Untitled2.ipynb

pretrained.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled2.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyNMuWD28Gnh0mM7deAIGL1c",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/vardanagarwal/789e544af8b0eddc0e6e7e7badd3977b/untitled2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8bkfJIRv6Dbh",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "import os\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import re\n",
        "import random\n",
        "import cv2"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OpoFbzyX7ayf",
        "colab_type": "code",
        "outputId": "8cf0244a-43c6-4ad5-c4de-620f712bb22d",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'\n",
        "\n",
        "path_to_zip = tf.keras.utils.get_file('cats_and_dogs.zip', origin=_URL, extract=True)\n",
        "\n",
        "PATH = os.path.join(os.path.dirname(path_to_zip), 'cats_and_dogs_filtered')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip\n",
            "68608000/68606236 [==============================] - 1s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1BVngABS7fL3",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_dir = os.path.join(PATH, 'train')\n",
        "validation_dir = os.path.join(PATH, 'validation')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_3Pia2267b3p",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_cats_dir = os.path.join(train_dir, 'cats')  # directory with our training cat pictures\n",
        "train_dogs_dir = os.path.join(train_dir, 'dogs')  # directory with our training dog pictures\n",
        "validation_cats_dir = os.path.join(validation_dir, 'cats')  # directory with our validation cat pictures\n",
        "validation_dogs_dir = os.path.join(validation_dir, 'dogs')  # directory with our validation dog pictures"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gJjS_Rf97k3e",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "cats_tr = os.listdir(train_cats_dir)\n",
        "dogs_tr = os.listdir(train_dogs_dir)\n",
        "\n",
        "cats_val = os.listdir(validation_cats_dir)\n",
        "dogs_val = os.listdir(validation_dogs_dir)\n",
        "\n",
        "cats_tr = [os.path.join(train_cats_dir, x) for x in cats_tr]\n",
        "dogs_tr = [os.path.join(train_dogs_dir, x) for x in dogs_tr]\n",
        "cats_val = [os.path.join(validation_cats_dir, x) for x in cats_val]\n",
        "dogs_val = [os.path.join(validation_dogs_dir, x) for x in dogs_val]\n",
        "\n",
        "total_train = cats_tr + dogs_tr\n",
        "total_val = cats_val + dogs_val"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7T-OTVHmXMJD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def data_to_array(total):\n",
        "    random.shuffle(total)\n",
        "    X = np.zeros((len(total_train), 224, 224, 3)).astype('float')\n",
        "    y = []\n",
        "    for i, img_path in enumerate(total):\n",
        "        img = cv2.imread(img_path)\n",
        "        img = cv2.resize(img, (224, 224))\n",
        "        X[i] = img\n",
        "        if len(re.findall('dog', img_path)) == 3:\n",
        "            y.append(0)\n",
        "        else: \n",
        "            y.append(1)\n",
        "    y = np.array(y)\n",
        "    return X, y"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "z1fR3KUdacha",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_train, y_train = data_to_array(total_train)\n",
        "X_test, y_test = data_to_array(total_val)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "n6P7polv7nk_",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "batch_size = 32\n",
        "epochs = 20"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w0r8YDyw6JvH",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def create_model(base_model):\n",
        "    base_model.trainable = True\n",
        "    global_average_layer = tf.keras.layers.GlobalAveragePooling2D()(base_model.output)\n",
        "    prediction_layer = tf.keras.layers.Dense(1, activation='sigmoid')(global_average_layer)\n",
        "    model = tf.keras.models.Model(inputs=base_model.input, outputs=prediction_layer)\n",
        "    model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.0001), loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=[\"accuracy\"])\n",
