03_introduction_to_computer_vision_with_tensorflow.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "toc_visible": true,
      "gpuType": "V28"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "TPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Introduction to Convolutional Neural Networks and Computer Vision with TensorFlow\n",
        "\n",
        "Computer vision is the practice of writing algorithms which can discover patterns in visual data. Such as the camera of a self-driving car recognizing the car in front."
      ],
      "metadata": {
        "id": "XqovNqIVXdBs"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Get the data\n",
        "\n",
        "The images we're working with are from the Food101 dataset (101 different classes of food): https://www.kaggle.com/dansbecker/food-101\n",
        "\n",
        "However we've modified it to only use two classes (pizza 🍕 & steak 🥩) using the image data modification notebook: https://github.com/mrdbourke/tensorflow-deep-learning/blob/main/extras/image_data_modification.ipynb\n",
        "\n",
        "🔑**Note:** We start with a smaller dataset so we can experiment quickly and figure what works (or better yet what doesn't work) before scaling up."
      ],
      "metadata": {
        "id": "GCiaCwsMYfHb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import zipfile\n",
        "\n",
        "!wget https://storage.googleapis.com/ztm_tf_course/food_vision/pizza_steak.zip  # This command searches the zip file from the address and downloads it into Colab\n",
        "\n",
        "# Unzip the downloaded file\n",
        "zip_ref = zipfile.ZipFile(\"pizza_steak.zip\")\n",
        "zip_ref.extractall()\n",
        "zip_ref.close()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "312bSvCsYiI1",
        "outputId": "acc038e5-d0f2-48b9-8325-3bd36feb9266"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-03 13:30:59--  https://storage.googleapis.com/ztm_tf_course/food_vision/pizza_steak.zip\n",
            "Resolving storage.googleapis.com (storage.googleapis.com)... 142.250.141.207, 142.251.2.207, 74.125.137.207, ...\n",
            "Connecting to storage.googleapis.com (storage.googleapis.com)|142.250.141.207|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 109540975 (104M) [application/zip]\n",
            "Saving to: ‘pizza_steak.zip’\n",
            "\n",
            "pizza_steak.zip     100%[===================>] 104.47M   144MB/s    in 0.7s    \n",
            "\n",
            "2024-08-03 13:31:00 (144 MB/s) - ‘pizza_steak.zip’ saved [109540975/109540975]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Inspect the data (become one with it)\n",
        "A very crucial step at the beginning of any machine learning project is becoming one with the data.\n",
        "\n",
        "And for a computer vision project... this usually means visualizing many samples of your data."
      ],
      "metadata": {
        "id": "8HyKadt9aYtq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!ls pizza_steak"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "guwpVG2Ycdm6",
        "outputId": "7bc38724-9492-4789-f50f-1775f3538206"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "test  train\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls pizza_steak/train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bi6yRjLjcj4B",
        "outputId": "e295aad9-abe7-4a9d-db25-784b5b644123"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "pizza  steak\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!ls pizza_steak/train/pizza"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vpcIb7JmcpvH",
        "outputId": "3f55fb6e-1bc6-4651-8f7d-dd556e2b37a8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1008104.jpg  1572608.jpg  2097315.jpg  2572958.jpg  3084957.jpg  3693710.jpg  668944.jpg\n",
            "1008144.jpg  1573562.jpg  2098014.jpg  2574896.jpg  3102271.jpg  3699992.jpg  670201.jpg\n",
            "1008844.jpg  1576248.jpg  2104569.jpg  2576168.jpg  3105724.jpg  3702863.jpg  674188.jpg\n",
            "1008941.jpg  1577871.jpg  2110257.jpg  2577373.jpg  3109486.jpg  3703769.jpg  676432.jpg\n",
            "1011404.jpg  1584379.jpg  2112757.jpg  2577377.jpg  312479.jpg\t 3704879.jpg  682201.jpg\n",
            "102037.jpg   1593665.jpg  2121603.jpg  2581276.jpg  3128495.jpg  3705479.jpg  68684.jpg\n",
            "1026922.jpg  1593835.jpg  2126352.jpg  2584745.jpg  3148119.jpg  370643.jpg   698251.jpg\n",
            "1029698.jpg  1600705.jpg  2126709.jpg  2587918.jpg  3164761.jpg  3712344.jpg  702165.jpg\n",
            "1033251.jpg  1608000.jpg  2135635.jpg  2587921.jpg  3168266.jpg  3713343.jpg  704161.jpg\n",
            "1035854.jpg  1617418.jpg  2137341.jpg  259449.jpg   3170114.jpg  372275.jpg   709273.jpg\n",
            "1038357.jpg  1620560.jpg  2142812.jpg  2602611.jpg  3173779.jpg  3742272.jpg  709947.jpg\n",
            "1040878.jpg  1620761.jpg  214728.jpg   2605343.jpg  317861.jpg\t 3745884.jpg  712149.jpg\n",
            "1044524.jpg  1625147.jpg  2148129.jpg  2606727.jpg  3185774.jpg  3749515.jpg  714991.jpg\n",
            "1044789.jpg  163039.jpg   2154394.jpg  262133.jpg   3191035.jpg  375401.jpg   715169.jpg\n",
            "1047561.jpg  1633289.jpg  2155475.jpg  2621534.jpg  3193599.jpg  3763593.jpg  717350.jpg\n",
            "1048649.jpg  1635386.jpg  2155735.jpg  2622336.jpg  3196721.jpg  376417.jpg   721383.jpg\n",
            "1054420.jpg  1636299.jpg  2161241.jpg  2639094.jpg  32004.jpg\t 3766053.jpg  724445.jpg\n",
            "1055065.jpg  1638227.jpg  2164255.jpg  2640502.jpg  320570.jpg\t 3766476.jpg  72716.jpg\n",
            "105910.jpg   1646974.jpg  216720.jpg   2664219.jpg  3207504.jpg  3767723.jpg  739735.jpg\n",
            "1065078.jpg  1649108.jpg  2172850.jpg  2666066.jpg  3214153.jpg  3767773.jpg  740385.jpg\n",
            "1069629.jpg  1649276.jpg  218142.jpg   2667244.jpg  3256974.jpg  3772054.jpg  741491.jpg\n",
            "1075568.jpg  1652943.jpg  218711.jpg   2667255.jpg  3264148.jpg  3778801.jpg  741883.jpg\n",
            "1076699.jpg  1654444.jpg  2187466.jpg  2667824.jpg  32666.jpg\t 3790235.jpg  755968.jpg\n",
            "1083380.jpg  1660415.jpg  2188452.jpg  2670730.jpg  326809.jpg\t 3793314.jpg  759025.jpg\n",
            "1084888.jpg  1663749.jpg  2190018.jpg  2671508.jpg  3269634.jpg  3798959.jpg  759873.jpg\n",
            "1088332.jpg  1665654.jpg  220190.jpg   2674351.jpg  327415.jpg\t 3803596.jpg  762788.jpg\n",
            "1089334.jpg  166823.jpg   220910.jpg   2687575.jpg  3281494.jpg  3821701.jpg  764429.jpg\n",
            "1097980.jpg  1670471.jpg  221048.jpg   2693334.jpg  329302.jpg\t 3822139.jpg  765000.jpg\n",
            "1098197.jpg  1671531.jpg  2215531.jpg  269396.jpg   3297714.jpg  3826377.jpg  765799.jpg\n",
            "1105700.jpg  1678284.jpg  2217956.jpg  2694223.jpg  3312584.jpg  382829.jpg   768276.jpg\n",
            "1107714.jpg  1681043.jpg  2224099.jpg  2697971.jpg  3314176.jpg  3830773.jpg  771878.jpg\n",
            "111051.jpg   1686908.jpg  2224828.jpg  2700543.jpg  3314535.jpg  38349.jpg    774142.jpg\n",
            "1110966.jpg  1687681.jpg  2228322.jpg  2702825.jpg  332231.jpg\t 384215.jpg   77677.jpg\n",
            "1123386.jpg  168879.jpg   2231356.jpg  2705497.jpg  3324050.jpg  3845083.jpg  786995.jpg\n",
            "1137400.jpg  1688838.jpg  2235981.jpg  2707814.jpg  3326344.jpg  3860002.jpg  790432.jpg\n",
            "1138936.jpg  169318.jpg   2236914.jpg  2711828.jpg  3333459.jpg  3862243.jpg  790841.jpg\n",
            "1143057.jpg  169720.jpg   2241448.jpg  271592.jpg   3337370.jpg  3864383.jpg  792093.jpg\n",
            "1157438.jpg  1705747.jpg  2247711.jpg  271675.jpg   3338774.jpg  3871666.jpg  799874.jpg\n",
            "1159797.jpg  1705773.jpg  2253670.jpg  271779.jpg   333985.jpg\t 3873326.jpg  803243.jpg\n",
            "1165451.jpg  1708197.jpg  2255361.jpg  2722646.jpg  3342039.jpg  387697.jpg   807128.jpg\n",
            "1173913.jpg  1717790.jpg  2274117.jpg  2723529.jpg  3366256.jpg  3882444.jpg  809024.jpg\n",
            "1183278.jpg  1742542.jpg  2279642.jpg  2739039.jpg  3367113.jpg  3906901.jpg  812349.jpg\n",
            "1202925.jpg  1743389.jpg  2280345.jpg  2739100.jpg  337272.jpg\t 3910117.jpg  816577.jpg\n",
