Auto_Encoder.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Auto Encoder.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyPuPF9GNhTBjpifhFzVQk4d",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/HeshanDissanayake/Convolutional_Auto_encoder/blob/main/Auto_Encoder.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "FUv8cFPGeezm"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yQ0qq5dIlDlf"
      },
      "source": [
        "import os\n",
        "os.environ['KAGGLE_CONFIG_DIR'] = \"/content/gdrive/My Drive/Kaggle\""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Nj6lPlsYlsTt"
      },
      "source": [
        "!kaggle datasets"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CyVB5w9COdVR"
      },
      "source": [
        "!kaggle -h"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7AEh4l2YmTZC",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 104
        },
        "outputId": "e7d85f59-2151-4135-ee3a-b358a69f8cd8"
      },
      "source": [
        "!unzip lfwpeople.zip"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Archive:  lfwpeople.zip\n",
            "  inflating: lfw-funneled.tgz        \n",
            "  inflating: pairs.txt               \n",
            "  inflating: pairsDevTest.txt        \n",
            "  inflating: pairsDevTrain.txt       \n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Q3KEnpoTmnuw"
      },
      "source": [
        "!tar zxvf lfw-funneled.tgz"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LdnHSUAinCqy"
      },
      "source": [
        "!mkdir Faces\n",
        "!mkdir Faces/faces"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5-5yk83K24d4"
      },
      "source": [
        "for (root, dirs, files) in os.walk('/content/lfw_funneled',topdown=True):\n",
        "  for file in files:\n",
        "    if file.endswith('.jpg'):\n",
        "      os.system('sudo p %s/%s /content/Faces/faces/%s'%(root,file,file))\n",
        "\n",
        "\n",
        "  "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6VwXQMuI9_2d"
      },
      "source": [
        "from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, add, Dropout, Flatten, Dense, Reshape\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras import regularizers\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "import matplotlib.pyplot as plt\n",
        "import cv2\n",
        "import numpy as np\n",
        "from skimage.transform import resize, rescale\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TNTalm07jSKK"
      },
      "source": [
        "def combine_generator(gen1, gen2):\n",
        "    while True:\n",
        "        yield(next(gen1), next(gen2))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hgVxOouGLsxs",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 52
        },
        "outputId": "e197220e-6f46-426c-9ee3-f7d29b7bb430"
      },
      "source": [
        "color_datagen = ImageDataGenerator(rescale=1/255)\n",
        "bw_datagen = ImageDataGenerator(rescale=1/255)\n",
        "\n",
        "color_generator = color_datagen.flow_from_directory(directory='/content/Faces/', class_mode= None , shuffle=False, seed =1,batch_size=33)\n",
        "bw_generator = bw_datagen.flow_from_directory(directory='/content/Faces/', class_mode= None , shuffle=False, color_mode ='grayscale'\n",
        "                 ,batch_size=33, seed =1 )\n",
        "\n",
        "traingen = combine_generator(bw_generator, color_generator)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 13233 images belonging to 1 classes.\n",
            "Found 13233 images belonging to 1 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "N5TIRY4nB5Gb",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "78cae398-cd09-40b3-e7f9-a6c575bdccb4"
      },
      "source": [
        "datagen = ImageDataGenerator(rescale = 1./255)\n",
        "traingen =  datagen.flow_from_directory(directory='/content/Faces/', class_mode= 'input' , shuffle=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 13233 images belonging to 1 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xKRWrQhQ16Du",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "223ba8ca-3fe3-4e89-b375-5acc17a29477"
      },
      "source": [
        "\n",
        "for batch in traingen:\n",
        "  \n",
        "  plt.subplot(1,2,1)\n",
        "  plt.imshow(batch[0][0,:,:,:])\n",
        "\n",
        "  plt.subplot(1,2,2)\n",
        "  plt.imshow(batch[1][0,:,:,:])\n",
        "  plt.show()\n",
        "  break"
      ],
      "execution_count": null,
      "outputs": [
        {
          "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"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Adfp2qAZcQkh"
      },
      "source": [
        "input_layer = Input(shape = (256, 256, 1))\n",
        "l1 = Conv2D(64, (3,3), activation='relu', padding='same',activity_regularizer=regularizers.l1(10e-10))(input_layer)\n",
        "l2 = Conv2D(64, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l1)\n",
        "l2 = Dropout(0.3)(l2)\n",
        "\n",
        "l3 = MaxPooling2D((2,2))(l2)\n",
        "l4 = Conv2D(128, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l3)\n",
        "l5 = Conv2D(128, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l4)\n",
        "l6 = MaxPooling2D((2,2))(l5)\n",
        "l7 = Conv2D(256, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l6)\n",
        "\n",
        "encoder = Model(input_layer, l7)\n",
        "encoder.summary()\n",
        "\n",
        "\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "z2UQWrtDcPG3"
      },
      "source": [
        "l8 = UpSampling2D()(l7)\n",
        "l9  = Conv2D(128, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l8)\n",
        "l10 = Conv2D(128, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l9)\n",
        "l11 = add([l10, l5]) \n",
        "l12 = UpSampling2D()(l11)\n",
        "\n",
        "l13 = Conv2D(64, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l12)\n",
        "l14 = Conv2D(64, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l13)\n",
        "l15 = add([l14,l2])\n",
        "l16 = Conv2D(3, (3,3), activation='relu', padding='same', activity_regularizer=regularizers.l1(10e-10))(l15)\n",
        "auto_encoder = Model(input_layer, l16)\n",
        "auto_encoder.summary()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K4FWzwhVHPZ8"
      },
      "source": [
        "auto_encoder.compile(optimizer = \"adadelta\", loss = \"sparse_categorical_crossentropy\", metrics=['accuracy'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "H6PPIHWUozUk",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 434
        },
        "outputId": "446009a1-dcf3-447c-e6e6-e1f563479749"
      },
      "source": [
        "history = auto_encoder.fit(traingen, epochs=200 , steps_per_epoch=400)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/200\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "error",
