{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "markdown", "source": [ "## Import Libraries" ], "metadata": { "id": "1g7KAX4bxvZz" } }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "dqyHUaNpXoeE" }, "outputs": [], "source": [ "import tensorflow as tf\n", "from tensorflow import keras\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import confusion_matrix, classification_report\n", "import seaborn as sns\n", "from tensorflow.keras import layers, models, optimizers" ] }, { "cell_type": "markdown", "source": [ "## Dataset Description" ], "metadata": { "id": "gxjZRGE_xzOB" } }, { "cell_type": "code", "source": [ "tf.keras.datasets.cifar10.load_data()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "GDUaiZNUYU6h", "outputId": "4fd23f53-d27c-4211-a7e1-2c48bf69ac3d" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "((array([[[[ 59, 62, 63],\n", " [ 43, 46, 45],\n", " [ 50, 48, 43],\n", " ...,\n", " [158, 132, 108],\n", " [152, 125, 102],\n", " [148, 124, 103]],\n", " \n", " [[ 16, 20, 20],\n", " [ 0, 0, 0],\n", " [ 18, 8, 0],\n", " ...,\n", " [123, 88, 55],\n", " [119, 83, 50],\n", " [122, 87, 57]],\n", " \n", " [[ 25, 24, 21],\n", " [ 16, 7, 0],\n", " [ 49, 27, 8],\n", " ...,\n", " [118, 84, 50],\n", " [120, 84, 50],\n", " [109, 73, 42]],\n", " \n", " ...,\n", " \n", " [[208, 170, 96],\n", " [201, 153, 34],\n", " [198, 161, 26],\n", " ...,\n", " [160, 133, 70],\n", " [ 56, 31, 7],\n", " [ 53, 34, 20]],\n", " \n", " [[180, 139, 96],\n", " [173, 123, 42],\n", " [186, 144, 30],\n", " ...,\n", " [184, 148, 94],\n", " [ 97, 62, 34],\n", " [ 83, 53, 34]],\n", " \n", " [[177, 144, 116],\n", " [168, 129, 94],\n", " [179, 142, 87],\n", " ...,\n", " [216, 184, 140],\n", " [151, 118, 84],\n", " [123, 92, 72]]],\n", " \n", " \n", " [[[154, 177, 187],\n", " [126, 137, 136],\n", " [105, 104, 95],\n", " ...,\n", " [ 91, 95, 71],\n", " [ 87, 90, 71],\n", " [ 79, 81, 70]],\n", " \n", " [[140, 160, 169],\n", " [145, 153, 154],\n", " [125, 125, 118],\n", " ...,\n", " [ 96, 99, 78],\n", " [ 77, 80, 62],\n", " [ 71, 73, 61]],\n", " \n", " [[140, 155, 164],\n", " [139, 146, 149],\n", " [115, 115, 112],\n", " ...,\n", " [ 79, 82, 64],\n", " [ 68, 70, 55],\n", " [ 67, 69, 55]],\n", " \n", " ...,\n", " \n", " [[175, 167, 166],\n", " [156, 154, 160],\n", " [154, 160, 170],\n", " ...,\n", " [ 42, 34, 36],\n", " [ 61, 53, 57],\n", " [ 93, 83, 91]],\n", " \n", " [[165, 154, 128],\n", " [156, 152, 130],\n", " [159, 161, 142],\n", " ...,\n", " [103, 93, 96],\n", " [123, 114, 120],\n", " [131, 121, 131]],\n", " \n", " [[163, 148, 120],\n", " [158, 148, 122],\n", " [163, 156, 133],\n", " ...,\n", " [143, 133, 139],\n", " [143, 134, 142],\n", " [143, 133, 144]]],\n", " \n", " \n", " [[[255, 255, 255],\n", " [253, 253, 253],\n", " [253, 253, 253],\n", " ...,\n", " [253, 253, 253],\n", " [253, 253, 253],\n", " [253, 253, 253]],\n", " \n", " [[255, 255, 255],\n", " [255, 255, 255],\n", " [255, 255, 255],\n", " ...,\n", " [255, 255, 255],\n", " [255, 255, 255],\n", " [255, 255, 255]],\n", " \n", " [[255, 255, 255],\n", " [254, 254, 254],\n", " [254, 254, 254],\n", " ...,\n", " [254, 254, 254],\n", " [254, 254, 254],\n", " [254, 254, 254]],\n", " \n", " ...,\n", " \n", " [[113, 120, 112],\n", " [111, 118, 111],\n", " [105, 112, 106],\n", " ...,\n", " [ 72, 81, 80],\n", " [ 72, 80, 79],\n", " [ 72, 80, 79]],\n", " \n", " [[111, 118, 110],\n", " [104, 111, 104],\n", " [ 99, 106, 98],\n", " ...,\n", " [ 68, 75, 73],\n", " [ 70, 76, 75],\n", " [ 78, 84, 82]],\n", " \n", " [[106, 113, 105],\n", " [ 99, 106, 98],\n", " [ 95, 102, 94],\n", " ...,\n", " [ 78, 85, 83],\n", " [ 79, 85, 83],\n", " [ 80, 86, 84]]],\n", " \n", " \n", " ...,\n", " \n", " \n", " [[[ 