Corcuera_CNN_Exercise.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 21,
      "metadata": {
        "id": "-hBsyvXhyXj_"
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import tensorflow as tf\n",
        "import keras\n",
        "import numpy as np\n",
        "import cv2\n",
        "import os\n",
        "\n",
        "from keras.backend import categorical_crossentropy\n",
        "from tensorflow.keras.preprocessing import image\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "amA_9w3AzMMR",
        "outputId": "5177bc59-5cf5-4926-a096-fe71dd81d6e0"
      },
      "outputs": [
        {
          "output_type": "error",
          "ename": "FileNotFoundError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-20-5c2fecde483e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     10\u001b[0m                                           \u001b[0mtarget_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m224\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m224\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     11\u001b[0m                                           \u001b[0mbatch_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m32\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 12\u001b[0;31m                                           class_mode = 'categorical')\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/keras/preprocessing/image.py\u001b[0m in \u001b[0;36mflow_from_directory\u001b[0;34m(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio)\u001b[0m\n\u001b[1;32m   1485\u001b[0m         \u001b[0msubset\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msubset\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1486\u001b[0m         \u001b[0minterpolation\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minterpolation\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1487\u001b[0;31m         dtype=self.dtype)\n\u001b[0m\u001b[1;32m   1488\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1489\u001b[0m   def flow_from_dataframe(self,\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/keras/preprocessing/image.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio, dtype)\u001b[0m\n\u001b[1;32m    505\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mclasses\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    506\u001b[0m       \u001b[0mclasses\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--> 507\u001b[0;31m       \u001b[0;32mfor\u001b[0m \u001b[0msubdir\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msorted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\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[0m\u001b[1;32m    508\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubdir\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[1;32m    509\u001b[0m           \u001b[0mclasses\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msubdir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'C:/Users/VINCENT/Downloads/Covid19-dataset/Covid19-dataset/train'"
          ]
        }
      ],
      "source": [
        "from keras.preprocessing.image import ImageDataGenerator\n",
        "from keras.layers import *\n",
        "from keras.models import Sequential\n",
        "\n",
        "\n",
        "data_train = ImageDataGenerator(rescale = 1./255,shear_range = 0.2,zoom_range = 0.2,horizontal_flip = True)\n",
        "\n",
        "train_path = 'C:/Users/VINCENT/Downloads/Covid19-dataset/Covid19-dataset/train'\n",
        "train_dataset = data_train.flow_from_directory(train_path, \n",
        "                                          target_size = (224, 224), \n",
        "                                          batch_size = 32, \n",
        "                                          class_mode = 'categorical')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "oiRb7unk4ZJl",
        "outputId": "cf7ca21b-4049-4912-b88a-c7451a3cac3f"
      },
      "outputs": [
        {
          "output_type": "error",
          "ename": "FileNotFoundError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-24-4402adc5d538>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m                                          \u001b[0mtarget_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m224\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m224\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      5\u001b[0m                                          \u001b[0mbatch_size\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m32\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m                                          class_mode = 'categorical')\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/keras/preprocessing/image.py\u001b[0m in \u001b[0;36mflow_from_directory\u001b[0;34m(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio)\u001b[0m\n\u001b[1;32m   1485\u001b[0m         \u001b[0msubset\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msubset\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1486\u001b[0m         \u001b[0minterpolation\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minterpolation\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1487\u001b[0;31m         dtype=self.dtype)\n\u001b[0m\u001b[1;32m   1488\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1489\u001b[0m   def flow_from_dataframe(self,\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/keras/preprocessing/image.