          "ename": "ResourceExhaustedError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mResourceExhaustedError\u001b[0m                    Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-22-53e643c2510f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mhistory\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mauto_encoder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtraingen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m200\u001b[0m \u001b[0;34m,\u001b[0m \u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m400\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36m_method_wrapper\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m     64\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0m_method_wrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     65\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_in_multi_worker_mode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 66\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     67\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     68\u001b[0m     \u001b[0;31m# Running inside `run_distribute_coordinator` already.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m    846\u001b[0m                 batch_size=batch_size):\n\u001b[1;32m    847\u001b[0m               \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 848\u001b[0;31m               \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    849\u001b[0m               \u001b[0;31m# Catch OutOfRangeError for Datasets of unknown size.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    850\u001b[0m               \u001b[0;31m# This blocks until the batch has finished executing.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    578\u001b[0m         \u001b[0mxla_context\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mExit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    579\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 580\u001b[0;31m       \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    581\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    582\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mtracing_count\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    642\u001b[0m         \u001b[0;31m# Lifting succeeded, so variables are initialized and we can run the\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    643\u001b[0m         \u001b[0;31m# stateless function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 644\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    645\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    646\u001b[0m       \u001b[0mcanon_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcanon_kwds\u001b[0m \u001b[0;34m=\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   2418\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2419\u001b[0m       \u001b[0mgraph_function\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2420\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_filtered_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2421\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2422\u001b[0m   \u001b[0;34m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_filtered_call\u001b[0;34m(self, args, kwargs)\u001b[0m\n\u001b[1;32m   1663\u001b[0m          if isinstance(t, (ops.Tensor,\n\u001b[1;32m   1664\u001b[0m                            resource_variable_ops.BaseResourceVariable))),\n\u001b[0;32m-> 1665\u001b[0;31m         self.captured_inputs)\n\u001b[0m\u001b[1;32m   1666\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1667\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0m_call_flat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcaptured_inputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcancellation_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m   1744\u001b[0m       \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1745\u001b[0m       return self._build_call_outputs(self._inference_function.call(\n\u001b[0;32m-> 1746\u001b[0;31m           ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0m\u001b[1;32m   1747\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m   1748\u001b[0m         \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m    596\u001b[0m               \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    597\u001b[0m               \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 598\u001b[0;31m               ctx=ctx)\n\u001b[0m\u001b[1;32m    599\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    600\u001b[0m           outputs = execute.execute_with_cancellation(\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     58\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     59\u001b[0m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0;32m---> 60\u001b[0;31m                                         inputs, attrs, num_outputs)\n\u001b[0m\u001b[1;32m     61\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mResourceExhaustedError\u001b[0m:  OOM when allocating tensor with shape[33,64,256,256] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc\n\t [[node model_1/conv2d_13/ActivityRegularizer/Abs (defined at <ipython-input-22-53e643c2510f>:1) ]]\nHint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.\n [Op:__inference_train_function_4395]\n\nFunction call stack:\ntrain_function\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jwcd7Lgy5jJO",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 269
        },
        "outputId": "abf0c08d-f5fb-4bf6-e856-2f4739b8e034"
      },
      "source": [
        " for batch in traingen:\n",
        "  img = auto_encoder.predict(batch[0])\n",
        "  plt.imshow(img[0])\n",
        "  plt.show()\n",
        "  break"
      ],
      "execution_count": null,
      "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": "bkkOg1KA17lz"
      },
      "source": [
        "\n",
        "dirs = ['/content/dildo.jpg', '/content/me.jpg', '/content/aaasdasdaa.jpeg',\n",
        "        '/content/chanuk.jpg', '/content/rashen.jpg']\n",
        "\n",
        "plt.figure(figsize=(100, 100))\n",
        "i = 0\n",
        "\n",
        "for dir in dirs:\n",
        "\n",
        "  img = resize(plt.imread(dir),(256,256,3))\n",
        "  img = img.reshape(1,256,256,3)\n",
        "\n",
        "\n",
        "  i += 1\n",
        "  ax = plt.subplot(5, 3, i)\n",
        "  plt.imshow(img[0,:,:,:])\n",
        "\n",
        "  encode = encoder.predict(img.reshape((1,256,256,3)))\n",
        "  i += 1\n",
        "  ax = plt.subplot(5, 3, i)\n",
        "  plt.imshow(encode.reshape(25,20))\n",
        "\n",
        "  i += 1\n",
        "  predicted = auto_encoder.predict(img)\n",
        "  ax = plt.subplot(5, 3, i)\n",
        "  plt.imshow(predicted[0,:,:,:])\n",
        "\n",
        "\n",
        "\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LJJ_MH45ecWM"
      },
      "source": [
        "for img in val:\n",
        "  img.shape\n",
        "  break"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iA61crOn2XeD"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}