        "    return model\n",
        "\n",
        "def fit_model(model):\n",
        "    history = model.fit(\n",
        "                        X_train, y_train,\n",
        "                        batch_size=batch_size,\n",
        "                        steps_per_epoch=len(total_train) // batch_size,\n",
        "                        epochs=epochs,\n",
        "                        validation_data=(X_test, y_test),\n",
        "                        validation_steps=len(total_val) // batch_size\n",
        "                        )\n",
        "    return history\n",
        "\n",
        "def plot_history(history):\n",
        "    acc = history.history['accuracy']\n",
        "    val_acc = history.history['val_accuracy']\n",
        "\n",
        "    loss=history.history['loss']\n",
        "    val_loss=history.history['val_loss']\n",
        "\n",
        "    epochs_range = range(epochs)\n",
        "\n",
        "    plt.figure(figsize=(12, 6))\n",
        "    plt.subplot(1, 2, 1)\n",
        "    plt.plot(epochs_range, acc, label='Training Accuracy')\n",
        "    plt.plot(epochs_range, val_acc, label='Validation Accuracy')\n",
        "    plt.legend(loc='lower right')\n",
        "    plt.title('Training and Validation Accuracy')\n",
        "\n",
        "    plt.subplot(1, 2, 2)\n",
        "    plt.plot(epochs_range, loss, label='Training Loss')\n",
        "    plt.plot(epochs_range, val_loss, label='Validation Loss')\n",
        "    plt.legend(loc='upper right')\n",
        "    plt.title('Training and Validation Loss')\n",
        "    plt.show()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_r8OrUqA775j",
        "colab_type": "code",
        "outputId": "0ba8270c-bd0b-4ca1-ca93-5afdfb14d04e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "IMG_SHAPE = (224, 224, 3)\n",
        "base_model1 = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE, include_top=False, weights=\"imagenet\")\n",
        "base_model2 = tf.keras.applications.InceptionV3(input_shape=IMG_SHAPE, include_top=False, weights=\"imagenet\")\n",
        "base_model3 = tf.keras.applications.Xception(input_shape=IMG_SHAPE, include_top=False, weights=\"imagenet\")\n",
        "\n",
        "model1 = create_model(base_model1)\n",
        "model2 = create_model(base_model2)\n",
        "model3 = create_model(base_model3)\n",
        "\n",
        "history1 = fit_model(model1)\n",
        "model1.save('models/model1.h5')\n",
        "\n",
        "history2 = fit_model(model2)\n",
        "model2.save('models/model2.h5')\n",
        "\n",
        "history3 = fit_model(model3)\n",
        "model3.save('models/model3.h5')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_224_no_top.h5\n",
            "9412608/9406464 [==============================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "87916544/87910968 [==============================] - 1s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/xception/xception_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "83689472/83683744 [==============================] - 1s 0us/step\n",
            "Epoch 1/20\n",
            "62/62 [==============================] - 23s 377ms/step - loss: 0.5541 - accuracy: 0.9244 - val_loss: 0.7184 - val_accuracy: 0.6411\n",
            "Epoch 2/20\n",
            "62/62 [==============================] - 23s 363ms/step - loss: 0.5097 - accuracy: 0.9893 - val_loss: 0.6511 - val_accuracy: 0.7490\n",
            "Epoch 3/20\n",
            "62/62 [==============================] - 22s 363ms/step - loss: 0.5055 - accuracy: 0.9970 - val_loss: 0.5901 - val_accuracy: 0.8558\n",
            "Epoch 4/20\n",
            "62/62 [==============================] - 23s 364ms/step - loss: 0.5071 - accuracy: 0.9944 - val_loss: 0.5390 - val_accuracy: 0.9355\n",
            "Epoch 5/20\n",
            "62/62 [==============================] - 23s 365ms/step - loss: 0.5025 - accuracy: 0.9970 - val_loss: 0.5362 - val_accuracy: 0.9405\n",
            "Epoch 6/20\n",
            "62/62 [==============================] - 22s 362ms/step - loss: 0.5085 - accuracy: 0.9980 - val_loss: 0.5412 - val_accuracy: 0.9385\n",
            "Epoch 7/20\n",
            "62/62 [==============================] - 23s 365ms/step - loss: 0.5043 - accuracy: 0.9985 - val_loss: 0.5341 - val_accuracy: 0.9486\n",