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio, dtype)\u001b[0m\n\u001b[1;32m    505\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mclasses\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    506\u001b[0m       \u001b[0mclasses\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--> 507\u001b[0;31m       \u001b[0;32mfor\u001b[0m \u001b[0msubdir\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msorted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\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[0m\u001b[1;32m    508\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdirectory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msubdir\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[1;32m    509\u001b[0m           \u001b[0mclasses\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msubdir\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'C://Users/VINCENT/Downloads/Covid19-dataset/Covid19-dataset/test'"
          ]
        }
      ],
      "source": [
        "my_test = ImageDataGenerator(rescale=1./255)\n",
        "test_path = 'C:/Users/VINCENT/Downloads/Covid19-dataset/Covid19-dataset/test'\n",
        "test_dataset = data_train.flow_from_directory(test_path, \n",
        "                                         target_size = (224, 224), \n",
        "                                         batch_size = 32, \n",
        "                                         class_mode = 'categorical')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "dVQP21swKyFj",
        "outputId": "ded23e76-3bd1-4750-94ff-8f34fedd774f"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " conv2d (Conv2D)             (None, 222, 222, 32)      896       \n",
            "                                                                 \n",
            " conv2d_1 (Conv2D)           (None, 220, 220, 64)      18496     \n",
            "                                                                 \n",
            " max_pooling2d (MaxPooling2D  (None, 110, 110, 64)     0         \n",
            " )                                                               \n",
            "                                                                 \n",
            " dropout (Dropout)           (None, 110, 110, 64)      0         \n",
            "                                                                 \n",
            " conv2d_2 (Conv2D)           (None, 108, 108, 64)      36928     \n",
            "                                                                 \n",
            " max_pooling2d_1 (MaxPooling  (None, 54, 54, 64)       0         \n",
            " 2D)                                                             \n",
            "                                                                 \n",
            " dropout_1 (Dropout)         (None, 54, 54, 64)        0         \n",
            "                                                                 \n",
            " conv2d_3 (Conv2D)           (None, 52, 52, 128)       73856     \n",
            "                                                                 \n",
            " max_pooling2d_2 (MaxPooling  (None, 26, 26, 128)      0         \n",
            " 2D)                                                             \n",
            "                                                                 \n",
            " dropout_2 (Dropout)         (None, 26, 26, 128)       0         \n",
            "                                                                 \n",
            " flatten (Flatten)           (None, 86528)             0         \n",
            "                                                                 \n",
            " dense (Dense)               (None, 64)                5537856   \n",
            "                                                                 \n",
            " dropout_3 (Dropout)         (None, 64)                0         \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 3)                 195       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 5,668,227\n",
            "Trainable params: 5,668,227\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "model = Sequential()\n",
        "model.add(Conv2D(32,\n",
        "                 kernel_size=(3,3),\n",
        "                 activation='relu',\n",
        "                 input_shape=(224,224,3)))\n",
        "model.add(Conv2D(64, (3,3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2,2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Conv2D(64, (3,3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2,2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Conv2D(128, (3,3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2,2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Flatten())\n",
        "model.add(Dense(64, activation='relu'))\n",
        "model.add(Dropout(0.5))\n",
        "model.add(Dense(3, activation='sigmoid'))\n",
        "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
        "model.summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yWNhXuxceb_a",
        "outputId": "86b2dc17-f38d-4fcf-d6f7-f6c9e0664580",
        "scrolled": true
