{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!mkdir ~/.kaggle"
      ],
      "metadata": {
        "id": "Jb5omVVTKouR"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!mv kaggle.json ~/.kaggle"
      ],
      "metadata": {
        "id": "3fllnrt3KvCu"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JKhveax8IDqI",
        "outputId": "dee65b41-4879-4a74-d142-5ab844efeed8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /root/.kaggle/kaggle.json'\n",
            "Downloading dogs-vs-cats.zip to /content\n",
            " 99% 808M/812M [00:20<00:00, 44.5MB/s]\n",
            "100% 812M/812M [00:20<00:00, 41.9MB/s]\n"
          ]
        }
      ],
      "source": [
        "! kaggle competitions download -c dogs-vs-cats"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip dogs-vs-cats.zip"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dcicRQJ-LEfz",
        "outputId": "31367796-e6d9-499c-a96d-18ef7e79cbf3"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Archive:  dogs-vs-cats.zip\n",
            "  inflating: sampleSubmission.csv    \n",
            "  inflating: test1.zip               \n",
            "  inflating: train.zip               \n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!unzip -qq train.zip"
      ],
      "metadata": {
        "id": "WMc8VAeULQuQ"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!ls train | wc -l"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QcE_yjY7LfUY",
        "outputId": "30770810-00da-4323-c257-990e73d660d2"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "25000\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "len(os.listdir('train'))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xgP5aHN5LpS0",
        "outputId": "f31cec94-b622-421f-f075-89cfa71b63c6"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "25000"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!rm -r dogs-vs-cats.zip sampleSubmission.csv test1.zip train.zip sample_data/"
      ],
      "metadata": {
        "id": "P3zAckKQLwD0"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os, shutil"
      ],
      "metadata": {
        "id": "mhJqzCgIMJwG"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# The path to the directory where the original\n",
        "# dataset was uncompressed\n",
        "original_dataset_dir = '/content/train'\n",
        "\n",
        "# The directory where we will\n",
        "# store our smaller dataset\n",
        "base_dir = '/content/subset'\n",
        "os.makedirs(base_dir, exist_ok=True)"
      ],
      "metadata": {
        "id": "qMyIKYT5MMQ8"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Directories for our training,\n",
        "# validation and test splits\n",
        "train_dir = os.path.join(base_dir, 'train')\n",
        "os.mkdir(train_dir)\n",
        "validation_dir = os.path.join(base_dir, 'validation')\n",
        "os.mkdir(validation_dir)\n",
        "test_dir = os.path.join(base_dir, 'test')\n",
        "os.mkdir(test_dir)\n",
        "# Directory with our training cat pictures\n",
        "train_cats_dir = os.path.join(train_dir, 'cats')\n",
        "os.mkdir(train_cats_dir)\n",
        "\n",
        "# Directory with our training dog pictures\n",
        "train_dogs_dir = os.path.join(train_dir, 'dogs')\n",
        "os.mkdir(train_dogs_dir)\n",
        "\n",
        "# Directory with our validation cat pictures\n",
        "validation_cats_dir = os.path.join(validation_dir, 'cats')\n",
        "os.mkdir(validation_cats_dir)\n",
        "\n",
        "# Directory with our validation dog pictures\n",
        "validation_dogs_dir = os.path.join(validation_dir, 'dogs')\n",
        "os.mkdir(validation_dogs_dir)\n",
        "\n",
        "# Directory with our validation cat pictures\n",
        "test_cats_dir = os.path.join(test_dir, 'cats')\n",
        "os.mkdir(test_cats_dir)\n",
        "\n",
        "# Directory with our validation dog pictures\n",
        "test_dogs_dir = os.path.join(test_dir, 'dogs')\n",
        "os.mkdir(test_dogs_dir)\n",
        "\n",
        "# Copy first 1000 cat images to train_cats_dir\n",
        "fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(train_cats_dir, fname)\n",
        "    shutil.copyfile(src, dst)\n",
        "\n",
        "# Copy next 500 cat images to validation_cats_dir\n",
        "fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(validation_cats_dir, fname)\n",
        "    shutil.copyfile(src, dst)\n",
        "\n",
        "# Copy next 500 cat images to test_cats_dir\n",
        "fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(test_cats_dir, fname)\n",
        "    shutil.copyfile(src, dst)\n",
        "\n",
        "# Copy first 1000 dog images to train_dogs_dir\n",
        "fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(train_dogs_dir, fname)\n",
        "    shutil.copyfile(src, dst)\n",
        "\n",
        "# Copy next 500 dog images to validation_dogs_dir\n",
        "fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(validation_dogs_dir, fname)\n",