            "Epoch 8/20\n",
            "62/62 [==============================] - 23s 364ms/step - loss: 0.5029 - accuracy: 0.9990 - val_loss: 0.5355 - val_accuracy: 0.9466\n",
            "Epoch 9/20\n",
            "62/62 [==============================] - 22s 362ms/step - loss: 0.5036 - accuracy: 1.0000 - val_loss: 0.5313 - val_accuracy: 0.9536\n",
            "Epoch 10/20\n",
            "62/62 [==============================] - 22s 360ms/step - loss: 0.5062 - accuracy: 0.9980 - val_loss: 0.5241 - val_accuracy: 0.9637\n",
            "Epoch 11/20\n",
            "62/62 [==============================] - 22s 361ms/step - loss: 0.5003 - accuracy: 0.9990 - val_loss: 0.5277 - val_accuracy: 0.9597\n",
            "Epoch 12/20\n",
            "62/62 [==============================] - 22s 360ms/step - loss: 0.5076 - accuracy: 0.9985 - val_loss: 0.5367 - val_accuracy: 0.9456\n",
            "Epoch 13/20\n",
            "62/62 [==============================] - 22s 359ms/step - loss: 0.5040 - accuracy: 0.9954 - val_loss: 0.5231 - val_accuracy: 0.9667\n",
            "Epoch 14/20\n",
            "62/62 [==============================] - 22s 358ms/step - loss: 0.5020 - accuracy: 0.9995 - val_loss: 0.5201 - val_accuracy: 0.9738\n",
            "Epoch 15/20\n",
            "62/62 [==============================] - 22s 362ms/step - loss: 0.5029 - accuracy: 0.9995 - val_loss: 0.5252 - val_accuracy: 0.9657\n",
            "Epoch 16/20\n",
            "62/62 [==============================] - 23s 365ms/step - loss: 0.5051 - accuracy: 0.9985 - val_loss: 0.5156 - val_accuracy: 0.9798\n",
            "Epoch 17/20\n",
            "62/62 [==============================] - 22s 361ms/step - loss: 0.4987 - accuracy: 1.0000 - val_loss: 0.5159 - val_accuracy: 0.9758\n",
            "Epoch 18/20\n",
            "62/62 [==============================] - 23s 363ms/step - loss: 0.5074 - accuracy: 0.9990 - val_loss: 0.5151 - val_accuracy: 0.9808\n",
            "Epoch 19/20\n",
            "62/62 [==============================] - 22s 362ms/step - loss: 0.5046 - accuracy: 0.9975 - val_loss: 0.5135 - val_accuracy: 0.9819\n",
            "Epoch 20/20\n",
            "62/62 [==============================] - 22s 362ms/step - loss: 0.5077 - accuracy: 0.9995 - val_loss: 0.5156 - val_accuracy: 0.9788\n",
            "Epoch 1/20\n",
            "62/62 [==============================] - 41s 656ms/step - loss: 0.5427 - accuracy: 0.9355 - val_loss: 0.6219 - val_accuracy: 0.8034\n",
            "Epoch 2/20\n",
            "62/62 [==============================] - 39s 632ms/step - loss: 0.5129 - accuracy: 0.9807 - val_loss: 0.5212 - val_accuracy: 0.9677\n",
            "Epoch 3/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5096 - accuracy: 0.9863 - val_loss: 0.5278 - val_accuracy: 0.9607\n",
            "Epoch 4/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5093 - accuracy: 0.9858 - val_loss: 0.5155 - val_accuracy: 0.9788\n",
            "Epoch 5/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5086 - accuracy: 0.9934 - val_loss: 0.5151 - val_accuracy: 0.9738\n",
            "Epoch 6/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5032 - accuracy: 0.9970 - val_loss: 0.5133 - val_accuracy: 0.9808\n",
            "Epoch 7/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5059 - accuracy: 0.9959 - val_loss: 0.5142 - val_accuracy: 0.9788\n",
            "Epoch 8/20\n",
            "62/62 [==============================] - 39s 626ms/step - loss: 0.5044 - accuracy: 0.9944 - val_loss: 0.5223 - val_accuracy: 0.9688\n",
            "Epoch 9/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5055 - accuracy: 0.9970 - val_loss: 0.5141 - val_accuracy: 0.9829\n",
            "Epoch 10/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5053 - accuracy: 0.9959 - val_loss: 0.5148 - val_accuracy: 0.9778\n",
            "Epoch 11/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5084 - accuracy: 0.9949 - val_loss: 0.5197 - val_accuracy: 0.9597\n",
            "Epoch 12/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5006 - accuracy: 0.9959 - val_loss: 0.5174 - val_accuracy: 0.9657\n",
            "Epoch 13/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5103 - accuracy: 0.9954 - val_loss: 0.5133 - val_accuracy: 0.9798\n",
            "Epoch 14/20\n",