            "1205154.jpg  175626.jpg   2285269.jpg  2742044.jpg  3376519.jpg  3913912.jpg  816729.jpg\n",
            "1207213.jpg  1757288.jpg  2285942.jpg  274945.jpg   3379038.jpg  3917951.jpg  819547.jpg\n",
            "1209973.jpg  1761451.jpg  228778.jpg   2754150.jpg  3382880.jpg  393658.jpg   823104.jpg\n",
            "121834.jpg   1763205.jpg  2291093.jpg  2755875.jpg  3383977.jpg  394049.jpg   82578.jpg\n",
            "12301.jpg    1774438.jpg  2292986.jpg  2757327.jpg  3384856.jpg  394590.jpg   82772.jpg\n",
            "1234172.jpg  1778167.jpg  2293453.jpg  2760984.jpg  338838.jpg\t 395034.jpg   829229.jpg\n",
            "1243215.jpg  1786840.jpg  2301105.jpg  276803.jpg   3391208.jpg  395960.jpg   83538.jpg\n",
            "1245628.jpg  179165.jpg   2304021.jpg  2769168.jpg  3392649.jpg  398565.jpg   835833.jpg\n",
            "1247645.jpg  1795316.jpg  2312987.jpg  2774899.jpg  3392671.jpg  401701.jpg   839461.jpg\n",
            "1248346.jpg  1806491.jpg  23199.jpg    2775763.jpg  3393898.jpg  401979.jpg   853441.jpg\n",
            "1248478.jpg  1810844.jpg  2321465.jpg  2778214.jpg  3397336.jpg  40231.jpg    857888.jpg\n",
            "1260554.jpg  1818014.jpg  232976.jpg   277963.jpg   3398309.jpg  403431.jpg   861771.jpg\n",
            "1267359.jpg  1828050.jpg  2330965.jpg  2785084.jpg  3399610.jpg  413710.jpg   866834.jpg\n",
            "1269960.jpg  1836888.jpg  233143.jpg   2793535.jpg  3401720.jpg  413789.jpg   868789.jpg\n",
            "1270986.jpg  1839077.jpg  2331467.jpg  27963.jpg    3401767.jpg  419516.jpg   869763.jpg\n",
            "12718.jpg    1870865.jpg  2361973.jpg  2800325.jpg  340814.jpg\t 422261.jpg   872094.jpg\n",
            "1284978.jpg  1871498.jpg  2365046.jpg  2811032.jpg  3425999.jpg  424288.jpg   874288.jpg\n",
            "1285298.jpg  1877103.jpg  2382016.jpg  282013.jpg   3426946.jpg  430118.jpg   875262.jpg\n",
            "1287004.jpg  1878005.jpg  238843.jpg   2821034.jpg  3427699.jpg  44449.jpg    875856.jpg\n",
            "1289139.jpg  1881674.jpg  2397868.jpg  2821048.jpg  3434372.jpg  448519.jpg   877881.jpg\n",
            "129536.jpg   1888911.jpg  2410138.jpg  2827938.jpg  3441394.jpg  452989.jpg   878377.jpg\n",
            "1312761.jpg  1890444.jpg  2412237.jpg  2831983.jpg  3443136.jpg  464388.jpg   884986.jpg\n",
            "131561.jpg   1895479.jpg  2412970.jpg  2844278.jpg  3456440.jpg  465454.jpg   886505.jpg\n",
            "132484.jpg   1897129.jpg  2421445.jpg  2849924.jpg  3462250.jpg  467986.jpg   8917.jpg\n",
            "132554.jpg   1898723.jpg  2426686.jpg  2852301.jpg  34632.jpg\t 474493.jpg   893644.jpg\n",
            "1325918.jpg  1899562.jpg  2428085.jpg  2855844.jpg  3464027.jpg  489347.jpg   896448.jpg\n",
            "1326065.jpg  1899785.jpg  242813.jpg   287000.jpg   3464858.jpg  489532.jpg   898119.jpg\n",
            "1327402.jpg  1900585.jpg  2432061.jpg  2877565.jpg  3473991.jpg  495892.jpg   898303.jpg\n",
            "1336882.jpg  1906287.jpg  2439992.jpg  2881282.jpg  3475936.jpg  513754.jpg   898843.jpg\n",
            "134462.jpg   1907713.jpg  2441328.jpg  2885050.jpg  3478964.jpg  514014.jpg   89892.jpg\n",
            "1344966.jpg  1912976.jpg  2443498.jpg  2885796.jpg  3479875.jpg  517902.jpg   899818.jpg\n",
            "1351146.jpg  1914969.jpg  244505.jpg   2902766.jpg  3479936.jpg  518527.jpg   899959.jpg\n",
            "1351631.jpg  1915343.jpg  2448844.jpg  2916034.jpg  3484590.jpg  527199.jpg   904938.jpg\n",
            "1370319.jpg  1916846.jpg  2451169.jpg  2922019.jpg  3493457.jpg  52934.jpg    910419.jpg\n",
            "1383291.jpg  1934355.jpg  2456207.jpg  2924941.jpg  349946.jpg\t 532970.jpg   917774.jpg\n",
            "1384464.jpg  1944600.jpg  2462190.jpg  2933332.jpg  350358.jpg\t 543556.jpg   918506.jpg\n",
            "138855.jpg   1947572.jpg  2467990.jpg  29417.jpg    3505182.jpg  54461.jpg    920219.jpg\n",
            "1390308.jpg  1950499.jpg  2468499.jpg  2951831.jpg  3512070.jpg  54540.jpg    920595.jpg\n",
            "13983.jpg    1951130.jpg  2470671.jpg  2952219.jpg  3514408.jpg  545561.jpg   926046.jpg\n",
            "1399531.jpg  1958364.jpg  2471646.jpg  2959665.jpg  352051.jpg\t 56449.jpg    928663.jpg\n",
            "140031.jpg   1964051.jpg  2473559.jpg  2965.jpg     3530210.jpg  568383.jpg   928670.jpg\n",
            "1403878.jpg  1968947.jpg  2476468.jpg  2967846.jpg  3536393.jpg  568995.jpg   929067.jpg\n",
            "1407753.jpg  1973447.jpg  2481333.jpg  2980131.jpg  3546278.jpg  576236.jpg   937915.jpg\n",
            "1412034.jpg  1980167.jpg  248252.jpg   2989328.jpg  3549765.jpg  5764.jpg     938821.jpg\n",
            "1413289.jpg  1981348.jpg  2486277.jpg  2990023.jpg  3550805.jpg  579691.jpg   93961.jpg\n",
            "141507.jpg   1984976.jpg  2487039.jpg  2990186.jpg  3554287.jpg  593400.jpg   947246.jpg\n",
            "1423515.jpg  1987634.jpg  2490163.jpg  2992084.jpg  3555299.jpg  59445.jpg    951953.jpg\n",
            "1425089.jpg  1988629.jpg  2491110.jpg  299535.jpg   3557127.jpg  596494.jpg   959901.jpg\n",
            "1426781.jpg  199019.jpg   2492287.jpg  2995731.jpg  3574192.jpg  598381.jpg   962785.jpg\n",
            "143453.jpg   1998483.jpg  2493954.jpg  2999507.jpg  358178.jpg\t 604977.jpg   966644.jpg\n",
            "1454995.jpg  2005870.jpg  2501636.jpg  3000535.jpg  3589437.jpg  608085.jpg   967694.jpg\n",
            "1468795.jpg  2010437.jpg  2501961.jpg  300869.jpg   3595758.jpg  618021.jpg   970073.jpg\n",
            "147785.jpg   2014717.jpg  2502234.jpg  3018077.jpg  3597955.jpg  61822.jpg    972000.jpg\n",
            "1499661.jpg  2019441.jpg  2508157.jpg  3020376.jpg  3614525.jpg  618348.jpg   976382.jpg\n",
            "1504421.jpg  2019583.jpg  2511911.jpg  3023774.jpg  3628930.jpg  625687.jpg   979955.jpg\n",
            "1504719.jpg  2021516.jpg  2516510.jpg  302591.jpg   3629996.jpg  626170.jpg   979998.jpg\n",
            "1507039.jpg  2026009.jpg  2519291.jpg  3039549.jpg  3644733.jpg  626902.jpg   985164.jpg\n",
            "1512514.jpg  2032236.jpg  2529205.jpg  3042454.jpg  3653528.jpg  63480.jpg    98617.jpg\n",
            "1524599.jpg  2035248.jpg  253127.jpg   3055697.jpg  3653643.jpg  647215.jpg   998719.jpg\n",
            "1524655.jpg  203831.jpg   2534774.jpg  3057192.jpg  3660716.jpg  652004.jpg\n",
            "1535273.jpg  2044732.jpg  2556273.jpg  3063955.jpg  3663580.jpg  656817.jpg\n",
            "1544197.jpg  2077999.jpg  2557340.jpg  3066951.jpg  3675128.jpg  662526.jpg\n",
            "1552253.jpg  2078141.jpg  2560539.jpg  307677.jpg   3678290.jpg  663285.jpg\n",
            "1553353.jpg  2078208.jpg  2569760.jpg  3082068.jpg  368644.jpg\t 665900.jpg\n",
            "1571074.jpg  2091857.jpg  2570329.jpg  3082443.jpg  369017.jpg\t 667309.jpg\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "# Walk through the pizza_steak directory and list the number of files\n",
        "for dirpath, dirnames, filenames in os.walk(\"pizza_steak\"):\n",
        "  print(f\"There are {len(dirnames)} directories and {len(filenames)} images in '{dirpath}'.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TArSXBZXc1RY",
        "outputId": "6499c9aa-4050-433d-c1c9-634a292d057b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "There are 2 directories and 0 images in 'pizza_steak'.\n",
            "There are 2 directories and 0 images in 'pizza_steak/train'.\n",
            "There are 0 directories and 750 images in 'pizza_steak/train/steak'.\n",
            "There are 0 directories and 750 images in 'pizza_steak/train/pizza'.\n",
            "There are 2 directories and 0 images in 'pizza_steak/test'.\n",
            "There are 0 directories and 250 images in 'pizza_steak/test/steak'.\n",
            "There are 0 directories and 250 images in 'pizza_steak/test/pizza'.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Another way to fnd out how many images are there in a file\n",
        "num_steak_images_train = len(os.listdir(\"pizza_steak/train/steak\"))\n",
        "num_steak_images_train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H4XplZcFdlgw",
        "outputId": "d94e3f19-f0dd-4d8d-d5b9-2b647d8f9d58"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "750"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### To visualize our images , first let's get the class names programmatically."