35, 178, 235],\n", " [ 40, 176, 239],\n", " [ 42, 176, 241],\n", " ...,\n", " [ 99, 177, 219],\n", " [ 79, 147, 197],\n", " [ 89, 148, 189]],\n", " \n", " [[ 57, 182, 234],\n", " [ 44, 184, 250],\n", " [ 50, 183, 240],\n", " ...,\n", " [156, 182, 200],\n", " [141, 177, 206],\n", " [116, 149, 175]],\n", " \n", " [[ 98, 197, 237],\n", " [ 64, 189, 252],\n", " [ 69, 192, 245],\n", " ...,\n", " [188, 195, 206],\n", " [119, 135, 147],\n", " [ 61, 79, 90]],\n", " \n", " ...,\n", " \n", " [[ 73, 79, 77],\n", " [ 53, 63, 68],\n", " [ 54, 68, 80],\n", " ...,\n", " [ 17, 40, 64],\n", " [ 21, 36, 51],\n", " [ 33, 48, 49]],\n", " \n", " [[ 61, 68, 75],\n", " [ 55, 70, 86],\n", " [ 57, 79, 103],\n", " ...,\n", " [ 24, 48, 72],\n", " [ 17, 35, 53],\n", " [ 7, 23, 32]],\n", " \n", " [[ 44, 56, 73],\n", " [ 46, 66, 88],\n", " [ 49, 77, 105],\n", " ...,\n", " [ 27, 52, 77],\n", " [ 21, 43, 66],\n", " [ 12, 31, 50]]],\n", " \n", " \n", " [[[189, 211, 240],\n", " [186, 208, 236],\n", " [185, 207, 235],\n", " ...,\n", " [175, 195, 224],\n", " [172, 194, 222],\n", " [169, 194, 220]],\n", " \n", " [[194, 210, 239],\n", " [191, 207, 236],\n", " [190, 206, 235],\n", " ...,\n", " [173, 192, 220],\n", " [171, 191, 218],\n", " [167, 190, 216]],\n", " \n", " [[208, 219, 244],\n", " [205, 216, 240],\n", " [204, 215, 239],\n", " ...,\n", " [175, 191, 217],\n", " [172, 190, 216],\n", " [169, 191, 215]],\n", " \n", " ...,\n", " \n", " [[207, 199, 181],\n", " [203, 195, 175],\n", " [203, 196, 173],\n", " ...,\n", " [135, 132, 127],\n", " [162, 158, 150],\n", " [168, 163, 151]],\n", " \n", " [[198, 190, 170],\n", " [189, 181, 159],\n", " [180, 172, 147],\n", " ...,\n", " [178, 171, 160],\n", " [175, 169, 156],\n", " [175, 169, 154]],\n", " \n", " [[198, 189, 173],\n", " [189, 181, 162],\n", " [178, 170, 149],\n", " ...,\n", " [195, 184, 169],\n", " [196, 189, 171],\n", " [195, 190, 171]]],\n", " \n", " \n", " [[[229, 229, 239],\n", " [236, 237, 247],\n", " [234, 236, 247],\n", " ...,\n", " [217, 219, 233],\n", " [221, 223, 234],\n", " [222, 223, 233]],\n", " \n", " [[222, 221, 229],\n", " [239, 239, 249],\n", " [233, 234, 246],\n", " ...,\n", " [223, 223, 236],\n", " [227, 228, 238],\n", " [210, 211, 220]],\n", " \n", " [[213, 206, 211],\n", " [234, 232, 239],\n", " [231, 233, 244],\n", " ...,\n", " [220, 220, 232],\n", " [220, 219, 232],\n", " [202, 203, 215]],\n", " \n", " ...,\n", " \n", " [[150, 143, 135],\n", " [140, 135, 127],\n", " [132, 127, 120],\n", " ...,\n", " [224, 222, 218],\n", " [230, 228, 225],\n", " [241, 241, 238]],\n", " \n", " [[137, 132, 126],\n", " [130, 127, 120],\n", " [125, 121, 115],\n", " ...,\n", " [181, 180, 178],\n", " [202, 201, 198],\n", " [212, 211, 207]],\n", " \n", " [[122, 119, 114],\n", " [118, 116, 110],\n", " [120, 116, 111],\n", " ...,\n", " [179, 177, 173],\n", " [164, 164, 162],\n", " [163, 163, 161]]]], dtype=uint8),\n", " array([[6],\n", " [9],\n", " [9],\n", " ...,\n", " [9],\n", " [1],\n", " [1]], dtype=uint8)),\n", " (array([[[[158, 112, 49],\n", " [159, 111, 47],\n", " [165, 116, 51],\n", " ...,\n", " [137, 95, 36],\n", " [126, 91, 36],\n", " [116, 85, 33]],\n", " \n", " [[152, 112, 51],\n", " [151, 110, 40],\n", " [159, 114, 45],\n", " ...,\n", " [136, 95, 31],\n", " [125, 91, 32],\n", " [119, 88, 34]],\n", " \n", " [[151, 110, 47],\n", " [151, 109, 33],\n", " [158, 111, 36],\n", " ...,\n", " [139, 98, 34],\n", " [130, 95, 34],\n", " [120, 89, 33]],\n", " \n", " ...,\n", " \n", " [[ 68, 124, 177],\n", " [ 42, 100, 148],\n", " [ 31, 88, 137],\n", " ...,\n", " [ 38, 97, 146],\n", " [ 13, 64, 108],\n", " [ 40, 85, 127]],\n", " \n", " [[ 61, 116, 168],\n", " [ 49, 102, 