        "    shutil.copyfile(src, dst)\n",
        "\n",
        "# Copy next 500 dog images to test_dogs_dir\n",
        "fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]\n",
        "for fname in fnames:\n",
        "    src = os.path.join(original_dataset_dir, fname)\n",
        "    dst = os.path.join(test_dogs_dir, fname)\n",
        "    shutil.copyfile(src, dst)"
      ],
      "metadata": {
        "id": "smLPDY_zIEUm"
      },
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print('total training cat images:', len(os.listdir(train_cats_dir)))\n",
        "print('total training dog images:', len(os.listdir(train_dogs_dir)))\n",
        "print('total validation cat images:', len(os.listdir(validation_cats_dir)))\n",
        "print('total validation dog images:', len(os.listdir(validation_dogs_dir)))\n",
        "print('total test cat images:', len(os.listdir(test_cats_dir)))\n",
        "print('total test dog images:', len(os.listdir(test_dogs_dir)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l3W70oBeILXs",
        "outputId": "6f8c860c-13f2-4946-81fb-47330d2dc531"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "total training cat images: 1000\n",
            "total training dog images: 1000\n",
            "total validation cat images: 500\n",
            "total validation dog images: 500\n",
            "total test cat images: 500\n",
            "total test dog images: 500\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!rm -r train"
      ],
      "metadata": {
        "id": "Y37B2OEBMgbV"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras import layers\n",
        "from keras import models\n",
        "\n",
        "model = models.Sequential()\n",
        "model.add(layers.Conv2D(32, (3, 3), activation='relu',\n",
        "                        input_shape=(150, 150, 3)))\n",
        "model.add(layers.MaxPooling2D((2, 2)))\n",
        "model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n",
        "model.add(layers.MaxPooling2D((2, 2)))\n",
        "model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n",
        "model.add(layers.MaxPooling2D((2, 2)))\n",
        "model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n",
        "model.add(layers.MaxPooling2D((2, 2)))\n",
        "model.add(layers.Flatten())\n",
        "model.add(layers.Dense(512, activation='relu'))\n",
        "model.add(layers.Dense(1, activation='sigmoid'))"
      ],
      "metadata": {
        "id": "V5-eUhQNMjY2"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras import optimizers\n",
        "\n",
        "model.compile(loss='binary_crossentropy',\n",
        "              optimizer='rmsprop',\n",
        "              metrics=['acc'])"
      ],
      "metadata": {
        "id": "VwzMCmy_Mvcv"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# All images will be rescaled by 1./255\n",
        "train_datagen = ImageDataGenerator(rescale=1./255)\n",
        "test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "train_generator = train_datagen.flow_from_directory(\n",
        "        # This is the target directory\n",
        "        train_dir,\n",
        "        # All images will be resized to 150x150\n",
        "        target_size=(150, 150),\n",
        "        batch_size=20,\n",
        "        # Since we use binary_crossentropy loss, we need binary labels\n",
        "        class_mode='binary')\n",
        "\n",
        "validation_generator = test_datagen.flow_from_directory(\n",
        "        validation_dir,\n",
        "        target_size=(150, 150),\n",
        "        batch_size=20,\n",
        "        class_mode='binary')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a3Dl0PZiMv-v",
        "outputId": "a51cc68d-86f4-435f-de86-83a41914dae1"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 2000 images belonging to 2 classes.\n",
            "Found 1000 images belonging to 2 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(\n",
        "      train_generator,\n",
        "      epochs=30,\n",
        "      validation_data=validation_generator)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "q1lyRwjAMxv8",
        "outputId": "0d798bb4-071a-4ffe-a388-296bd7f223c5"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/30\n",
            "100/100 [==============================] - 23s 110ms/step - loss: 0.7299 - acc: 0.5080 - val_loss: 0.6926 - val_acc: 0.5000\n",
            "Epoch 2/30\n",
            "100/100 [==============================] - 11s 105ms/step - loss: 0.6938 - acc: 0.5170 - val_loss: 0.7003 - val_acc: 0.5000\n",
            "Epoch 3/30\n",
            "100/100 [==============================] - 12s 118ms/step - loss: 0.6823 - acc: 0.5585 - val_loss: 0.6757 - val_acc: 0.5510\n",
            "Epoch 4/30\n",
            "100/100 [==============================] - 10s 103ms/step - loss: 0.6558 - acc: 0.6235 - val_loss: 0.6358 - val_acc: 0.6350\n",
            "Epoch 5/30\n",
            "100/100 [==============================] - 11s 106ms/step - loss: 0.6038 - acc: 0.6820 - val_loss: 0.6054 - val_acc: 0.6630\n",