      ],
      "metadata": {
        "id": "YFZfRr2aeyVY"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Get the classnames programmatically\n",
        "import pathlib\n",
        "import numpy as np\n",
        "data_dir = pathlib.Path(\"pizza_steak/train\")\n",
        "class_names = np.array(sorted([item.name for item in data_dir.glob(\"*\")])) # Created a list of classnames from subdirectories\n",
        "print(class_names)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "63ZGMUm1e_bX",
        "outputId": "335fd5e5-9469-451c-c32f-51deb2b7bbac"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['pizza' 'steak']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Let's visualize our images (creating a function)\n",
        "import matplotlib.pyplot as plt\n",
        "import matplotlib.image as mpimg\n",
        "import random\n",
        "\n",
        "def view_random_image(target_dir, target_class):\n",
        "  # Setup a target directory (we'll view the image from here)\n",
        "  target_folder = target_dir+target_class\n",
        "\n",
        "  # Get a random image path\n",
        "  random_image = random.sample(os.listdir(target_folder), 1)\n",
        "  print(random_image)\n",
        "\n",
        "  # Read in the image and plot it using matplotlib\n",
        "  img = mpimg.imread(target_folder + \"/\" + random_image[0])\n",
        "  plt.imshow(img)\n",
        "  plt.title(target_class)\n",
        "  plt.axis(\"off\");\n",
        "\n",
        "  print(f\"Image shape: {img.shape}\") # show the shape of the image\n",
        "\n",
        "  return img"
      ],
      "metadata": {
        "id": "8RC_yFmNgFCO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# View a random image from the training dataset\n",
        "img = view_random_image(target_dir=\"pizza_steak/train/\",\n",
        "                        target_class=\"pizza\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 463
        },
        "id": "BU1mv5VDiXYt",
        "outputId": "a402050a-81af-4939-80c3-fd0e5b6ee012"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['709947.jpg']\n",
            "Image shape: (509, 512, 3)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# The images we've imported and plotted are actually giant arrays/tensors of different pixel values\n",
        "import tensorflow as tf\n",
        "tf.constant(img)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LGcjYLs2jD1N",
        "outputId": "f25b408c-e0f5-4d71-d5ea-59bc38b9ba3c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(509, 512, 3), dtype=uint8, numpy=\n",
              "array([[[  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        ...,\n",
              "        [ 85,  48,  21],\n",
              "        [ 84,  47,  20],\n",
              "        [ 84,  47,  20]],\n",
              "\n",
              "       [[  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        ...,\n",
              "        [ 85,  48,  21],\n",
              "        [ 85,  48,  21],\n",
              "        [ 85,  48,  21]],\n",
              "\n",
              "       [[  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        [  1,   1,   1],\n",
              "        ...,\n",
              "        [ 85,  48,  19],\n",
              "        [ 86,  49,  20],\n",
              "        [ 86,  49,  20]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[100,  60,  25],\n",
              "        [101,  61,  26],\n",
              "        [105,  62,  28],\n",
              "        ...,\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3]],\n",
              "\n",
              "       [[101,  61,  26],\n",
              "        [102,  62,  27],\n",
              "        [106,  63,  29],\n",
              "        ...,\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3]],\n",
              "\n",
              "       [[100,  60,  24],\n",
              "        [101,  61,  25],\n",
              "        [106,  63,  28],\n",
              "        ...,\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3],\n",
              "        [  2,   0,   3]]], dtype=uint8)>"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# View the image shape\n",
        "img.shape # returns the width, height and colour channels"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gMCfZijrj1kV",
        "outputId": "cb97a0c9-bb45-4412-eec0-76254e5f20a2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(509, 512, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "🔑**Note:** As we've discussed before , many machine learning models, including neural networks prefer the values they work with to be between 0 and 1 . Knowing this, one of the most common preprocessing steps for working with images is to scale (also referred to as normalize) their pixel values by dividing the image arrays by 255. (since 255 is maximum pixel value)."
      ],
      "metadata": {
        "id": "_bF9LpqQ0SvR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Get all the pixel values between 0 & 1\n",
        "img/255"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d-oi1XLWklA0",
        "outputId": "d068407d-3e52-4bb5-a79e-dfdd9c027307"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[[0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        ...,\n",
              "        [0.33333333, 0.18823529, 0.08235294],\n",
              "        [0.32941176, 0.18431373, 0.07843137],\n",
              "        [0.32941176, 0.18431373, 0.07843137]],\n",
              "\n",
              "       [[0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        ...,\n",
              "        [0.33333333, 0.18823529, 0.08235294],\n",
              "        [0.33333333, 0.18823529, 0.08235294],\n",
              "        [0.33333333, 0.18823529, 0.08235294]],\n",
              "\n",
              "       [[0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        [0.00392157, 0.00392157, 0.00392157],\n",
              "        ...,\n",
              "        [0.33333333, 0.18823529, 0.0745098 ],\n",
              "        [0.3372549 , 0.19215686, 0.07843137],\n",
              "        [0.3372549 , 0.19215686, 0.07843137]],\n",
              "\n",
              "       ...,\n",
              "\n",
              "       [[0.39215686, 0.23529412, 0.09803922],\n",
              "        [0.39607843, 0.23921569, 0.10196078],\n",
              "        [0.41176471, 0.24313725, 0.10980392],\n",
              "        ...,\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471]],\n",
              "\n",
              "       [[0.39607843, 0.23921569, 0.10196078],\n",
              "        [0.4       , 0.24313725, 0.10588235],\n",
              "        [0.41568627, 0.24705882, 0.11372549],\n",
              "        ...,\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471]],\n",
              "\n",
              "       [[0.39215686, 0.23529412, 0.09411765],\n",
              "        [0.39607843, 0.23921569, 0.09803922],\n",
              "        [0.41568627, 0.24705882, 0.10980392],\n",
              "        ...,\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471],\n",
              "        [0.00784314, 0.        , 0.01176471]]])"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tf_keras"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8TSN8hFAFxDh",
        "outputId": "dc76f819-6309-48ff-c519-031f24f2df5f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tf_keras in /usr/local/lib/python3.10/dist-packages (2.17.0)\n",
            "Requirement already satisfied: tensorflow<2.18,>=2.17 in /usr/local/lib/python3.10/dist-packages (from tf_keras) (2.17.0)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=24.3.25 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (24.3.25)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (0.6.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (0.2.0)\n",
            "Requirement already satisfied: h5py>=3.10.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (3.11.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (18.1.1)\n",
            "Requirement already satisfied: ml-dtypes<0.5.0,>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (0.4.0)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (3.3.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (24.1)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (3.20.3)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (2.31.0)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (71.0.4)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.16.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (2.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (4.12.2)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.16.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.64.1)\n",
            "Requirement already satisfied: tensorboard<2.18,>=2.17 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (2.17.0)\n",
            "Requirement already satisfied: keras>=3.2.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (3.4.1)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (0.37.1)\n",
            "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in /usr/local/lib/python3.10/dist-packages (from tensorflow<2.18,>=2.17->tf_keras) (1.26.4)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from astunparse>=1.6.0->tensorflow<2.18,>=2.17->tf_keras) (0.43.0)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (13.7.1)\n",
            "Requirement already satisfied: namex in /usr/local/lib/python3.10/dist-packages (from keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (0.0.8)\n",
            "Requirement already satisfied: optree in /usr/local/lib/python3.10/dist-packages (from keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (0.12.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorflow<2.18,>=2.17->tf_keras) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorflow<2.18,>=2.17->tf_keras) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorflow<2.18,>=2.17->tf_keras) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorflow<2.18,>=2.17->tf_keras) (2024.7.4)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.18,>=2.17->tensorflow<2.18,>=2.17->tf_keras) (3.6)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.18,>=2.17->tensorflow<2.18,>=2.17->tf_keras) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.18,>=2.17->tensorflow<2.18,>=2.17->tf_keras) (3.0.3)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard<2.18,>=2.17->tensorflow<2.18,>=2.17->tf_keras) (2.1.5)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich->keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (2.16.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->keras>=3.2.0->tensorflow<2.18,>=2.17->tf_keras) (0.1.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tf_keras as keras"
      ],
      "metadata": {
        "id": "XIWbdXoXF8Mv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## An end-to-end example\n",
        "Let's build a convolutional neural network to find patterns in our images, more specifically we need a way to :\n",
        "* Load our images\n",
        "* Preprocess our images\n",
        "* Build a CNN to find patterns in our images\n",
        "* Compile our CNN\n",
        "* Fit the CNN to our training data"
      ],
      "metadata": {
        "id": "QGf8R4illJ5d"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# Set the seed\n",
        "tf.random.set_seed(69)\n",
        "\n",
        "# Preprocess data (get all of the pixel values between 0 & 1 , also called normalization)\n",
        "train_datagen = ImageDataGenerator(rescale=1./255)\n",
        "valid_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "# Setup paths to our data directories\n",
        "train_dir = \"/content/pizza_steak/train\"\n",
        "test_dir = \"/content/pizza_steak/test\"\n",
        "\n",
        "# Import data from directories and turn it into batches\n",
        "train_data = keras.utils.image_dataset_from_directory(directory=train_dir,\n",
        "                                                         batch_size=32,\n",
        "                                                         image_size=(224,224),\n",
        "                                                         label_mode=\"binary\",\n",
        "                                                         seed=69)\n",
        "valid_data = keras.utils.image_dataset_from_directory(directory=test_dir,\n",
        "                                                         batch_size=32,\n",
        "                                                         image_size=(224,224),\n",
        "                                                         label_mode=\"binary\",\n",
        "                                                         seed=69)\n",
        "\n",
        "# Build a CNN model ( same as Tiny VGG on the CNN explainer website)\n",
        "model_1 = keras.models.Sequential([\n",
        "    keras.layers.Conv2D(filters=10,\n",
        "                           kernel_size=3,\n",
        "                           activation=\"relu\",\n",
        "                           input_shape=(224,224,3)),\n",
        "    keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    keras.layers.MaxPool2D(pool_size=2,\n",
        "                              padding=\"valid\"),\n",
        "    keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    keras.layers.MaxPool2D(2),\n",
        "    keras.layers.Flatten(),\n",
        "    keras.layers.Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "\n",
        "# Compile our CNN\n",
        "model_1.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=\"Adam\",\n",
        "                metrics=[\"accuracy\"])\n",
        "\n",
        "# Fit the model\n",
        "history_model_1 = model_1.fit(train_data,\n",
        "                              epochs=5,\n",
        "                              steps_per_epoch=len(train_data),\n",
        "                              validation_data=valid_data,\n",
        "                              validation_steps=len(valid_data))"
      ],
      "metadata": {
        "id": "NqYyHmeg2DhW",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "00dd6d0c-a193-419f-bda3-45140915aa25"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 1500 files belonging to 2 classes.\n",
            "Found 500 files belonging to 2 classes.\n",
            "Epoch 1/5\n",
            "47/47 [==============================] - 99s 2s/step - loss: 22.8083 - accuracy: 0.5673 - val_loss: 0.7444 - val_accuracy: 0.6420\n",
            "Epoch 2/5\n",
            "47/47 [==============================] - 98s 2s/step - loss: 0.5872 - accuracy: 0.7260 - val_loss: 0.5993 - val_accuracy: 0.7280\n",
            "Epoch 3/5\n",
            "47/47 [==============================] - 97s 2s/step - loss: 0.4000 - accuracy: 0.8280 - val_loss: 0.6139 - val_accuracy: 0.7520\n",
            "Epoch 4/5\n",
            "47/47 [==============================] - 97s 2s/step - loss: 0.3093 - accuracy: 0.8807 - val_loss: 0.5958 - val_accuracy: 0.7500\n",
            "Epoch 5/5\n",
            "47/47 [==============================] - 96s 2s/step - loss: 0.2275 - accuracy: 0.9247 - val_loss: 0.6163 - val_accuracy: 0.7620\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "The above cell is run using CPU , so it takes a lot of time. Let's do the same using a GPU this time."