148],\n", " [ 35, 85, 132],\n", " ...,\n", " [ 26, 82, 130],\n", " [ 29, 82, 126],\n", " [ 20, 64, 107]],\n", " \n", " [[ 54, 107, 160],\n", " [ 56, 105, 149],\n", " [ 45, 89, 132],\n", " ...,\n", " [ 24, 77, 124],\n", " [ 34, 84, 129],\n", " [ 21, 67, 110]]],\n", " \n", " \n", " [[[235, 235, 235],\n", " [231, 231, 231],\n", " [232, 232, 232],\n", " ...,\n", " [233, 233, 233],\n", " [233, 233, 233],\n", " [232, 232, 232]],\n", " \n", " [[238, 238, 238],\n", " [235, 235, 235],\n", " [235, 235, 235],\n", " ...,\n", " [236, 236, 236],\n", " [236, 236, 236],\n", " [235, 235, 235]],\n", " \n", " [[237, 237, 237],\n", " [234, 234, 234],\n", " [234, 234, 234],\n", " ...,\n", " [235, 235, 235],\n", " [235, 235, 235],\n", " [234, 234, 234]],\n", " \n", " ...,\n", " \n", " [[ 87, 99, 89],\n", " [ 43, 51, 37],\n", " [ 19, 23, 11],\n", " ...,\n", " [169, 184, 179],\n", " [182, 197, 193],\n", " [188, 202, 201]],\n", " \n", " [[ 82, 96, 82],\n", " [ 46, 57, 36],\n", " [ 36, 44, 22],\n", " ...,\n", " [174, 189, 183],\n", " [185, 200, 196],\n", " [187, 202, 200]],\n", " \n", " [[ 85, 101, 83],\n", " [ 62, 75, 48],\n", " [ 58, 67, 38],\n", " ...,\n", " [168, 183, 178],\n", " [180, 195, 191],\n", " [186, 200, 199]]],\n", " \n", " \n", " [[[158, 190, 222],\n", " [158, 187, 218],\n", " [139, 166, 194],\n", " ...,\n", " [228, 231, 234],\n", " [237, 239, 243],\n", " [238, 241, 246]],\n", " \n", " [[170, 200, 229],\n", " [172, 199, 226],\n", " [151, 176, 201],\n", " ...,\n", " [232, 232, 236],\n", " [246, 246, 250],\n", " [246, 247, 251]],\n", " \n", " [[174, 201, 225],\n", " [176, 200, 222],\n", " [157, 179, 199],\n", " ...,\n", " [230, 229, 232],\n", " [250, 249, 251],\n", " [245, 244, 247]],\n", " \n", " ...,\n", " \n", " [[ 31, 40, 45],\n", " [ 30, 39, 44],\n", " [ 26, 35, 40],\n", " ...,\n", " [ 37, 40, 46],\n", " [ 9, 13, 14],\n", " [ 4, 7, 5]],\n", " \n", " [[ 23, 34, 39],\n", " [ 27, 38, 43],\n", " [ 25, 36, 41],\n", " ...,\n", " [ 19, 20, 24],\n", " [ 4, 6, 3],\n", " [ 5, 7, 3]],\n", " \n", " [[ 28, 41, 47],\n", " [ 30, 43, 50],\n", " [ 32, 45, 52],\n", " ...,\n", " [ 5, 6, 8],\n", " [ 4, 5, 3],\n", " [ 7, 8, 7]]],\n", " \n", " \n", " ...,\n", " \n", " \n", " [[[ 20, 15, 12],\n", " [ 19, 14, 11],\n", " [ 15, 14, 11],\n", " ...,\n", " [ 10, 9, 7],\n", " [ 12, 11, 9],\n", " [ 13, 12, 10]],\n", " \n", " [[ 21, 16, 13],\n", " [ 20, 16, 13],\n", " [ 18, 17, 12],\n", " ...,\n", " [ 10, 9, 7],\n", " [ 10, 9, 7],\n", " [ 12, 11, 9]],\n", " \n", " [[ 21, 16, 13],\n", " [ 21, 17, 12],\n", " [ 20, 18, 11],\n", " ...,\n", " [ 12, 11, 9],\n", " [ 12, 11, 9],\n", " [ 13, 12, 10]],\n", " \n", " ...,\n", " \n", " [[ 33, 25, 13],\n", " [ 34, 26, 15],\n", " [ 34, 26, 15],\n", " ...,\n", " [ 28, 25, 52],\n", " [ 29, 25, 58],\n", " [ 23, 20, 42]],\n", " \n", " [[ 33, 25, 14],\n", " [ 34, 26, 15],\n", " [ 34, 26, 15],\n", " ...,\n", " [ 27, 24, 52],\n", " [ 27, 24, 56],\n", " [ 25, 22, 47]],\n", " \n", " [[ 31, 23, 12],\n", " [ 32, 24, 13],\n", " [ 33, 25, 14],\n", " ...,\n", " [ 24, 23, 50],\n", " [ 26, 23, 53],\n", " [ 25, 20, 47]]],\n", " \n", " \n", " [[[ 25, 40, 12],\n", " [ 15, 36, 3],\n", " [ 23, 41, 18],\n", " ...,\n", " [ 61, 82, 78],\n", " [ 92, 113, 112],\n", " [ 75, 89, 92]],\n", " \n", " [[ 12, 25, 6],\n", " [ 20, 37, 7],\n", " [ 24, 36, 15],\n", " ...,\n", " [115, 134, 138],\n", " [149, 168, 177],\n", " [104, 117, 131]],\n", " \n", " [[ 12, 25, 11],\n", " [ 15, 29, 6],\n", " [ 34, 40, 24],\n", " ...,\n", " [154, 172, 182],\n", " [157, 175, 192],\n", " [116, 129, 151]],\n", " \n", " ...,\n", " \n", " [[100, 129, 81],\n", " [103, 132, 84],\n", " [104, 134, 86],\n", " ...,\n", " [ 97, 128, 84],\n", " [ 98, 126, 84],\n", " [ 91, 121, 