tvganesh/cats_vs_dogs_2.ipynb Secret

## cats_vs_dogs_2.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Cats_vs_Dogs_2.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true,
      "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/gist/tvganesh/11dad7ce29707d90e9cb8efd66d7657d/cats_vs_dogs_2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tEWzqW5xZjSH",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import csv\n",
        "import numpy as np\n",
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from google.colab import files\n"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jUJ0UvW9ZmNy",
        "colab_type": "text"
      },
      "source": [
        "# 1. Download the data from Kaggle \n",
        "Download the training and test data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "M4VWwKWaZq7r",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 445
        },
        "outputId": "c8901e4c-0bf1-44bb-8413-5baf52215ac2"
      },
      "source": [
        "!wget --no-check-certificate \\\n",
        "  https://www.dropbox.com/s/9zpwgb8kjndlw3y/train.zip?dl=0 \\\n",
        "  -O /usr/train.zip"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "--2020-04-04 09:40:02--  https://www.dropbox.com/s/9zpwgb8kjndlw3y/train.zip?dl=0\n",
            "Resolving www.dropbox.com (www.dropbox.com)... 162.125.81.1, 2620:100:6031:1::a27d:5101\n",
            "Connecting to www.dropbox.com (www.dropbox.com)|162.125.81.1|:443... connected.\n",
            "HTTP request sent, awaiting response... 301 Moved Permanently\n",
            "Location: /s/raw/9zpwgb8kjndlw3y/train.zip [following]\n",
            "--2020-04-04 09:40:02--  https://www.dropbox.com/s/raw/9zpwgb8kjndlw3y/train.zip\n",
            "Reusing existing connection to www.dropbox.com:443.\n",
            "HTTP request sent, awaiting response... 302 Found\n",
            "Location: https://ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com/cd/0/inline/A1Oq0j9ztKEW7beb5i9Wyh8GtYwtwuDHkM0FRNLVTw13jNnghlu0vM5wzvHXlnD7nsAPC0lrXxcOkSpS2ZMD8hMLhhaCxOly8eW-oSTLkRy2xU1rtzFuHNYbc1VOt_StLew/file# [following]\n",
            "--2020-04-04 09:40:02--  https://ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com/cd/0/inline/A1Oq0j9ztKEW7beb5i9Wyh8GtYwtwuDHkM0FRNLVTw13jNnghlu0vM5wzvHXlnD7nsAPC0lrXxcOkSpS2ZMD8hMLhhaCxOly8eW-oSTLkRy2xU1rtzFuHNYbc1VOt_StLew/file\n",
            "Resolving ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com (ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com)... 162.125.8.6, 2620:100:6031:6::a27d:5106\n",
            "Connecting to ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com (ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com)|162.125.8.6|:443... connected.\n",
            "HTTP request sent, awaiting response... 302 FOUND\n",
            "Location: /cd/0/inline2/A1PsgZGkpwwLU0yP3EYrx8-T52zERTgrx9OsuWIVhtxheh0gFZeDQWj4wnvGy6UpV4falx2f7tcMgoISE_YKxzOyX6KQPC_EoQt1GKkFSUj-0zgQc-Iol0B5hYIwjhzEV_iuj-YwaYBseYLEIPjFRLnMBPw3kQ7mQWuFTD1pRTbyUtIOefUx-X3Jj3oupqgCywTa97bG43FMh2TS1yzrcOuJGayUaN22osRiB9pbI0HeE_DZqXbBIs4a9sWhY-vXzMhXBCL63LqJpV0bPd7V1gDuUUiEIjoa6r4CVe_xIb6sPOiFdAcBZizNmMaAeThhj58846wUWj_cJPCfizgudTL7AKiTPKe2jq8LwdT5QdUCEw/file [following]\n",
            "--2020-04-04 09:40:03--  https://ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com/cd/0/inline2/A1PsgZGkpwwLU0yP3EYrx8-T52zERTgrx9OsuWIVhtxheh0gFZeDQWj4wnvGy6UpV4falx2f7tcMgoISE_YKxzOyX6KQPC_EoQt1GKkFSUj-0zgQc-Iol0B5hYIwjhzEV_iuj-YwaYBseYLEIPjFRLnMBPw3kQ7mQWuFTD1pRTbyUtIOefUx-X3Jj3oupqgCywTa97bG43FMh2TS1yzrcOuJGayUaN22osRiB9pbI0HeE_DZqXbBIs4a9sWhY-vXzMhXBCL63LqJpV0bPd7V1gDuUUiEIjoa6r4CVe_xIb6sPOiFdAcBZizNmMaAeThhj58846wUWj_cJPCfizgudTL7AKiTPKe2jq8LwdT5QdUCEw/file\n",