      ],
      "metadata": {
        "id": "2ENPPLF58IWQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# Set the seed\n",
        "tf.random.set_seed(69)\n",
        "\n",
        "# Preprocess data (get all of the pixel values between 0 & 1 , also called normalization)\n",
        "train_datagen = ImageDataGenerator(rescale=1./255)\n",
        "valid_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "# Setup paths to our data directories\n",
        "train_dir = \"/content/pizza_steak/train\"\n",
        "test_dir = \"/content/pizza_steak/test\"\n",
        "\n",
        "# Import data from directories and turn it into batches\n",
        "train_data = train_datagen.flow_from_directory(directory=train_dir,\n",
        "                                               batch_size=32,\n",
        "                                               target_size=(224,224),\n",
        "                                               class_mode=\"binary\",\n",
        "                                               seed=69)\n",
        "valid_data = valid_datagen.flow_from_directory(directory=test_dir,\n",
        "                                               batch_size=32,\n",
        "                                               target_size=(224,224),\n",
        "                                               class_mode=\"binary\",\n",
        "                                               seed=69)\n",
        "\n",
        "# Build a CNN model ( same as Tiny VGG on the CNN explainer website)\n",
        "model_1 = tf.keras.models.Sequential([\n",
        "    tf.keras.layers.Conv2D(filters=10,\n",
        "                           kernel_size=3,\n",
        "                           activation=\"relu\",\n",
        "                           input_shape=(224,224,3)),\n",
        "    tf.keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    tf.keras.layers.MaxPool2D(pool_size=2,\n",
        "                              padding=\"valid\"),\n",
        "    tf.keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    tf.keras.layers.Conv2D(10,3, activation=\"relu\"),\n",
        "    tf.keras.layers.MaxPool2D(2),\n",
        "    tf.keras.layers.Flatten(),\n",
        "    tf.keras.layers.Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "\n",
        "# Compile our CNN\n",
        "model_1.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=tf.keras.optimizers.Adam(),\n",
        "                metrics=[\"accuracy\"])\n",
        "\n",
        "# Fit the model\n",
        "history_model_1 = model_1.fit(train_data,\n",
        "                              epochs=5,\n",
        "                              steps_per_epoch=len(train_data),\n",
        "                              validation_data=valid_data,\n",
        "                              validation_steps=len(valid_data))"
      ],
      "metadata": {
        "id": "uo0yINIr-TZH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "🔑**Note:** If a cell takes more than 10 seconds to execute , make sure to use a GPU for faster execution"
      ],
      "metadata": {
        "id": "vnlnv3ZZ-jm9"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a model summary\n",
        "model_1.summary()"
      ],
      "metadata": {
        "id": "kJ-cz6Lp_poV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Using the same model as before\n",
        "\n",
        "Let's replicate the model we've built in a previous section to see if it works with our image data.\n",
        "\n",
        "The model we're building is from TensorFlow playground."
      ],
      "metadata": {
        "id": "vDxXUk2j_w2U"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Set random seed\n",
        "tf.random.set_seed(69)\n",
        "# Create a model to replicate the TensorFlow playground model\n",
        "model_2 = tf.keras.Sequential([\n",
        "    tf.keras.layers.Flatten(input_shape=(224,224,3)),\n",
        "    tf.keras.layers.Dense(4, activation=\"relu\"),\n",
        "    tf.keras.layers.Dense(4, activation=\"relu\"),\n",
        "    tf.keras.layers.Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "# Compile the model\n",
        "model_2.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=\"Adam\",\n",
        "                metrics=[\"accuracy\"])\n",
        "# Fit the model\n",
        "history_2 = model_2.fit(train_data,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=valid_data,\n",
        "                        validation_steps=len(valid_data))"
      ],
      "metadata": {
        "id": "MEdTNmq5Amzt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a summary of model 2\n",
        "model_2.summary()"
      ],
      "metadata": {
        "id": "IlmUEwS7D3XL"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Despite having 20x more parameters than our CNN (model_1), model_2 performs terribly...let's try and improve it"
      ],
      "metadata": {
        "id": "PnkF5FrMEpIL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Set random seed\n",
        "tf.random.set_seed(69)\n",
        "# Create a model to replicate the TensorFlow playground model\n",
        "model_3 = tf.keras.Sequential([\n",
        "    tf.keras.layers.Flatten(input_shape=(224,224,3)),\n",
        "    tf.keras.layers.Dense(100, activation=\"relu\"),\n",
        "    tf.keras.layers.Dense(60, activation=\"relu\"),\n",
        "    tf.keras.layers.Dense(30, activation=\"relu\"),\n",
        "    tf.keras.layers.Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "# Compile the model\n",
        "model_3.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=\"Adam\",\n",
        "                metrics=[\"accuracy\"])\n",
        "# Fit the model\n",
        "history_3 = model_3.fit(train_data,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=valid_data,\n",
        "                        validation_steps=len(valid_data))"
      ],
      "metadata": {
        "id": "ZARjbl-qFcsv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a summary of model 3\n",
        "model_3.summary()"
      ],
      "metadata": {
        "id": "UdhZYJykFnZi"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Binary Classification : Let's break it down\n",
        "\n",
        "1. Become one with the data (visualize, visualize, visualize)\n",
        "2. Preprocess the data (prepare it for our model, the main step here was scaling/normalizing & turning our data into batches)\n",
        "3. Create a model (start with a baseline)\n",
        "4. Fit the model\n",
        "5. Evaluate the model\n",
        "6. Adjust different parameters and improve the model (try to beat our baseline)\n",
        "7. Repeat until satisfied(experiment, experiment, experiment)"
      ],
      "metadata": {
        "id": "STY_l4ZYGseh"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 1. Become one with the data"
      ],
      "metadata": {
        "id": "rpZT85EJJ10W"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Visualize data\n",
        "plt.figure()\n",
        "plt.subplot(1,2,1)\n",
        "steak_img = view_random_image(\"pizza_steak/train/\",\"steak\")\n",
        "plt.subplot(1,2,2)\n",
        "pizza_img = view_random_image(\"pizza_steak/train/\", \"pizza\")"
      ],
      "metadata": {
        "id": "GF2GmpObJ0PR"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. Preprocess our data (prepare it for our model)"
      ],
      "metadata": {
        "id": "bF5p_qHiKrQ_"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Define our directory dataset paths\n",
        "train_dir = \"/content/pizza_steak/train\"\n",
        "test_dir = \"/content/pizza_steak/test\""
      ],
      "metadata": {
        "id": "0Tw5H_h2OyZG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Our next step is to turn our data into **batches**.\n",
        "\n",
        "A batch is a small subset of data. Rather than look at all ~10,000 images at one time , a model might only look at 32 at a time.\n",
        "\n",
        "It does this for a couple of reasons:\n",
        "1. 10,000 images(or more) might not fit into the memory of your processor (GPU).\n",
        "2. Trying to learn the patterns in 10,000 images in one hit could result in the same model not being able to learn very well.\n",
        "\n",
        "Why 32(size of one batch)?\n",
        "\n",
        "Because 32 is good for your health...🤣\n"
      ],
      "metadata": {
        "id": "S5rOaboAPJJO"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Create train and test data generators and rescale the data\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "train_datagen = ImageDataGenerator(rescale=1/255.)\n",
        "test_datagen = ImageDataGenerator(rescale=1/255.)"
      ],
      "metadata": {
        "id": "HDuwv34yPGhl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load in our image data from our directories and turn them into batches\n",
        "train_data = train_datagen.flow_from_directory(directory=train_dir,   # Target directory of images\n",
        "                                               target_size=(224,224),   # Target size of images (height,width)\n",
        "                                               class_mode=\"binary\",   # Type of data we're working with\n",
        "                                               batch_size=32)    # Size of minibatches to load data into\n",
        "test_data = test_datagen.flow_from_directory(directory=test_dir,\n",
        "                                             target_size=(224,224),\n",
        "                                             class_mode=\"binary\",\n",
        "                                             batch_size=32)"
      ],
      "metadata": {
        "id": "y8D6an0FSnS7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a sample of training data batch\n",
        "images , labels = train_data.next()  # get the 'next' batch of images/labels in train_data\n",
        "len(images), len(labels)"
      ],
      "metadata": {
        "id": "pWHO_ZSnU2qk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# How many batches are there ?\n",
        "len(train_data)"
      ],
      "metadata": {
        "id": "bfH-Vl0rVf6a"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get the first two images\n",
        "images[:2], images[0].shape"
      ],
      "metadata": {
        "id": "IFqS3ovoV2Yq"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# View the first batch of labels\n",
        "labels"
      ],
      "metadata": {
        "id": "_vB7nrs_WFzp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 3. Create a CNN model (start with a baseline)\n",
        "\n",
        "A baseline is a relatively simple model or existing result that you setup when beginning a machine learning experiment and then as you keep experimenting , you try to beat the baseline.\n",
        "\n",
        ">🔑**Note:** In deep learning , there is almost an infinite number of architecture you could create. So one of the best ways to get started is to start with something simple and see if it works on your data and then introduce complexity as required (e.g. look at which current model is performing best in the field for your problem)."