79]],\n", " \n", " [[103, 132, 83],\n", " [104, 131, 83],\n", " [107, 135, 87],\n", " ...,\n", " [101, 132, 87],\n", " [ 99, 127, 84],\n", " [ 92, 121, 79]],\n", " \n", " [[ 95, 126, 78],\n", " [ 95, 123, 76],\n", " [101, 128, 81],\n", " ...,\n", " [ 93, 124, 80],\n", " [ 95, 123, 81],\n", " [ 92, 120, 80]]],\n", " \n", " \n", " [[[ 73, 78, 75],\n", " [ 98, 103, 113],\n", " [ 99, 106, 114],\n", " ...,\n", " [135, 150, 152],\n", " [135, 149, 154],\n", " [203, 215, 223]],\n", " \n", " [[ 69, 73, 70],\n", " [ 84, 89, 97],\n", " [ 68, 75, 81],\n", " ...,\n", " [ 85, 95, 89],\n", " [ 71, 82, 80],\n", " [120, 133, 135]],\n", " \n", " [[ 69, 73, 70],\n", " [ 90, 95, 100],\n", " [ 62, 71, 74],\n", " ...,\n", " [ 74, 81, 70],\n", " [ 53, 62, 54],\n", " [ 62, 74, 69]],\n", " \n", " ...,\n", " \n", " [[123, 128, 96],\n", " [132, 132, 102],\n", " [129, 128, 100],\n", " ...,\n", " [108, 107, 88],\n", " [ 62, 60, 55],\n", " [ 27, 27, 28]],\n", " \n", " [[115, 121, 91],\n", " [123, 124, 95],\n", " [129, 126, 99],\n", " ...,\n", " [115, 116, 94],\n", " [ 66, 65, 59],\n", " [ 27, 27, 27]],\n", " \n", " [[116, 120, 90],\n", " [121, 122, 94],\n", " [129, 128, 101],\n", " ...,\n", " [116, 115, 94],\n", " [ 68, 65, 58],\n", " [ 27, 26, 26]]]], dtype=uint8),\n", " array([[3],\n", " [8],\n", " [8],\n", " ...,\n", " [5],\n", " [1],\n", " [7]], dtype=uint8)))" ] }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()" ], "metadata": { "id": "aDypGyh3YX8g" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "print(\"Training set:\", x_train.shape, y_train.shape)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "dTvsOd_tYcwn", "outputId": "257951d7-62d7-41a4-91f3-e61ae991b316" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Training set: (50000, 32, 32, 3) (50000, 1)\n" ] } ] }, { "cell_type": "code", "source": [ "print(\"Test set:\", x_test.shape, y_test.shape)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Yd1yAmgmaJO2", "outputId": "232d4ea7-9d0c-47ab-d720-8751fd89e3d1" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Test set: (10000, 32, 32, 3) (10000, 1)\n" ] } ] }, { "cell_type": "markdown", "source": [ "## Data Pre-processing" ], "metadata": { "id": "7vLsPeboaM6P" } }, { "cell_type": "code", "source": [ "x_train = x_train.astype('float32') / 255.0\n", "x_test = x_test.astype('float32') / 255.0\n", "\n", "y_train = keras.utils.to_categorical(y_train, 10)\n", "y_test = keras.utils.to_categorical(y_test, 10)" ], "metadata": { "id": "hDUQtIDPaK6W" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "class_names = ['airplane','automobile','bird','cat','deer',\n", " 'dog','frog','horse','ship','truck']\n", "\n", "plt.figure(figsize=(10,8))\n", "for i in range(5):\n", " plt.subplot(1,5,i+1)\n", " plt.imshow(x_train[i])\n", " plt.title(class_names[np.argmax(y_train[i])])\n", " plt.axis('off')\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 192 }, "id": "hHYMCE8QaMmv", "outputId": "195c638f-0cfa-4d24-f52b-d8b4891a593e" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "## Build the CNN Model" ], "metadata": { "id": "9FpW1_oiaXa2" } }, { "cell_type": "code", "source": [ "model = models.Sequential([\n", " layers.Conv2D(32, (3,3), activation='relu', padding='same', input_shape=(32,32,3)),\n", " layers.BatchNormalization(),\n", " layers.MaxPooling2D((2,2)),\n", " layers.Dropout(0.25),\n", "\n", " layers.Conv2D(64, (3,3), activation='relu', padding='same'),\n", " layers.BatchNormalization(),\n", " layers.MaxPooling2D((2,2)),\n", " layers.Dropout(0.25),\n", "\n", " layers.Conv2D(128, (3,3), activation='relu', padding='same'),\n", " layers.BatchNormalization(),\n", " layers.MaxPooling2D((2,2)),\n", " layers.Dropout(0.25),\n", "\n", " layers.Flatten(),\n", " layers.Dense(128, activation='relu'),\n", " layers.Dropout(0.5),\n", " layers.Dense(10, activation='softmax')\n", "])\n", "\n", "model.summary()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 800 }, "id": "TdQVL1RgaMkO", "outputId": "f0b655ec-d550-4d35-f19b-d46adf0224fc" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1mModel: \"sequential\"\u001b[0m\n" ], "text/html": [ "