            "Reusing existing connection to ucda23696928ea3018fb23cb2a24.dl.dropboxusercontent.com:443.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 569546721 (543M) [application/zip]\n",
            "Saving to: ‘/usr/train.zip’\n",
            "\n",
            "/usr/train.zip      100%[===================>] 543.16M  15.6MB/s    in 37s     \n",
            "\n",
            "2020-04-04 09:40:41 (14.6 MB/s) - ‘/usr/train.zip’ saved [569546721/569546721]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ng58Bn6s-D7A",
        "colab_type": "code",
        "outputId": "acb9cc3b-5fb4-4411-ae6b-46ab0f012a74",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 445
        }
      },
      "source": [
        "!wget --no-check-certificate \\\n",
        "  https://www.dropbox.com/s/lj8gg12qemqzybl/test1.zip?dl=0 \\\n",
        "  -O /usr/test1.zip"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "--2020-04-04 09:40:45--  https://www.dropbox.com/s/lj8gg12qemqzybl/test1.zip?dl=0\n",
            "Resolving www.dropbox.com (www.dropbox.com)... 162.125.81.1, 2620:100:6031:1::a27d:5101\n",
            "Connecting to www.dropbox.com (www.dropbox.com)|162.125.81.1|:443... connected.\n",
            "HTTP request sent, awaiting response... 301 Moved Permanently\n",
            "Location: /s/raw/lj8gg12qemqzybl/test1.zip [following]\n",
            "--2020-04-04 09:40:46--  https://www.dropbox.com/s/raw/lj8gg12qemqzybl/test1.zip\n",
            "Reusing existing connection to www.dropbox.com:443.\n",
            "HTTP request sent, awaiting response... 302 Found\n",
            "Location: https://ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com/cd/0/inline/A1MYMaTZvvUxXeEom2_Q6gjq6Ku6Wvucvu0hkVbgkSCIRO3WC95xCLRHutJDJMxCIp9MyZP9sq-IQ_82coxLcjTp480LpHcKBUBPSFw5DV5vIyVolvaWd728nj17Zoi5kiI/file# [following]\n",
            "--2020-04-04 09:40:46--  https://ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com/cd/0/inline/A1MYMaTZvvUxXeEom2_Q6gjq6Ku6Wvucvu0hkVbgkSCIRO3WC95xCLRHutJDJMxCIp9MyZP9sq-IQ_82coxLcjTp480LpHcKBUBPSFw5DV5vIyVolvaWd728nj17Zoi5kiI/file\n",
            "Resolving ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com (ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com)... 162.125.81.6, 2620:100:601b:6::a27d:806\n",
            "Connecting to ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com (ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com)|162.125.81.6|:443... connected.\n",
            "HTTP request sent, awaiting response... 302 FOUND\n",
            "Location: /cd/0/inline2/A1OGZLfqLL1X5d2ObqAWhDUnXIBS2ONo0JWK87hZYKBcAD_5qsl__8eCZdUfQ-UZvWUeX8ftwX8gOGtQypMQ3aSkSPQf2ShY0d2ZaTAse16rUhlYQO9FECoL_cUc6-mRCt1dARP4BiuS-xjxmvIKHy-yzl_cIWPdD7FH4yKedqrZ0ZOeqlwAhZyBgl7x9Au-oce081Jli6X4SWaZzz_MWSHgj46rwNzvg0S9wSSP6wxSboXsinRteWkXreUW0EVdvoxucoO-8Vs0VwGgF9qSPYQjt9f0zlPo37JqhC2784MlI6UbXHftt_54pERBD_5A_8FhfHlo-wfTFR5LY4IAoNPhIJlvk8Oxz-BHbg0xlYEVSQ/file [following]\n",
            "--2020-04-04 09:40:47--  https://ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com/cd/0/inline2/A1OGZLfqLL1X5d2ObqAWhDUnXIBS2ONo0JWK87hZYKBcAD_5qsl__8eCZdUfQ-UZvWUeX8ftwX8gOGtQypMQ3aSkSPQf2ShY0d2ZaTAse16rUhlYQO9FECoL_cUc6-mRCt1dARP4BiuS-xjxmvIKHy-yzl_cIWPdD7FH4yKedqrZ0ZOeqlwAhZyBgl7x9Au-oce081Jli6X4SWaZzz_MWSHgj46rwNzvg0S9wSSP6wxSboXsinRteWkXreUW0EVdvoxucoO-8Vs0VwGgF9qSPYQjt9f0zlPo37JqhC2784MlI6UbXHftt_54pERBD_5A_8FhfHlo-wfTFR5LY4IAoNPhIJlvk8Oxz-BHbg0xlYEVSQ/file\n",
            "Reusing existing connection to ucfb9d89e4d3d2ec8835a77ffce8.dl.dropboxusercontent.com:443.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 284321224 (271M) [application/zip]\n",
            "Saving to: ‘/usr/test1.zip’\n",
            "\n",
            "/usr/test1.zip      100%[===================>] 271.15M  4.13MB/s    in 72s     \n",
            "\n",