      ],
      "metadata": {
        "id": "FuhKuC2VWiSq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Make the creating of our model a little easier\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPool2D, Activation\n",
        "from tensorflow.keras import Sequential"
      ],
      "metadata": {
        "id": "Pxqu5ilDXt9h"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create the model (this will be our baseline, a 3 layer convolutional neural network)\n",
        "model_4 = Sequential([\n",
        "    Conv2D(filters=10,   # filter is the number of sliding windows going across an input (higher = more complex model)\n",
        "           kernel_size=3,  # the size of the sliding window going across an input\n",
        "           strides=1,   # the size of the step the sliding window takes across an input\n",
        "           padding=\"valid\",   # if \"same\" , output shape is same as input shape , if \"valid\" , output shape gets compressed\n",
        "           activation=\"relu\",\n",
        "           input_shape=(224,224,3)),   # input layer (specify the input shape )\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    Flatten(),\n",
        "    Dense(1, activation=\"sigmoid\")   # output layer (working with binary classification so only 1 output neuron)\n",
        "])"
      ],
      "metadata": {
        "id": "rlDfr1WwYcQh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Compile the model\n",
        "model_4.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=Adam(),\n",
        "                metrics=[\"accuracy\"])"
      ],
      "metadata": {
        "id": "MFXKEOBk1OEi"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a summary of our model\n",
        "model_4.summary()"
      ],
      "metadata": {
        "id": "zXWBt_Xp1qgM"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 4. Fit the Model"
      ],
      "metadata": {
        "id": "vox0NMAY1iRt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Check the lengths of training and test data generators\n",
        "len(train_data), len(test_data)"
      ],
      "metadata": {
        "id": "UusIafs11yD6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Fit the model\n",
        "history_4 = model_4.fit(train_data, # this is a combination of labels and sample data\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(test_data))"
      ],
      "metadata": {
        "id": "WfiedpOI2E2W"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 5. Evaluating our model\n",
        "\n",
        "It looks like our model is learning something, let's evaluate it."
      ],
      "metadata": {
        "id": "owIQi0oU3Wo1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Let's plot the training curves\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "pd.DataFrame(history_4.history).plot(figsize=(10,7));"
      ],
      "metadata": {
        "id": "qOpKZ3rS4mB6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot the validation and training curves seperately\n",
        "def plot_loss_curves(history):\n",
        "  \"\"\"\n",
        "  Returns seperate loss curves for training and validation metrics.\n",
        "  \"\"\"\n",
        "  loss = history.history[\"loss\"]\n",
        "  val_loss = history.history[\"val_loss\"]\n",
        "\n",
        "  accuracy = history.history[\"accuracy\"]\n",
        "  val_accuracy = history.history[\"val_accuracy\"]\n",
        "\n",
        "  epochs = range(len(history.history[\"loss\"])) # how many epochs did we run for ?\n",
        "\n",
        "  # Plot loss\n",
        "  plt.plot(epochs, loss, label=\"training_loss\")\n",
        "  plt.plot(epochs, val_loss, label=\"val_loss\")\n",
        "  plt.title(\"loss\")\n",
        "  plt.xlabel(\"epochs\")\n",
        "  plt.legend()\n",
        "\n",
        "  # Plot accuracy\n",
        "  plt.figure()\n",
        "  plt.plot(epochs, accuracy, label=\"training_accuracy\")\n",
        "  plt.plot(epochs, val_accuracy, label=\"val_accuracy\")\n",
        "  plt.title(\"accuracy\")\n",
        "  plt.xlabel(\"epochs\")\n",
        "  plt.legend();"
      ],
      "metadata": {
        "id": "I60TPb-15HU0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        ">🔑**Note:** When a model's **validation loss starts to increase**, it's likely that the model is **overfitting** the training dataset. This means, it's learning the patterns *too well* and thus the model's ability to generalize the unseen data is diminished ."
      ],
      "metadata": {
        "id": "duJ5xvKD7wU5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Check out loss and accuracy of model 4\n",
        "plot_loss_curves(history_4)"
      ],
      "metadata": {
        "id": "KZdZR9hr6uIS"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "🔑**Note:** Ideally the two loss curves (training and validation) will be very similar to each other (training loss and validation loss decreasing at similar rates), when there are large differences your model may be **overfitting**."
      ],
      "metadata": {
        "id": "vNGMkve_7X-7"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 6. Adjust the model parameters\n",
        "\n",
        "Fitting a machine learning model comes in 3 steps :\n",
        "\n",
        "0. Create a baseline\n",
        "1. Beat the baseline by overfitting a larger model\n",
        "2. Reduce overfitting\n",
        "\n",
        "Ways to induce overfitting :\n",
        "* Increase the number of conv layers\n",
        "* Increase the number of conv filters\n",
        "* Add another dense layer to the output of our flattened layer\n",
        "\n",
        "Ways to reduce overfitting:\n",
        "* Add data augmentation\n",
        "* Add regularization layers (such as MaxPool2D)\n",
        "* Add more data...\n",
        "\n",
        ">🔑**Note:** Reducing overfitting is also known as **regularization**."
      ],
      "metadata": {
        "id": "BIt3_N969pV-"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Create the model (this is going to be our new baseline)\n",
        "model_5 = Sequential([\n",
        "    Conv2D(10, 3, activation=\"relu\", input_shape=(224,224, 3)),\n",
        "    MaxPool2D(pool_size=2),\n",
        "    Conv2D(10, 3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Conv2D(10, 3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Flatten(),\n",
        "    Dense(1, activation=\"sigmoid\")\n",
        "])"
      ],
      "metadata": {
        "id": "lxZb2AnW-0C1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Compile the model\n",
        "model_5.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=Adam(),\n",
        "                metrics=[\"accuracy\"])"
      ],
      "metadata": {
        "id": "-GST70vXBoTk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Fit the model\n",
        "history_5 = model_5.fit(train_data,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(valid_data))"
      ],
      "metadata": {
        "id": "29VJ4R-MCUuE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get a summary of our model with max pooling\n",
        "model_5.summary()"
      ],
      "metadata": {
        "id": "HR1e_6CDDX_D"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot loss curves using our helpful function\n",
        "plot_loss_curves(history_5)"
      ],
      "metadata": {
        "id": "w81Ut1d6D4j8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Opening our bag of tricks and finding Data Augmentation"
      ],
      "metadata": {
        "id": "aIivzSeXENIz"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Create ImageDataGenerator training instance with data augmentation\n",
        "train_datagen_augmented = ImageDataGenerator(rescale=1/255.,\n",
        "                                             rotation_range=0.2,   # how much do you want to rotate an image ?\n",
        "                                             shear_range=0.2,   # how much do you want to shear an image ?\n",
        "                                             zoom_range=0.2,  # zoom in randomly on an image\n",
        "                                             width_shift_range=0.2,  # move your image around on the x-axis\n",
        "                                             height_shift_range=0.2,  # move your image around on the y-axis\n",
        "                                             horizontal_flip=True)   # do you want to flip an image ?\n",
        "# Create ImageDataGenerator without data augmentation\n",
        "train_datagen = ImageDataGenerator(rescale=1/255.)\n",
        "\n",
        "# Create ImageDataGenerator without data augmentation for the test dataset\n",
        "test_datagen = ImageDataGenerator(rescale=1/255.)"
      ],
      "metadata": {
        "id": "G56u-ClUFnpt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "🤔**Question:** What is data augmentation ?\n",
        "\n",
        "Data augmentation is the process of altering our training data, leading it to have more diversity and in turn allowing our models to learn more generalizable(hopefully) patterns. Altering might mean adjusting the rotation of an image , flipping it , cropping it or something similar.\n",
        "\n",
        "Let's write some code to visualize data augmentation."
      ],
      "metadata": {
        "id": "QhoIXdYZHuvK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import data and augment it from the training directory\n",
        "print(\"Augmented training data:\")\n",
        "train_data_augmented = train_datagen_augmented.flow_from_directory(train_dir,\n",
        "                                                                   target_size=(224,224),\n",
        "                                                                   batch_size=32,\n",
        "                                                                   class_mode=\"binary\",\n",
        "                                                                   shuffle=False)  # for demonstration purpose only\n",
        "# Create non-augmented train data batches\n",
        "print(\"Non-augmented training data:\")\n",
        "train_data = train_datagen.flow_from_directory(train_dir,\n",
        "                                               target_size=(224,224),\n",
        "                                               batch_size=32,\n",
        "                                               class_mode=\"binary\",\n",
        "                                               shuffle=False)\n",
        "# Create non-augmented test data batches\n",
        "print(\"Non-augmented test data:\")\n",
        "test_data = test_datagen.flow_from_directory(test_dir,\n",
        "                                             target_size=(224,224),\n",
        "                                             batch_size=32,\n",
        "                                             class_mode=\"binary\")"
      ],
      "metadata": {
        "id": "L3qVcuqFIogB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        ">🔑**Note:** Data augmentation is usually performed on the training data. Using `ImageDataGenerator` built-in data augmentation parameters our images are left as they are in the directories but are modified as they are loaded into the model.\n",
        "\n",
        "Finally...let's visualize some augmented data !!!"
