqYEQ0fx"
      },
      "source": [
        "\n",
        "report=classification_report(Y_test_l, Pred_l)"
      ],
      "execution_count": 49,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gXLt0q86SiI2",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "dead7a16-b0ed-4a9c-d99f-f26bc06a3529"
      },
      "source": [
        "print(report)"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       1.00      1.00      1.00        17\n",
            "           1       0.83      1.00      0.91        15\n",
            "           2       1.00      1.00      1.00        51\n",
            "           3       0.95      1.00      0.97        36\n",
            "           4       1.00      0.95      0.98        66\n",
            "           5       1.00      1.00      1.00        39\n",
            "           6       1.00      0.91      0.95        22\n",
            "\n",
            "    accuracy                           0.98       246\n",
            "   macro avg       0.97      0.98      0.97       246\n",
            "weighted avg       0.98      0.98      0.98       246\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7LcBCMAESlya"
      },
      "source": [
        "\n",
        "results = confusion_matrix(Y_test_l, Pred_l)"
      ],
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B5x8_HqWSry3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 282
        },
        "outputId": "f2c6d6da-1947-49dd-fd87-9b167547f7ad"
      },
      "source": [
        "import seaborn as sns\n",
        "\n",
        "sns.heatmap(results, annot=True)"
      ],
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7fbbf63cd090>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}