Model: \"sequential\"\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ batch_normalization │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n", "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ batch_normalization_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │\n", "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ batch_normalization_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │\n", "│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2048\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m262,272\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ], "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (Conv2D)                 │ (None, 32, 32, 32)     │           896 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization             │ (None, 32, 32, 32)     │           128 │\n",
              "│ (BatchNormalization)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (MaxPooling2D)    │ (None, 16, 16, 32)     │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (Dropout)               │ (None, 16, 16, 32)     │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (Conv2D)               │ (None, 16, 16, 64)     │        18,496 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_1           │ (None, 16, 16, 64)     │           256 │\n",
              "│ (BatchNormalization)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 8, 8, 64)       │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (Dropout)             │ (None, 8, 8, 64)       │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (Conv2D)               │ (None, 8, 8, 128)      │        73,856 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_2           │ (None, 8, 8, 128)      │           512 │\n",
              "│ (BatchNormalization)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (MaxPooling2D)  │ (None, 4, 4, 128)      │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_2 (Dropout)             │ (None, 4, 4, 128)      │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (Flatten)               │ (None, 2048)           │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (Dense)                   │ (None, 128)            │       262,272 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (Dropout)             │ (None, 128)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (Dense)                 │ (None, 10)             │         1,290 │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m357,706\u001b[0m (1.36 MB)\n" ], "text/html": [ "
 Total params: 357,706 (1.36 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m357,258\u001b[0m (1.36 MB)\n" ], "text/html": [ "
 Trainable params: 357,258 (1.36 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m448\u001b[0m (1.75 KB)\n" ], "text/html": [ "