            "2020-04-04 09:42:00 (3.76 MB/s) - ‘/usr/test1.zip’ saved [284321224/284321224]\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RejRobhbaAbR",
        "colab_type": "text"
      },
      "source": [
        "#2. Unzip files\n",
        "Extract the training and test files into their respective folders"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "g1QmWuBNcwaI",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import os\n",
        "import zipfile\n",
        "\n",
        "#local_zip = '/Users/tvganesh/Downloads/dogs-vs-cats.zip'\n",
        "#zip_ref = zipfile.ZipFile(local_zip, 'r')\n",
        "#zip_ref.extractall('/Users/tvganesh/Downloads')\n",
        "\n",
        "train_zip ='/usr/train.zip'\n",
        "train = zipfile.ZipFile(train_zip, 'r')\n",
        "train.extractall('/usr/dogs_vs_cats')\n",
        "train.close()\n",
        "test_zip = '/usr/test1.zip'\n",
        "test = zipfile.ZipFile(test_zip, 'r')\n",
        "\n",
        "test.extractall('/usr/dogs_vs_cats')\n",
        "test.close()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tJ2AopYr0-N-",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import os\n",
        "import shutil\n",
        "#os.listdir('/Users/tvganesh/Downloads/dogs_vs_cats/train')\n",
        "baseDir=\"/usr/dogs_vs_cats/training/\"        \n",
        "\n",
        "\n",
        "if not os.path.isdir(os.path.join(baseDir)):    \n",
        "     os.makedirs(os.path.join(baseDir))\n",
        "if not os.path.isdir(os.path.join(baseDir,\"dogs\")):    \n",
        "     os.makedirs(os.path.join(baseDir,\"dogs\"))\n",
        "if not os.path.isdir(os.path.join(baseDir,\"cats\")):  \n",
        "     os.makedirs(os.path.join(baseDir,\"cats\"))\n",
        "\n",
        "dogDir=\"/usr/dogs_vs_cats/training/dogs\"\n",
        "catDir=\"/usr/dogs_vs_cats/training/cats\"\n",
        "for f in os.listdir(\"/usr/dogs_vs_cats/train\"):\n",
        "    if(\"dog\" in f):\n",
        "        shutil.move(os.path.join('/usr/dogs_vs_cats/train',f), os.path.join(dogDir,f))\n",
        "    else:\n",
        "        shutil.move(os.path.join('/usr/dogs_vs_cats/train', f), os.path.join(catDir,f))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "75OkEPLQ9zkW",
        "colab_type": "code",
        "outputId": "0c41ef31-c915-4439-8e0e-d0251c01e805",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "print(len(os.listdir(\"/usr/dogs_vs_cats/training/dogs\")))\n",
        "print(len(os.listdir(\"/usr/dogs_vs_cats/training/cats\")))"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "12500\n",
            "12500\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "81poZzwUaOvh",
        "colab_type": "text"
      },
      "source": [
        "# Create validation test set\n",
        "Randomly sample 20% of the training data and use as validation test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6s1r8Dvw1ocH",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import random\n",
        "import os\n",
        "import shutil\n",
        "baseDir=\"/usr/dogs_vs_cats/training/\" \n",
        "validationDir=\"/usr/dogs_vs_cats/validation/\"  \n",
        "dogDir=\"/usr/dogs_vs_cats/validation/dogs\"\n",
        "catDir=\"/usr/dogs_vs_cats/validation/cats\"\n",
        "\n",
        "\n",
        "if not os.path.isdir(os.path.join(validationDir)):    \n",
        "     os.makedirs(validationDir)\n",
        "if not os.path.isdir(os.path.join(validationDir,\"dogs\")):    \n",
        "     os.makedirs(os.path.join(validationDir,\"dogs\"))\n",
        "if not os.path.isdir(os.path.join(validationDir,\"cats\")):  \n",
        "     os.makedirs(os.path.join(validationDir,\"cats\"))\n",
        "\n",
        "dir1=\"/usr/dogs_vs_cats/training/dogs\"\n",
        "a= os.listdir(dir1)\n",
        "l = random.sample(a, int(0.2 *len(a)))\n",
        "for f in l:\n",