            "62/62 [==============================] - 39s 626ms/step - loss: 0.5042 - accuracy: 0.9975 - val_loss: 0.5111 - val_accuracy: 0.9849\n",
            "Epoch 15/20\n",
            "62/62 [==============================] - 39s 625ms/step - loss: 0.5006 - accuracy: 1.0000 - val_loss: 0.5105 - val_accuracy: 0.9829\n",
            "Epoch 16/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5079 - accuracy: 0.9939 - val_loss: 0.5165 - val_accuracy: 0.9738\n",
            "Epoch 17/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5040 - accuracy: 0.9959 - val_loss: 0.5114 - val_accuracy: 0.9819\n",
            "Epoch 18/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5036 - accuracy: 0.9980 - val_loss: 0.5122 - val_accuracy: 0.9819\n",
            "Epoch 19/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5059 - accuracy: 0.9980 - val_loss: 0.5173 - val_accuracy: 0.9768\n",
            "Epoch 20/20\n",
            "62/62 [==============================] - 39s 624ms/step - loss: 0.5101 - accuracy: 0.9959 - val_loss: 0.5155 - val_accuracy: 0.9778\n",
            "Epoch 1/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5556 - accuracy: 0.9446 - val_loss: 0.5147 - val_accuracy: 0.9819\n",
            "Epoch 2/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5092 - accuracy: 0.9919 - val_loss: 0.5122 - val_accuracy: 0.9788\n",
            "Epoch 3/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5048 - accuracy: 0.9970 - val_loss: 0.5107 - val_accuracy: 0.9879\n",
            "Epoch 4/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5025 - accuracy: 0.9990 - val_loss: 0.5106 - val_accuracy: 0.9879\n",
            "Epoch 5/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5072 - accuracy: 0.9995 - val_loss: 0.5138 - val_accuracy: 0.9788\n",
            "Epoch 6/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5050 - accuracy: 0.9970 - val_loss: 0.5136 - val_accuracy: 0.9798\n",
            "Epoch 7/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5051 - accuracy: 0.9995 - val_loss: 0.5121 - val_accuracy: 0.9839\n",
            "Epoch 8/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.4999 - accuracy: 1.0000 - val_loss: 0.5119 - val_accuracy: 0.9839\n",
            "Epoch 9/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5063 - accuracy: 1.0000 - val_loss: 0.5121 - val_accuracy: 0.9819\n",
            "Epoch 10/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5032 - accuracy: 1.0000 - val_loss: 0.5128 - val_accuracy: 0.9778\n",
            "Epoch 11/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5034 - accuracy: 0.9990 - val_loss: 0.5132 - val_accuracy: 0.9819\n",
            "Epoch 12/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5043 - accuracy: 0.9985 - val_loss: 0.5152 - val_accuracy: 0.9768\n",
            "Epoch 13/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.4992 - accuracy: 0.9995 - val_loss: 0.5141 - val_accuracy: 0.9778\n",
            "Epoch 14/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5082 - accuracy: 0.9954 - val_loss: 0.5190 - val_accuracy: 0.9647\n",
            "Epoch 15/20\n",
            "62/62 [==============================] - 83s 1s/step - loss: 0.5071 - accuracy: 0.9980 - val_loss: 0.5130 - val_accuracy: 0.9808\n",
            "Epoch 16/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5028 - accuracy: 1.0000 - val_loss: 0.5153 - val_accuracy: 0.9788\n",
            "Epoch 17/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5027 - accuracy: 1.0000 - val_loss: 0.5116 - val_accuracy: 0.9839\n",
            "Epoch 18/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5054 - accuracy: 0.9995 - val_loss: 0.5187 - val_accuracy: 0.9708\n",
            "Epoch 19/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5013 - accuracy: 0.9980 - val_loss: 0.5220 - val_accuracy: 0.9667\n",
            "Epoch 20/20\n",
            "62/62 [==============================] - 84s 1s/step - loss: 0.5043 - accuracy: 0.9990 - val_loss: 0.5158 - val_accuracy: 0.9788\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "oj6uCOS17-yz",
        "colab_type": "code",
        "outputId": "f5350d74-2313-4eeb-ba5b-1956bbbe7d57",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "plot_history(history1)\n",
        "plot_history(history2)\n",
        "plot_history(history3)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}