 Non-trainable params: 448 (1.75 KB)\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "## Compile the Model" ], "metadata": { "id": "VE1OvMYuaerG" } }, { "cell_type": "code", "source": [ "model.compile(optimizer='adam',\n", " loss='categorical_crossentropy',\n", " metrics=['accuracy'])" ], "metadata": { "id": "t75LqjzeaMhm" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "## Train the Model" ], "metadata": { "id": "f9rh3BOoajsG" } }, { "cell_type": "code", "source": [ "history = model.fit(\n", " x_train, y_train,\n", " epochs=20,\n", " batch_size=64,\n", " validation_data=(x_test, y_test),\n", " verbose=1\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "55h7ASJjajiO", "outputId": "c8342e6b-6ea0-4822-b3b5-5c1dc2d796dc" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 14ms/step - accuracy: 0.2617 - loss: 2.1067 - val_accuracy: 0.4695 - val_loss: 1.5008\n", "Epoch 2/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.4530 - loss: 1.4956 - val_accuracy: 0.5844 - val_loss: 1.1930\n", "Epoch 3/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 6ms/step - accuracy: 0.5434 - loss: 1.2858 - val_accuracy: 0.5330 - val_loss: 1.4171\n", "Epoch 4/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 6ms/step - accuracy: 0.5856 - loss: 1.1767 - val_accuracy: 0.6409 - val_loss: 1.0039\n", "Epoch 5/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.6167 - loss: 1.0971 - val_accuracy: 0.6936 - val_loss: 0.8936\n", "Epoch 6/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 6ms/step - accuracy: 0.6453 - loss: 1.0277 - val_accuracy: 0.6976 - val_loss: 0.8768\n", "Epoch 7/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.6578 - loss: 0.9850 - val_accuracy: 0.6988 - val_loss: 0.8654\n", "Epoch 8/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 5ms/step - accuracy: 0.6723 - loss: 0.9425 - val_accuracy: 0.7251 - val_loss: 0.8058\n", "Epoch 9/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 6ms/step - accuracy: 0.6872 - loss: 0.9030 - val_accuracy: 0.7167 - val_loss: 0.8292\n", "Epoch 10/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.6973 - loss: 0.8761 - val_accuracy: 0.7095 - val_loss: 0.8480\n", "Epoch 11/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 6ms/step - accuracy: 0.7062 - loss: 0.8498 - val_accuracy: 0.7514 - val_loss: 0.7189\n", "Epoch 12/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 6ms/step - accuracy: 0.7162 - loss: 0.8203 - val_accuracy: 0.6858 - val_loss: 0.9418\n", "Epoch 13/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.7201 - loss: 0.8009 - val_accuracy: 0.7670 - val_loss: 0.6858\n", "Epoch 14/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 6ms/step - accuracy: 0.7277 - loss: 0.7836 - val_accuracy: 0.7643 - val_loss: 0.6974\n", "Epoch 15/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.7358 - loss: 0.7655 - val_accuracy: 0.7727 - val_loss: 0.6713\n", "Epoch 16/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.7408 - loss: 0.7451 - val_accuracy: 0.7529 - val_loss: 0.7166\n", "Epoch 17/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 6ms/step - accuracy: 0.7496 - loss: 0.7209 - val_accuracy: 0.7326 - val_loss: 0.8042\n", "Epoch 18/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.7573 - loss: 0.7077 - val_accuracy: 0.7598 - val_loss: 0.7368\n", "Epoch 19/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 6ms/step - accuracy: 0.7587 - loss: 0.6980 - val_accuracy: 0.7159 - val_loss: 0.8771\n", "Epoch 20/20\n", "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 7ms/step - accuracy: 0.7602 - loss: 0.6919 - val_accuracy: 0.7369 - val_loss: 0.8017\n" ] } ] }, { "cell_type": "markdown", "source": [ "## Evaluate and Visualise Results\n" ], "metadata": { "id": "XP4psg7ca92d" } }, { "cell_type": "code", "source": [ "test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)\n", "print(f\"\\nTest Accuracy: {test_acc:.3f}\")\n", "\n", "plt.figure(figsize=(12,4))\n", "plt.subplot(1,2,1)\n", "plt.plot(history.history['accuracy'], label='Train Accuracy')\n", "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n", "plt.title('Model