        "    shutil.move(os.path.join(dir1,f), os.path.join(validationDir,os.path.join(dogDir,f)))\n",
        "    \n",
        "dir1=\"/usr/dogs_vs_cats/training/cats\"\n",
        "a= os.listdir(dir1)\n",
        "l = random.sample(a, int(0.2 *len(a)))\n",
        "for f in l:\n",
        "    shutil.move(os.path.join(dir1,f), os.path.join(catDir,f))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "61fFLZbK81So",
        "colab_type": "code",
        "outputId": "8c2fd0b0-ca5e-456c-a042-620ca37f3710",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "print(len(os.listdir(\"/usr/dogs_vs_cats/validation/dogs\")))\n",
        "print(len(os.listdir(\"/usr/dogs_vs_cats/validation/cats\")))"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "2500\n",
            "2500\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bkgUFGSNjLEZ",
        "colab_type": "text"
      },
      "source": [
        "# Set up training and validation folders\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rGaTECXk9Car",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "baseDir=\"/usr/dogs_vs_cats\"   \n",
        "\n",
        "train_dir = os.path.join(baseDir, 'training')\n",
        "validation_dir = os.path.join(baseDir, 'validation')\n",
        "\n",
        "# Directory with our training cat/dog pictures\n",
        "train_cats_dir = os.path.join(train_dir, 'cats')\n",
        "train_dogs_dir = os.path.join(train_dir, 'dogs')\n",
        "\n",
        "# Directory with our validation cat/dog pictures\n",
        "validation_cats_dir = os.path.join(validation_dir, 'cats')\n",
        "validation_dogs_dir = os.path.join(validation_dir, 'dogs')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "q_n5vbK9jWW_",
        "colab_type": "text"
      },
      "source": [
        "# Use Image Generator\n",
        "Read data from training and validation folders in batches of 32"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "t1PrZjGE9L6B",
        "colab_type": "code",
        "outputId": "30cfe6ae-61b2-4252-ba30-3528ca4d9c93",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "train_datagen = ImageDataGenerator( rescale = 1.0/255. )\n",
        "validation_datagen = ImageDataGenerator( rescale = 1.0/255. )\n",
        "\n",
        "train_generator = train_datagen.flow_from_directory(train_dir,\n",
        "                                                    batch_size=32,\n",
        "                                                    class_mode='binary',\n",
        "                                                    target_size=(150, 150))     \n",
        "# --------------------\n",
        "# Flow validation images in batches of 20 using test_datagen generator\n",
        "# --------------------\n",
        "validation_generator =  validation_datagen.flow_from_directory(validation_dir,\n",
        "                                                         batch_size=32,\n",
        "                                                         class_mode  = 'binary',\n",
        "                                                         target_size = (150, 150))"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 20000 images belonging to 2 classes.\n",
            "Found 5000 images belonging to 2 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SlVRtkIMlUV2",
        "colab_type": "text"
      },
      "source": [
        "# Use Image Augumentation\n",
        "Use Image Augumentation to improve performance\n",
        "\n",
        "- Use the same model parameters as before\n",
        "- Perform the following image augmentation\n",
        "  - width, height shift\n",
        "  - shear and zoom\n",
        "\n",
        "  Note: Adding rotation made the performance worse\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rrGxezjQEO0X",