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "C:\\Users\\lborb\\AppData\\Local\\Temp\\ipykernel_12900\\2625774409.py:1: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n",
            "  history = model.fit_generator(train_dataset,steps_per_epoch=7,epochs = 5,validation_data = test_dataset,validation_steps=2)\n"
          ]
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Epoch 1/5\n",
            "7/7 [==============================] - 106s 16s/step - loss: 1.7723 - accuracy: 0.3871 - val_loss: 1.0954 - val_accuracy: 0.2969\n",
            "Epoch 2/5\n",
            "7/7 [==============================] - 81s 11s/step - loss: 1.0299 - accuracy: 0.5115 - val_loss: 1.0003 - val_accuracy: 0.5781\n",
            "Epoch 3/5\n",
            "7/7 [==============================] - 84s 12s/step - loss: 0.7796 - accuracy: 0.6518 - val_loss: 0.8566 - val_accuracy: 0.5781\n",
            "Epoch 4/5\n",
            "7/7 [==============================] - 98s 14s/step - loss: 0.6911 - accuracy: 0.7005 - val_loss: 0.7338 - val_accuracy: 0.6250\n",
            "Epoch 5/5\n",
            "7/7 [==============================] - 89s 13s/step - loss: 0.6080 - accuracy: 0.7465 - val_loss: 0.6619 - val_accuracy: 0.6719\n"
          ]
        }
      ],
      "source": [
        "history = model.fit_generator(train_dataset,steps_per_epoch=7,epochs = 5,validation_data = test_dataset,validation_steps=2)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gqevIJCM0J7e",
        "outputId": "9d574c6c-1694-4864-dabe-72807a749ac3"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "8/8 [==============================] - 32s 4s/step - loss: 0.4856 - accuracy: 0.8313\n",
            "Test accuracy: 0.8313252925872803\n"
          ]
        }
      ],
      "source": [
        "accu_score = model.evaluate(train_dataset)\n",
        "print('Test accuracy:', accu_score[1])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "id": "uhIvIJVu0zD8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 321
        },
        "outputId": "0db9541b-59ba-4f76-fad2-c0adb0b12031"
      },
      "outputs": [
        {
          "output_type": "error",
          "ename": "NameError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-19-bde7df688cfe>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      7\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mdata_files\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0mv_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mloadImages\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'validation'\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<ipython-input-19-bde7df688cfe>\u001b[0m in \u001b[0;36mloadImages\u001b[0;34m(path, folder)\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mloadImages\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfolder\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      4\u001b[0m     data_files = sorted([os.path.join(path, folder, file)\n\u001b[0;32m----> 5\u001b[0;31m                         \u001b[0;32mfor\u001b[0m \u001b[0mfile\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mfolder\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[0m\u001b[1;32m      6\u001b[0m                         if (file.endswith('.jpg') or file.endswith('.jpeg'))])\n\u001b[1;32m      7\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mdata_files\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mNameError\u001b[0m: name 'os' is not defined"
          ]
        }
      ],
      "source": [
        "path_dir = 'C:/Users/VINCENT/Downloads/Covid19-dataset/Covid19-dataset/'\n",
        "\n",
        "def loadImages(path, folder):\n",
        "    data_files = sorted([os.path.join(path, folder, file)\n",
        "                        for file in os.listdir(path + folder + '/')\n",
        "                        if (file.endswith('.jpg') or file.endswith('.jpeg'))])\n",
        "    return data_files\n",
        "\n",
        "v_data = loadImages(path_dir, 'validation')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "uc8QKdjoDMkK"
      },
      "outputs": [],
      "source": [
        "g = v_data\n",
        "f = []\n",
        "images = []\n",
        "\n",
        "for x in g:\n",
        "    img = cv2.imread(x)\n",
        "    img = img[:, :, :3]\n",
        "    images.append(img)\n",
        "\n",
        "    width = 224\n",
        "    height = 224\n",
        "    dim = (width, height)\n",
        "\n",
        "    resized = cv2.resize(img, dim, interpolation=cv2.INTER_AREA)\n",
        "    f.append(resized)\n",
        "\n",
        "f = np.array(f)\n",
        "f = f/255"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GUfl58h1Dj46",
        "outputId": "74859c6d-f261-4650-a685-21771e7c7b5a"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "1/1 [==============================] - 1s 605ms/step\n",
            "[1 1 0 2 2 2 0 0 2 0]\n"
          ]
        }
      ],
      "source": [
        "preddd = model.predict(f)\n",
        "predict = np.argmax(preddd, axis=1)\n",
        "print(predict)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "htdoGM_DY0rV"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "colab": {
      "collapsed_sections": [],
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.12"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}