Accuracy')\n", "plt.xlabel('Epoch'); plt.ylabel('Accuracy'); plt.legend()\n", "\n", "plt.subplot(1,2,2)\n", "plt.plot(history.history['loss'], label='Train Loss')\n", "plt.plot(history.history['val_loss'], label='Validation Loss')\n", "plt.title('Model Loss')\n", "plt.xlabel('Epoch'); plt.ylabel('Loss'); plt.legend()\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 462 }, "id": "8xNAem9Bajf4", "outputId": "d315769a-cbc2-4912-caba-afdf557d6f5b" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "313/313 - 1s - 2ms/step - accuracy: 0.7369 - loss: 0.8017\n", "\n", "Test Accuracy: 0.737\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "markdown", "source": [ "## Confusion Matrix & Classification Report" ], "metadata": { "id": "DWA8ULRYbPw2" } }, { "cell_type": "code", "source": [ "y_pred = np.argmax(model.predict(x_test), axis=1)\n", "y_true = np.argmax(y_test, axis=1)\n", "\n", "cm = confusion_matrix(y_true, y_pred)\n", "plt.figure(figsize=(10,8))\n", "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n", " xticklabels=class_names, yticklabels=class_names)\n", "plt.xlabel('Predicted'); plt.ylabel('True'); plt.title('Confusion Matrix')\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 800 }, "id": "bG2Fph8FajdX", "outputId": "e2973b72-ddb4-4b53-c72c-573b696014b3" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "print(\"Classification Report:\\n\")\n", "print(classification_report(y_true, y_pred, target_names=class_names))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "gXVBVOe4aMe3", "outputId": "611a3843-56f7-46b3-ba6d-b3b783a4ab52" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Classification Report:\n", "\n", " precision recall f1-score support\n", "\n", " airplane 0.87 0.73 0.80 1000\n", " automobile 0.89 0.88 0.88 1000\n", " bird 0.63 0.69 0.66 1000\n", " cat 0.55 0.59 0.57 1000\n", " deer 0.65 0.73 0.69 1000\n", " dog 0.71 0.53 0.61 1000\n", " frog 0.59 0.92 0.72 1000\n", " horse 0.92 0.63 0.75 1000\n", " ship 0.83 0.90 0.86 1000\n", " truck 0.95 0.76 0.84 1000\n", "\n", " accuracy 0.74 10000\n", " macro avg 0.76 0.74 0.74 10000\n", "weighted avg 0.76 0.74 0.74 10000\n", "\n" ] } ] }, { "cell_type": "markdown", "source": [ "## Hyperparameter" ], "metadata": { "id": "HOqBELo4oW6S" } }, { "cell_type": "code", "source": [ "batch_sizes = [32, 64, 128]\n", "learning_rates = [0.001, 0.0005, 0.0001]\n", "dropout_rates = [0.25, 0.3, 0.4]\n", "\n", "best_acc = 0\n", "best_config = None\n", "\n", "for batch in batch_sizes:\n", " for lr in learning_rates:\n", " for dr in dropout_rates:\n", " print(f\"\\nTraining with Batch={batch}, LR={lr}, Dropout={dr}\")\n", "\n", " model = models.Sequential()\n", " model.add(layers.Conv2D(32, (3,3), activation='relu', padding='same', input_shape=(32,32,3)))\n", " model.add(layers.BatchNormalization())\n", " model.add(layers.MaxPooling2D((2,2)))\n", " model.add(layers.Dropout(dr))\n", "\n", " model.add(layers.Conv2D(64, (3,3), activation='relu', padding='same'))\n", " model.add(layers.BatchNormalization())\n", " model.add(layers.MaxPooling2D((2,2)))\n", " model.add(layers.Dropout(dr))\n", "\n", " model.add(layers.Conv2D(128, (3,3), activation='relu', padding='same'))\n", " model.add(layers.BatchNormalization())\n", " model.add(layers.MaxPooling2D((2,2)))\n", " model.add(layers.Dropout(dr))\n", "\n", " model.add(layers.Flatten())\n", " model.add(layers.Dense(128, activation='relu'))\n", " model.add(layers.Dropout(0.5))\n", " model.add(layers.Dense(10, activation='softmax'))\n", "\n", " optimizer = optimizers.Adam(learning_rate=lr)\n", " model.compile(optimizer=optimizer,\n", " loss='categorical_crossentropy',\n", " metrics=['accuracy'])\n", "\n", " history = model.fit(\n", " x_train, y_train,\n", " epochs=10,\n", " batch_size=batch,\n", " validation_data=(x_test, y_test),\n", " verbose=0\n", " )\n", "\n", " val_acc = max(history.history['val_accuracy'])\n", " print(f\"Validation Accuracy: {val_acc:.4f}\")\n", "\n", " if val_acc > best_acc:\n", " best_acc = val_acc\n", " best_config = (batch, lr, dr)\n", "\n", "print(\"\\n==========================================\")\n", "print(\"Best Hyperparameter Configuration Found:\")\n", "print(f\"Batch Size: {best_config[0]}\")\n", "print(f\"Learning Rate: {best_config[1]}\")\n", "print(f\"Dropout Rate: {best_config[2]}\")\n", "print(f\"Highest Validation Accuracy: {best_acc:.4f}\")\n", "print(\"==========================================\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "_VfhzaDLbX8V", "outputId": "e42d8387-723d-4aae-f282-36d3471f6508" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Training with Batch=32, LR=0.001, Dropout=0.25\n", "Validation Accuracy: 0.7524\n", "\n", "Training with Batch=32, LR=0.001, Dropout=0.3\n", "Validation Accuracy: 0.7265\n", "\n", "Training with Batch=32, LR=0.001, Dropout=0.4\n", "Validation Accuracy: 0.7161\n", "\n", "Training with Batch=32, LR=0.0005, Dropout=0.25\n", "Validation Accuracy: 0.7295\n", "\n", "Training with Batch=32, LR=0.0005, Dropout=0.3\n", "Validation Accuracy: 0.7198\n", "\n", "Training with Batch=32, LR=0.0005, Dropout=0.4\n", "Validation Accuracy: 0.6788\n", "\n", "Training with Batch=32, LR=0.0001, Dropout=0.25\n", "Validation Accuracy: 0.6647\n", "\n", "Training with Batch=32, LR=0.0001, Dropout=0.3\n", "Validation Accuracy: 0.6277\n", "\n", "Training with Batch=32, LR=0.0001, Dropout=0.4\n", "Validation Accuracy: 0.5395\n", "\n", "Training with Batch=64, LR=0.001, Dropout=0.25\n", "Validation Accuracy: 0.7359\n", "\n", "Training with Batch=64, LR=0.001, Dropout=0.3\n", "Validation Accuracy: 0.7189\n", "\n", "Training with Batch=64, LR=0.001, Dropout=0.4\n", "Validation Accuracy: 0.6682\n", "\n", "Training with Batch=64, LR=0.0005, Dropout=0.25\n", "Validation Accuracy: 0.7281\n", "\n", "Training with Batch=64, LR=0.0005, Dropout=0.3\n", "Validation Accuracy: 0.7367\n", "\n", "Training with Batch=64, LR=0.0005, Dropout=0.4\n", "Validation Accuracy: 0.6975\n", "\n", "Training with Batch=64, LR=0.0001, Dropout=0.25\n", "Validation Accuracy: 0.6003\n", "\n", "Training with Batch=64, LR=0.0001, Dropout=0.3\n", "Validation Accuracy: 0.6066\n", "\n", "Training with Batch=64, LR=0.0001, Dropout=0.4\n", "Validation Accuracy: 0.5086\n", "\n", "Training with Batch=128, LR=0.001, Dropout=0.25\n", "Validation Accuracy: 0.7265\n", "\n", "Training with Batch=128, LR=0.001, Dropout=0.3\n", "Validation Accuracy: 0.6873\n", "\n", "Training with Batch=128, LR=0.001, Dropout=0.4\n", "Validation Accuracy: 0.6654\n", "\n", "Training with Batch=128, LR=0.0005, Dropout=0.25\n", "Validation Accuracy: 0.6851\n", "\n", "Training with Batch=128, LR=0.0005, Dropout=0.3\n", "Validation Accuracy: 0.6932\n", "\n", "Training with Batch=128, LR=0.0005, Dropout=0.4\n", "Validation Accuracy: 0.6701\n", "\n", "Training with Batch=128, LR=0.0001, Dropout=0.25\n", "Validation Accuracy: 0.5567\n", "\n", "Training with Batch=128, LR=0.0001, Dropout=0.3\n", "Validation Accuracy: 0.5368\n", "\n", "Training with Batch=128, LR=0.0001, Dropout=0.4\n", "Validation Accuracy: 0.4650\n", "\n", "==========================================\n", "Best Hyperparameter Configuration Found:\n", "Batch Size: 32\n", "Learning Rate: 0.001\n", "Dropout Rate: 0.25\n", "Highest Validation Accuracy: 0.7524\n", "==========================================\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "lSFswfVMxIO5" }, "execution_count": null, "outputs": [] } ] }