        "colab_type": "code",
        "outputId": "1bb79fe7-df26-4047-c915-8670e87f82d4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        }
      },
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras.optimizers import RMSprop\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "model = tf.keras.models.Sequential([\n",
        "    tf.keras.layers.Conv2D(32,(3,3),activation='relu',input_shape=(150,150,3)),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    tf.keras.layers.Conv2D(64,(3,3),activation='relu'),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    tf.keras.layers.Conv2D(128,(3,3),activation='relu'),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    tf.keras.layers.Flatten(),\n",
        "    tf.keras.layers.Dense(128,activation='relu'),\n",
        "    tf.keras.layers.Dense(512,activation='relu'),\n",
        "    tf.keras.layers.Dense(1,activation='sigmoid')\n",
        "])\n",
        "\n",
        "\n",
        "train_datagen = ImageDataGenerator(\n",
        "      rescale=1./255,\n",
        "      #rotation_range=90,\n",
        "      width_shift_range=0.2,\n",
        "      height_shift_range=0.2,\n",
        "      shear_range=0.2,\n",
        "      zoom_range=0.2)\n",
        "      #horizontal_flip=True,\n",
        "      #fill_mode='nearest')\n",
        "\n",
        "validation_datagen = ImageDataGenerator(rescale=1./255)\n",
        "#\n",
        "train_generator = train_datagen.flow_from_directory(train_dir,\n",
        "                                                    batch_size=32,\n",
        "                                                    class_mode='binary',\n",
        "                                                    target_size=(150, 150))     \n",
        "# --------------------\n",
        "# Flow validation images in batches of 20 using test_datagen generator\n",
        "# --------------------\n",
        "validation_generator =  validation_datagen.flow_from_directory(validation_dir,\n",
        "                                                         batch_size=32,\n",
        "                                                         class_mode  = 'binary',\n",
        "                                                         target_size = (150, 150))\n",
        "\n",
        "# Use Adam Optmizer \n",
        "model.compile(optimizer='adam',\n",
        "             loss='binary_crossentropy',\n",
        "             metrics=['accuracy'])\n"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 20000 images belonging to 2 classes.\n",
            "Found 5000 images belonging to 2 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NOncHlfMl2pe",
        "colab_type": "text"
      },
      "source": [
        "# Perform Gradient Descent"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-05OA-c5EX0y",
        "colab_type": "code",
        "outputId": "5c8a1c3c-a7f3-4952-ec12-4b4092c93518",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 527
        }
      },
      "source": [
        "history=model.fit(train_generator,\n",
        "                 validation_data=validation_generator,\n",
        "                 steps_per_epoch=100,\n",
        "                 epochs=15,\n",
        "                 validation_steps=50,\n",
        "                 verbose=2)"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/15\n",
            "100/100 - 27s - loss: 0.5716 - accuracy: 0.6922 - val_loss: 0.4843 - val_accuracy: 0.7744\n",
            "Epoch 2/15\n",
            "100/100 - 27s - loss: 0.5575 - accuracy: 0.7084 - val_loss: 0.4683 - val_accuracy: 0.7750\n",
            "Epoch 3/15\n",
            "100/100 - 26s - loss: 0.5452 - accuracy: 0.7228 - val_loss: 0.4856 - val_accuracy: 0.7665\n",
            "Epoch 4/15\n",