      ],
      "metadata": {
        "id": "UrijpXiUNAEH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Get sample augmented data batches\n",
        "images, labels = train_data.next()\n",
        "augmented_images, augmented_labels = train_data_augmented.next() # note: labels aren't augmented...only data (images)"
      ],
      "metadata": {
        "id": "_kNGFS2aOyhl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Show the original image and the augmented image\n",
        "import random\n",
        "random_number = random.randint(0,32) # our batch size are 32...\n",
        "print(f\"showing image number: {random_number}\")\n",
        "plt.imshow(images[random_number])\n",
        "plt.title(f\"Original image\")\n",
        "plt.axis(False)\n",
        "plt.figure()\n",
        "plt.imshow(augmented_images[random_number])\n",
        "plt.title(f\"Augmented image\")\n",
        "plt.axis(False);"
      ],
      "metadata": {
        "id": "uIL9hlA0PxSe"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Now we've seen what augmented training data looks like, let's build a model and see how it learns on augmented data."
      ],
      "metadata": {
        "id": "4vGZryEDSzEp"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Create a model on augmented data\n",
        "model_6 = Sequential([\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(pool_size=2),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Flatten(),\n",
        "    Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "\n",
        "# Compile the model\n",
        "model_6.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=Adam(),\n",
        "                metrics=[\"accuracy\"])\n",
        "\n",
        "# Fit the model\n",
        "history_6 = model_6.fit(train_data_augmented,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data_augmented),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(test_data))"
      ],
      "metadata": {
        "id": "n6kS-CSgQ3fd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Check our model's loss curves\n",
        "plot_loss_curves(history_6)"
      ],
      "metadata": {
        "id": "8VAbA2OTU7jE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Let's shuffle our augmented training data and train another model(the same as before) on it and see what happens."
      ],
      "metadata": {
        "id": "9C-cITBqVvMM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Import data and augment it and shuffle from the training directory\n",
        "train_data_augmented_shuffled = train_datagen_augmented.flow_from_directory(train_dir,\n",
        "                                                                            target_size=(224,224),\n",
        "                                                                            class_mode=\"binary\",\n",
        "                                                                            batch_size=32,\n",
        "                                                                            shuffle=True)  #shuffle data this time"
      ],
      "metadata": {
        "id": "LlpkK9ljW3BX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create the model (same as model_5 and model_6)\n",
        "model_7 = Sequential([\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(pool_size=2),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Flatten(),\n",
        "    Dense(1, activation=\"sigmoid\")\n",
        "])\n",
        "\n",
        "# Compile the model\n",
        "model_7.compile(loss=\"binary_crossentropy\",\n",
        "                optimizer=Adam(),\n",
        "                metrics=[\"accuracy\"])\n",
        "\n",
        "# Fit the model\n",
        "history_7 = model_7.fit(train_data_augmented_shuffled,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data_augmented_shuffled),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(test_data))"
      ],
      "metadata": {
        "id": "7Q-4rUORYAge"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot the loss curves\n",
        "plot_loss_curves(history_7)"
      ],
      "metadata": {
        "id": "-sP-gHzEY86J"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "🔑**Note:** When shuffling data, the model gets exposed to all different kinds of data during training , thus enabling it to learn features across a wide array of images (in our case , pizza and steak at the same time instead of just pizza and then steak)."
      ],
      "metadata": {
        "id": "TApZOJywZZA5"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 7. Repeat until satisfied\n",
        "\n",
        "Since we've already beaten our baseline , there are a few things we could try to continue to improve our model :\n",
        "\n",
        "* Increase the number of model layers (e.g. add more `Conv2D`\\ `MaxPool2D` layers)\n",
        "* Increase the number of filters in each convolutional layer (e.g. from 10 to 32 or even 64)\n",
        "* Train for longer (more epochs)\n",
        "* Find an ideal learning rate\n",
        "* Get more data (give the model more opportunities to learn)\n",
        "* Use **transfer learning** to leverage what another image model has learnt and adjust it for our own use case."
      ],
      "metadata": {
        "id": "fpCPKlh_a82m"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Making a prediction with our trained model on our own custom data"
      ],
      "metadata": {
        "id": "fNwgf8X1bcjg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Classes we're working with\n",
        "print(class_names)"
      ],
      "metadata": {
        "id": "9a_YOqL1dVva"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# View our example image\n",
        "import matplotlib.image as mpimg\n",
        "import matplotlib.pyplot as plt\n",
        "steak = mpimg.imread(\"03-steak.jpeg\")\n",
        "plt.imshow(steak)\n",
        "plt.axis(False);"
      ],
      "metadata": {
        "id": "hziuVhtYdazv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Check the shape of our shape\n",
        "steak.shape"
      ],
      "metadata": {
        "id": "Vr9tS1mhgiBt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        ">🔑**Note:** When you train a neural network and you want to make a prediction with it on your own custom data, it's important that your custom data (or new data) is preprocessed into the same format as the data your model was trained on."
      ],
      "metadata": {
        "id": "xWrmjdFIg6r1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf"
      ],
      "metadata": {
        "id": "_LxWALb3kR8l"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create a function to import an image and resize it to be able to be used with our model\n",
        "def load_and_pred_image(filename, img_shape=224):\n",
        "  \"\"\"\n",
        "  Reads an image form filename and turns it into a tensor and reshapes it to (img_shape, img_shape, colour_channels).\n",
        "  \"\"\"\n",
        "  # Read in the image\n",
        "  img = tf.io.read_file(filename)\n",
        "  # Decode the read file into a tensor\n",
        "  img = tf.image.decode_image(img)\n",
        "  # Resize the image\n",
        "  img = tf.image.resize(img, size=[img_shape, img_shape])\n",
        "  # Rescale the image and get all values beween 0 and 1]\n",
        "  img = img/255.\n",
        "  return img"
      ],
      "metadata": {
        "id": "9cuzv6m6iTiD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load in and preprocess ou custom images\n",
        "steak = load_and_pred_image(\"03-steak.jpeg\")\n",
        "steak"
      ],
      "metadata": {
        "id": "ZSy0N_njkDYk"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pred = model_7.predict(tf.expand_dims(steak, axis=0))\n",
        "pred"
      ],
      "metadata": {
        "id": "aNAyuFXRkPNr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Looks like our custom image is being put through our model , however it currently outputs a prediction probability , wouldn't it be nice if we could visualize the image as well as the model's prediction ?"
      ],
      "metadata": {
        "id": "z0iKLOpm-lXO"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Remind ourselves of the class names\n",
        "class_names"
      ],
      "metadata": {
        "id": "Tz9B73EGk2F8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# We can index the predicted class by rounding the prediction probability and indexing it on the class names\n",
        "pred_class = class_names[int(tf.round(pred))]\n",
        "pred_class"
      ],
      "metadata": {
        "id": "EqdTNaOa_T7T"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def pred_and_plot(model, filename, class_names=class_names):\n",
        "  \"\"\"\n",
        "  Imports an image located at filename, makes a prediction with model and plots the image with the predicted class as the title.\n",
        "  \"\"\"\n",
        "  # Import the target image and preprocess it\n",
        "  img = load_and_pred_image(filename)\n",
        "\n",
        "  # Make a prediction\n",
        "  pred = model.predict(tf.expand_dims(img, axis=0))\n",
        "\n",
        "  # Get the predicted class\n",
        "  pred_class = class_names[int(tf.round(pred))]\n",
        "\n",
        "  # Plot the image and predicted class\n",
        "  plt.imshow(img)\n",
        "  plt.title(f\"Prediction: {pred_class}\")\n",
        "  plt.axis(False);"
      ],
      "metadata": {
        "id": "wHR0plwf_2dr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Test our model on a custom image\n",
        "pred_and_plot(model_7, \"03-steak.jpeg\")"
      ],
      "metadata": {
        "id": "I79gS9yXBqne"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Our model works! Let's try it on another image... this time pizza 🍕"
      ],
      "metadata": {
        "id": "hIWEVfHdCDZa"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Download another test custom image and make a prediction on it\n",
        "pred_and_plot(model_7, \"pizza-sample.jpeg\")"
      ],
      "metadata": {
        "id": "kCQqfFIeDu_o"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Multi-class Image Classification\n",
        "\n",
        "We've just been through a bunch of the following steps with a binary classification problem (pizza vs. steak) , now we're going to step up things up a notch with 10 classes of food (multi-class classification). The steps to be taken are as follows :\n",
        "\n",
        "1. Become one with the data\n",
        "2. Preprocess the data ( get it ready for our model)\n",
        "3. Create a model (start with a baseline)\n",
        "4. Fit the model (overfit it to make sure it works)\n",
        "5. Evaluate the model\n",
        "6. Adjust different hyperparameters and improve the model (try to beat baseline/reduce overfitting)\n",
        "7. Repeat until satisfied"
      ],
      "metadata": {
        "id": "A0oSV-riESup"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 1. Import and become one with the data\n"
      ],
      "metadata": {
        "id": "Yz0x-4vmHPO5"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import zipfile\n",
        "\n",
        "!wget https://storage.googleapis.com/ztm_tf_course/food_vision/10_food_classes_all_data.zip\n",
        "\n",
        "# Unzip our data\n",
        "zip_ref = zipfile.ZipFile(\"10_food_classes_all_data.zip\", \"r\")\n",
        "zip_ref.extractall()\n",
        "zip_ref.close()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dQhSO1LwHoxM",
        "outputId": "4feb7f40-a6c3-4e6c-aa84-19f4ce405ccb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2024-08-03 13:42:39--  https://storage.googleapis.com/ztm_tf_course/food_vision/10_food_classes_all_data.zip\n",
            "Resolving storage.googleapis.com (storage.googleapis.com)... 142.250.101.207, 142.250.141.207, 142.251.2.207, ...\n",
            "Connecting to storage.googleapis.com (storage.googleapis.com)|142.250.101.207|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 519183241 (495M) [application/zip]\n",
            "Saving to: ‘10_food_classes_all_data.zip.1’\n",
            "\n",
            "10_food_classes_all 100%[===================>] 495.13M  50.5MB/s    in 5.2s    \n",
            "\n",
            "2024-08-03 13:42:45 (94.4 MB/s) - ‘10_food_classes_all_data.zip.1’ saved [519183241/519183241]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "# Walk through 10 classes of food image data\n",
        "for dirpath, dirnames, filenames in os.walk(\"10_food_classes_all_data\"):\n",
        "  print(f\"There are {len(dirnames)} directories and {len(filenames)} images in '{dirpath}'.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7QCPzpeXIII4",
        "outputId": "85f69662-dcf1-4dd1-8210-f967971448c5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "There are 2 directories and 0 images in '10_food_classes_all_data'.\n",
            "There are 10 directories and 0 images in '10_food_classes_all_data/train'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/hamburger'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/grilled_salmon'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/chicken_wings'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/steak'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/sushi'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/pizza'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/fried_rice'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/ramen'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/ice_cream'.\n",
            "There are 0 directories and 750 images in '10_food_classes_all_data/train/chicken_curry'.\n",