            "Epoch 6/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.5573 - acc: 0.7050 - val_loss: 0.5927 - val_acc: 0.6830\n",
            "Epoch 7/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.5088 - acc: 0.7405 - val_loss: 0.6323 - val_acc: 0.6240\n",
            "Epoch 8/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.4596 - acc: 0.7880 - val_loss: 0.5591 - val_acc: 0.7100\n",
            "Epoch 9/30\n",
            "100/100 [==============================] - 10s 97ms/step - loss: 0.4107 - acc: 0.8070 - val_loss: 0.6288 - val_acc: 0.7130\n",
            "Epoch 10/30\n",
            "100/100 [==============================] - 10s 101ms/step - loss: 0.3348 - acc: 0.8575 - val_loss: 0.6814 - val_acc: 0.7130\n",
            "Epoch 11/30\n",
            "100/100 [==============================] - 11s 106ms/step - loss: 0.2490 - acc: 0.8935 - val_loss: 0.9510 - val_acc: 0.7060\n",
            "Epoch 12/30\n",
            "100/100 [==============================] - 11s 105ms/step - loss: 0.1812 - acc: 0.9235 - val_loss: 0.8586 - val_acc: 0.7360\n",
            "Epoch 13/30\n",
            "100/100 [==============================] - 11s 106ms/step - loss: 0.1575 - acc: 0.9470 - val_loss: 1.0982 - val_acc: 0.7360\n",
            "Epoch 14/30\n",
            "100/100 [==============================] - 10s 105ms/step - loss: 0.0951 - acc: 0.9720 - val_loss: 1.2492 - val_acc: 0.7060\n",
            "Epoch 15/30\n",
            "100/100 [==============================] - 12s 119ms/step - loss: 0.0825 - acc: 0.9750 - val_loss: 1.4846 - val_acc: 0.7230\n",
            "Epoch 16/30\n",
            "100/100 [==============================] - 10s 105ms/step - loss: 0.0463 - acc: 0.9835 - val_loss: 1.8739 - val_acc: 0.7130\n",
            "Epoch 17/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.0973 - acc: 0.9800 - val_loss: 1.8018 - val_acc: 0.7310\n",
            "Epoch 18/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.0480 - acc: 0.9845 - val_loss: 1.6225 - val_acc: 0.7250\n",
            "Epoch 19/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.0297 - acc: 0.9895 - val_loss: 2.1245 - val_acc: 0.7350\n",
            "Epoch 20/30\n",
            "100/100 [==============================] - 10s 98ms/step - loss: 0.0304 - acc: 0.9915 - val_loss: 2.0890 - val_acc: 0.7230\n",
            "Epoch 21/30\n",
            "100/100 [==============================] - 10s 102ms/step - loss: 0.0658 - acc: 0.9855 - val_loss: 2.4989 - val_acc: 0.7110\n",
            "Epoch 22/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.0291 - acc: 0.9900 - val_loss: 2.0622 - val_acc: 0.7240\n",
            "Epoch 23/30\n",
            "100/100 [==============================] - 11s 108ms/step - loss: 0.0100 - acc: 0.9975 - val_loss: 3.7533 - val_acc: 0.6810\n",
            "Epoch 24/30\n",
            "100/100 [==============================] - 11s 108ms/step - loss: 0.0371 - acc: 0.9925 - val_loss: 3.0020 - val_acc: 0.6980\n",
            "Epoch 25/30\n",
            "100/100 [==============================] - 11s 107ms/step - loss: 0.0120 - acc: 0.9960 - val_loss: 3.6558 - val_acc: 0.7010\n",
            "Epoch 26/30\n",
            "100/100 [==============================] - 12s 120ms/step - loss: 0.0575 - acc: 0.9870 - val_loss: 3.1962 - val_acc: 0.7090\n",
            "Epoch 27/30\n",
            "100/100 [==============================] - 12s 120ms/step - loss: 0.0427 - acc: 0.9915 - val_loss: 3.7945 - val_acc: 0.7240\n",
            "Epoch 28/30\n",
            "100/100 [==============================] - 12s 119ms/step - loss: 0.0188 - acc: 0.9975 - val_loss: 3.1029 - val_acc: 0.7180\n",
            "Epoch 29/30\n",
            "100/100 [==============================] - 12s 119ms/step - loss: 0.0284 - acc: 0.9925 - val_loss: 3.6895 - val_acc: 0.7040\n",
            "Epoch 30/30\n",
            "100/100 [==============================] - 10s 102ms/step - loss: 0.0594 - acc: 0.9895 - val_loss: 3.0475 - val_acc: 0.7230\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline\n",
        "acc = history.history['acc']\n",
        "val_acc = history.history['val_acc']\n",
        "loss = history.history['loss']\n",
        "val_loss = history.history['val_loss']\n",
        "\n",
        "epochs = range(len(acc))\n",
        "\n",
        "plt.plot(epochs, acc, 'bo', label='Training acc')\n",
        "plt.plot(epochs, val_acc, 'b', label='Validation acc')\n",
        "plt.title('Training and validation accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.figure()\n",
        "\n",
        "plt.plot(epochs, loss, 'bo', label='Training loss')\n",
        "plt.plot(epochs, val_loss, 'b', label='Validation loss')\n",
        "plt.title('Training and validation loss')\n",
        "plt.legend()\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 887
        },
        "id": "jwckF_V7M0lP",
        "outputId": "d5be107e-456f-4732-f260-7dd87afee065"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}