            "100/100 - 27s - loss: 0.5294 - accuracy: 0.7347 - val_loss: 0.4654 - val_accuracy: 0.7812\n",
            "Epoch 5/15\n",
            "100/100 - 27s - loss: 0.5352 - accuracy: 0.7350 - val_loss: 0.4557 - val_accuracy: 0.7981\n",
            "Epoch 6/15\n",
            "100/100 - 26s - loss: 0.5136 - accuracy: 0.7453 - val_loss: 0.4964 - val_accuracy: 0.7621\n",
            "Epoch 7/15\n",
            "100/100 - 27s - loss: 0.5249 - accuracy: 0.7334 - val_loss: 0.4959 - val_accuracy: 0.7556\n",
            "Epoch 8/15\n",
            "100/100 - 26s - loss: 0.5035 - accuracy: 0.7497 - val_loss: 0.4555 - val_accuracy: 0.7969\n",
            "Epoch 9/15\n",
            "100/100 - 26s - loss: 0.5024 - accuracy: 0.7487 - val_loss: 0.4675 - val_accuracy: 0.7728\n",
            "Epoch 10/15\n",
            "100/100 - 27s - loss: 0.5015 - accuracy: 0.7500 - val_loss: 0.4276 - val_accuracy: 0.8075\n",
            "Epoch 11/15\n",
            "100/100 - 26s - loss: 0.5002 - accuracy: 0.7581 - val_loss: 0.4193 - val_accuracy: 0.8131\n",
            "Epoch 12/15\n",
            "100/100 - 27s - loss: 0.4733 - accuracy: 0.7706 - val_loss: 0.5209 - val_accuracy: 0.7398\n",
            "Epoch 13/15\n",
            "100/100 - 27s - loss: 0.4999 - accuracy: 0.7538 - val_loss: 0.4109 - val_accuracy: 0.8075\n",
            "Epoch 14/15\n",
            "100/100 - 27s - loss: 0.4550 - accuracy: 0.7859 - val_loss: 0.3770 - val_accuracy: 0.8288\n",
            "Epoch 15/15\n",
            "100/100 - 26s - loss: 0.4688 - accuracy: 0.7688 - val_loss: 0.4764 - val_accuracy: 0.7786\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Mqn9UFPvtULV",
        "colab_type": "text"
      },
      "source": [
        "# Plot results\n",
        "- Plot training and validation accuracy\n",
        "- Plot training and validation loss"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4jzpMxihtYhK",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 562
        },
        "outputId": "c0c8fdd1-dc4b-43da-e495-b898200b3c2f"
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "#-----------------------------------------------------------\n",
        "# Retrieve a list of list results on training and test data\n",
        "# sets for each training epoch\n",
        "#-----------------------------------------------------------\n",
        "acc      = history.history[     'accuracy' ]\n",
        "val_acc  = history.history[ 'val_accuracy' ]\n",
        "loss     = history.history[    'loss' ]\n",
        "val_loss = history.history['val_loss' ]\n",
        "\n",
        "epochs   = range(len(acc)) # Get number of epochs\n",
        "\n",
        "#------------------------------------------------\n",
        "# Plot training and validation accuracy per epoch\n",
        "#------------------------------------------------\n",
        "plt.plot  ( epochs,     acc,label=\"training accuracy\" )\n",
        "plt.plot  ( epochs, val_acc, label='validation acuracy' )\n",
        "plt.title ('Training and validation accuracy')\n",
        "plt.legend()\n",
        "\n",
        "plt.figure()\n",
        "\n",
        "#------------------------------------------------\n",
        "# Plot training and validation loss per epoch\n",
        "#------------------------------------------------\n",
        "plt.plot  ( epochs,     loss , label=\"training loss\")\n",
        "plt.plot  ( epochs, val_loss,label=\"validation loss\" )\n",
        "plt.title ('Training and validation loss'   )\n",
        "plt.legend()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7f5e84dd54e0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEICAYAAABRSj9aAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nyWYAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEICAYAAABWJCMKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}