            "There are 10 directories and 0 images in '10_food_classes_all_data/test'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/hamburger'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/grilled_salmon'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/chicken_wings'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/steak'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/sushi'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/pizza'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/fried_rice'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/ramen'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/ice_cream'.\n",
            "There are 0 directories and 250 images in '10_food_classes_all_data/test/chicken_curry'.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Setup the train and test directories\n",
        "train_dir = \"10_food_classes_all_data/train/\"\n",
        "test_dir = \"10_food_classes_all_data/test/\""
      ],
      "metadata": {
        "id": "EE7V_j-2J8JW"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Let's get the class_names\n",
        "import pathlib\n",
        "import numpy as np\n",
        "data_dir = pathlib.Path(train_dir)\n",
        "class_names = np.array(sorted([item.name for item in data_dir.glob('*')]))\n",
        "print(class_names)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "m4Pzy54vK4ih",
        "outputId": "5f66ca5f-e89e-4979-cdd3-c7e6e71e1a07"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['chicken_curry' 'chicken_wings' 'fried_rice' 'grilled_salmon' 'hamburger'\n",
            " 'ice_cream' 'pizza' 'ramen' 'steak' 'sushi']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Visualize, visualize, visusalize\n",
        "import random\n",
        "img = view_random_image(target_dir=train_dir,\n",
        "                        target_class=random.choice(class_names))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 463
        },
        "id": "7_mJq8a3OIzX",
        "outputId": "37f245b4-7da9-45af-81bb-ba328c51e0d8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['3168620.jpg']\n",
            "Image shape: (512, 384, 3)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 2. Preprocess the data (prepare it for a model)"
      ],
      "metadata": {
        "id": "27B-DEFsL9UF"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# Rescale\n",
        "train_datagen = ImageDataGenerator(rescale=1/255.)\n",
        "test_datagen = ImageDataGenerator(rescale=1/255.)\n",
        "\n",
        "# Load data directory and turn it into batches\n",
        "train_data = train_datagen.flow_from_directory(train_dir,\n",
        "                                               target_size=(224,224),\n",
        "                                               batch_size=32,\n",
        "                                               class_mode=\"categorical\")\n",
        "test_data = test_datagen.flow_from_directory(test_dir,\n",
        "                                             target_size=(224,224),\n",
        "                                             batch_size=32,\n",
        "                                             class_mode=\"categorical\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TBPqbasEMkb8",
        "outputId": "3ed05f4d-40d6-40cb-efba-8e0666eae649"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 7500 images belonging to 10 classes.\n",
            "Found 2500 images belonging to 10 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "print(tf.__version__)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P6H40huKdT-1",
        "outputId": "0c49d970-a944-42ca-8db9-75310e09d904"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "2.15.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip uninstall tensorflow"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2IWnGYm5dfDE",
        "outputId": "b3dc8c83-8565-4c9c-c0f5-df17cbb7d080"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found existing installation: tensorflow 2.17.0\n",
            "Uninstalling tensorflow-2.17.0:\n",
            "  Would remove:\n",
            "    /usr/local/bin/import_pb_to_tensorboard\n",
            "    /usr/local/bin/saved_model_cli\n",
            "    /usr/local/bin/tensorboard\n",
            "    /usr/local/bin/tf_upgrade_v2\n",
            "    /usr/local/bin/tflite_convert\n",
            "    /usr/local/bin/toco\n",
            "    /usr/local/bin/toco_from_protos\n",
            "    /usr/local/lib/python3.10/dist-packages/tensorflow-2.17.0.dist-info/*\n",
            "    /usr/local/lib/python3.10/dist-packages/tensorflow/*\n",
            "Proceed (Y/n)? Y\n",
            "Y\n",
            "  Successfully uninstalled tensorflow-2.17.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install tensorflow==2.15.0"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "C1Fka-fmd1GP",
        "outputId": "2eff005e-d1f1-48c3-ae02-8e26dc84f202"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting tensorflow==2.15.0\n",
            "  Downloading tensorflow-2.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.4 kB)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=23.5.26 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (24.3.25)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (0.6.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (0.2.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (3.11.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (18.1.1)\n",
            "Collecting ml-dtypes~=0.2.0 (from tensorflow==2.15.0)\n",
            "  Downloading ml_dtypes-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n",
            "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (1.26.4)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (3.3.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (24.1)\n",
            "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (3.20.3)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (71.0.4)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (1.16.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (2.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (4.12.2)\n",
            "Collecting wrapt<1.15,>=1.11.0 (from tensorflow==2.15.0)\n",
            "  Downloading wrapt-1.14.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (0.37.1)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.10/dist-packages (from tensorflow==2.15.0) (1.64.1)\n",
            "Collecting tensorboard<2.16,>=2.15 (from tensorflow==2.15.0)\n",
            "  Downloading tensorboard-2.15.2-py3-none-any.whl.metadata (1.7 kB)\n",
            "Collecting tensorflow-estimator<2.16,>=2.15.0 (from tensorflow==2.15.0)\n",
            "  Downloading tensorflow_estimator-2.15.0-py2.py3-none-any.whl.metadata (1.3 kB)\n",
            "Collecting keras<2.16,>=2.15.0 (from tensorflow==2.15.0)\n",
            "  Downloading keras-2.15.0-py3-none-any.whl.metadata (2.4 kB)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from astunparse>=1.6.0->tensorflow==2.15.0) (0.43.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (2.27.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (1.2.1)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (3.6)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (2.31.0)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard<2.16,>=2.15->tensorflow==2.15.0) (3.0.3)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (5.4.0)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (0.4.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (1.3.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (2024.7.4)\n",
            "Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (2.1.5)\n",
            "Requirement already satisfied: pyasn1<0.7.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (0.6.0)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow==2.15.0) (3.2.2)\n",
            "Downloading tensorflow-2.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (475.2 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m475.2/475.2 MB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading keras-2.15.0-py3-none-any.whl (1.7 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m48.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading ml_dtypes-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m33.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading tensorboard-2.15.2-py3-none-any.whl (5.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m61.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading tensorflow_estimator-2.15.0-py2.py3-none-any.whl (441 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m442.0/442.0 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading wrapt-1.14.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (77 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: wrapt, tensorflow-estimator, ml-dtypes, keras, tensorboard, tensorflow\n",
            "  Attempting uninstall: wrapt\n",
            "    Found existing installation: wrapt 1.16.0\n",
            "    Uninstalling wrapt-1.16.0:\n",
            "      Successfully uninstalled wrapt-1.16.0\n",
            "  Attempting uninstall: ml-dtypes\n",
            "    Found existing installation: ml-dtypes 0.4.0\n",
            "    Uninstalling ml-dtypes-0.4.0:\n",
            "      Successfully uninstalled ml-dtypes-0.4.0\n",
            "  Attempting uninstall: keras\n",
            "    Found existing installation: keras 3.4.1\n",
            "    Uninstalling keras-3.4.1:\n",
            "      Successfully uninstalled keras-3.4.1\n",
            "  Attempting uninstall: tensorboard\n",
            "    Found existing installation: tensorboard 2.17.0\n",
            "    Uninstalling tensorboard-2.17.0:\n",
            "      Successfully uninstalled tensorboard-2.17.0\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "tensorstore 0.1.63 requires ml-dtypes>=0.3.1, but you have ml-dtypes 0.2.0 which is incompatible.\n",
            "tf-keras 2.17.0 requires tensorflow<2.18,>=2.17, but you have tensorflow 2.15.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed keras-2.15.0 ml-dtypes-0.2.0 tensorboard-2.15.2 tensorflow-2.15.0 tensorflow-estimator-2.15.0 wrapt-1.14.1\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "keras",
                  "ml_dtypes",
                  "tensorflow",
                  "wrapt"
                ]
              },
              "id": "b76bcca793e4405ba7d5a6cf4047944a"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 3. Create a model (start with a baseline)\n",
        "\n",
        "We've been talking a lot about the CNN explainer website...how about we just take their model (also on 10 classes) and use it for our problem ?"
      ],
      "metadata": {
        "id": "e_2fh9I9PfPU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten, Dense\n",
        "\n",
        "# Create our model (a clone of model_8, except to be multi-class)\n",
        "model_8 = Sequential([\n",
        "  Conv2D(10, 3, activation='relu', input_shape=(224,224,3)),\n",
        "  Conv2D(10, 3, activation='relu'),\n",
        "  MaxPool2D(),\n",
        "  Conv2D(10, 3, activation='relu'),\n",
        "  Conv2D(10, 3, activation='relu'),\n",
        "  MaxPool2D(),\n",
        "  Flatten(),\n",
        "  Dense(10, activation='softmax') # changed to have 10 neurons (same as number of classes) and 'softmax' activation\n",
        "])\n",
        "\n",
        "# Compile the model\n",
        "model_8.compile(loss=\"categorical_crossentropy\", # changed to categorical_crossentropy\n",
        "                optimizer=tf.keras.optimizers.Adam(),\n",
        "                metrics=[\"accuracy\"])"
      ],
      "metadata": {
        "id": "mYL0PUvIQLhI"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 4. Fit the model"
      ],
      "metadata": {
        "id": "_Nwic7d1U-rB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Fit the model\n",
        "history_8 = model_8.fit(train_data,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(test_data))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6fFhSfTfVRgB",
        "outputId": "ba29de82-6300-4daa-92b6-7c76d01ca57d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/5\n",
            "235/235 [==============================] - 478s 2s/step - loss: 2.1656 - accuracy: 0.1947 - val_loss: 2.0341 - val_accuracy: 0.2544\n",
            "Epoch 2/5\n",
            "235/235 [==============================] - 485s 2s/step - loss: 1.9534 - accuracy: 0.3160 - val_loss: 1.8563 - val_accuracy: 0.3480\n",
            "Epoch 3/5\n",
            "235/235 [==============================] - 523s 2s/step - loss: 1.5570 - accuracy: 0.4732 - val_loss: 1.9588 - val_accuracy: 0.3292\n",
            "Epoch 4/5\n",
            "235/235 [==============================] - 490s 2s/step - loss: 0.9115 - accuracy: 0.6983 - val_loss: 2.4744 - val_accuracy: 0.3032\n",
            "Epoch 5/5\n",
            "235/235 [==============================] - 491s 2s/step - loss: 0.3743 - accuracy: 0.8825 - val_loss: 3.3859 - val_accuracy: 0.2612\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 5. Evaluating the model"
      ],
      "metadata": {
        "id": "VV-2PW3xVxEB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluate on the test data\n",
        "model_8.evaluate(test_data)"
      ],
      "metadata": {
        "id": "MJhSLjS5W9Ct"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Check out the model's loss curves\n",
        "plot_loss_curves(history_8)"
      ],
      "metadata": {
        "id": "uv6Civm2Xwoa"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "What do these loss curves tell us ?\n",
        "\n",
        "Well...it seems our model is **overfitting** the training set quite badly...in other words, it's getting great results on the training data but fails to generalise well to unseen data and performs poorly on the test dataset."
      ],
      "metadata": {
        "id": "g72tP5aRYJf9"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 6. Adjust the model's hyperparameters (to beat the baseline/reduce overfitting)\n",
        "\n",
        "Due to its performance on the training data , its' clear that the model is learning something...\n",
        "\n",
        "However, it's not generalizing well to unseen data (overfitting).\n",
        "\n",
        "So, let's try and fix overfitting by...\n",
        "\n",
        "* **Get more data** - having more data gives a model more oppurtunity to learn diverse patterns...\n",
        "* **Simplify the model** - if our current model is overfitting the data, it may be too complicated of a model , one way to simplify the model is to reduce the number of hidden units in layers\n",
        "* **Use data augmentation** - data augmentation manipulates the training data in such a way to add more diversity to it (without altering the original data)\n",
        "* **Use transfer learning** - transfer learning leverages the patterns another model has learned on similar data to your own and allows you to use those patterns on your own dataset"
      ],
      "metadata": {
        "id": "lMQWHPClY3oV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# How about we try to simplify our model first ?\n",
        "# Let's try to remove 2 convolutional layers...\n",
        "model_9 = Sequential([\n",
        "    Conv2D(10,3, activation=\"relu\", input_shape=(224,224,3)),\n",
        "    MaxPool2D(),\n",
        "    Conv2D(10,3, activation=\"relu\"),\n",
        "    MaxPool2D(),\n",
        "    Flatten(),\n",
        "    Dense(10, activation=\"softmax\")\n",
        "])\n",
        "\n",
        "model_9.compile(loss=\"categorical_crossentropy\",\n",
        "                optimizer=tf.keras.optimizers.Adam(),\n",
        "                metrics=[\"accuracy\"])"
      ],
      "metadata": {
        "id": "L1JDVA9rZZCH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_9.summary()"
      ],
      "metadata": {
        "id": "CD1nJC6Jedhf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Fit the model with 2x conv layers removed\n",
        "history_9 = model_9.fit(train_data,\n",
        "                        epochs=5,\n",
        "                        steps_per_epoch=len(train_data),\n",
        "                        validation_data=test_data,\n",
        "                        validation_steps=len(test_data))"
      ],
      "metadata": {
        "id": "4XRjdfUVeg4F"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Check out the loss curves of model_9\n",
        "plot_loss_curves(history_9)"
      ],
      "metadata": {
        "id": "chuucU5ZfYTr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Looks like our simplifying the model experiment didn't work...\n",
        ". the accuracy went down and overfitting continued...\n",
        "\n",
        "How about we try data augmentation ??"
      ],
      "metadata": {
        "id": "v8j27fMvfzRe"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Trying to reduce overfitting using Data Augmentation\n",
        "\n",
        "Let's try and improve our model's results by using augmented training data...\n",
        "\n",
        "Ideally, we want to :     \n",
        "* Reduce overfitting (get the train and validation loss curves closer)\n",
        "* Improve validation accuracy"
      ],
      "metadata": {
        "id": "sCq1nph_g7Nc"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Create an augmented data generator instance\n",
        "train_datagen_augmented = ImageDataGenerator(rescale=1/255.,\n",
        "                                             rotation_range=0.2,\n",
        "                                             width_shift_range=0.2,\n",
        "                                             height_shift_range=0.2,\n",
        "                                             zoom_range=0.2,\n",
        "                                             horizontal_flip=True)\n",
        "train_data_augmented = train_datagen_augmented.flow_from_directory(train_dir,\n",
        "                                                                   target_size=(224,224),\n",
        "                                                                   batch_size=32,\n",
        "                                                                   class_mode=\"categorical\")"
      ],
      "metadata": {
        "id": "TyJFm1ithwCL"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Let's create another model but this time we will fit it on the augmented training data\n",
        "model_10 = tf.keras.models.clone_model(model_8)\n",
        "\n",
        "# Compile the cloned model (using the same setup as previous models)\n",
        "model_10.compile(loss=\"categorical_crossentropy\",\n",
        "                 optimizer=tf.keras.optimizers.Adam(),\n",
        "                 metrics=[\"accuracy\"])"
      ],
      "metadata": {
        "id": "7VoAAvHCjRco"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Fit the model\n",
        "history_10 = model_10.fit(train_data_augmented,\n",
        "                          epochs=5,\n",
        "                          steps_per_epoch=len(train_data_augmented),\n",
        "                          validation_data=test_data,\n",
        "                          validation_steps=len(test_data))"
      ],
      "metadata": {
        "id": "mpAcOEZZkmp5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_8.evaluate(test_data)"
      ],
      "metadata": {
        "id": "uxm0k6UTl42S"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model_10.evaluate(test_data)"
      ],
      "metadata": {
        "id": "muaKUmO8mEWg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Check out our model trained on augmented data's loss curves\n",
        "plot_loss_curves(history_10)"
      ],
      "metadata": {
        "id": "DGpnccg5mJE3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Woah! That looks much better , the loss curves are much closer to each other than the baseline model and they look like they are heading in the right direction (certainly not the wrong direction) so if we were to train longer , we might see further improvements."
      ],
      "metadata": {
        "id": "M8i6bDAtmXoD"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### 7. Repeat until satisfied\n",
        "\n",
        "We could keep going here... continually trying to bring our loss curves closer together and trying to improve the validation test/accuracy.\n",
        "\n",
        "How ?\n",
        "\n",
        "By running lots of experiments :             \n",
        "- restructuring our model's architecture (increasing layers/hidden units)\n",
        "- adjusting the learning rate\n",
        "- try different methods of data augmentation (adjust hyperparameters in our ImageDataGenerator instance)\n",
        "- training for longer\n",
        "- try **transfer learning**"
      ],
      "metadata": {
        "id": "n9B2cb1SngLu"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Making a prediction with our trained model\n",
        "\n",
        "Let's use our trained model to make some predictions on our own custom images !"
      ],
      "metadata": {
        "id": "QKqVrFMYnlu3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# let's see our classes\n",
        "class_names"
      ],
      "metadata": {
        "id": "NJkLFhwYGYCa"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Downloading some custom images\n",
        "We uploaded our images in Google Colab , so it needs to be uploaded every time in order to predict on them"
      ],
      "metadata": {
        "id": "QaA9cg9tHBTe"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Reconfig pred and plot function to work with multi-class images\n",
        "def pred_and_plot(model, filename, class_names=class_names):\n",
        "  \"\"\"\n",
        "  Imports an image located at filename, makes a prediction with model and plots the image with the predicted class as the title.\n",
        "  \"\"\"\n",
        "  # Import the target image and preprocess it\n",
        "  img = load_and_pred_image(filename)\n",
        "\n",
        "  # Make a prediction\n",
        "  pred = model.predict(tf.expand_dims(img, axis=0))\n",
        "\n",
        "  # Add in logic for multi-class & get pred_class name\n",
        "  if len(pred[0]) > 1:\n",
        "    pred_class = class_names[tf.argmax(pred[0])]\n",
        "  else:\n",
        "    pred_class = class_names[int(tf.round(pred))]\n",
        "\n",
        "  # Plot the image and predicted class\n",
        "  plt.imshow(img)\n",
        "  plt.title(f\"Prediction: {pred_class}\")\n",
        "  plt.axis(False);"
      ],
      "metadata": {
        "id": "oQcaTYYdQQZQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Make a prediction using model_10\n",
        "pred_and_plot(model=model_10,\n",
        "              filename=\"sundae.jpg\",\n",
        "              class_names=class_names)"
      ],
      "metadata": {
        "id": "cdP8xfe3NAh_"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Make a prediction using model_10\n",
        "pred_and_plot(model=model_10,\n",
        "              filename=\"sushi.jpg\",\n",
        "              class_names=class_names)"
      ],
      "metadata": {
        "id": "uZMd8QykSME5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Our model might not perform very well on our custom images but this is because it only achieved ~39% accuracy on the test data. So we can expect it to function quite poorly at other unseen data."
      ],
      "metadata": {
        "id": "TpireQmsSfz4"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Saving and loading our Model"
      ],
      "metadata": {
        "id": "0NRCdTf0TO5_"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Save a model\n",
        "model_10.save(\"saved_trained_model_10\")"
      ],
      "metadata": {
        "id": "hU1pbv2JZM9u"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load in a trained model and evaluate it\n",
        "loaded_model_10 = tf.keras.models.load_model(\"saved_trained_model_10\")\n",
        "loaded_model_10.evaluate(test_data)"
      ],
      "metadata": {
        "id": "kQDudnLZZcm6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Compare our loaded model to our existing model\n",
        "model_10.evaluate()"
      ],
      "metadata": {
        "id": "if3F5DmaZ226"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "y5MBLl-qaBS5"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}