{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "8N0rRv2HLB_M" }, "outputs": [], "source": [ "import numpy as np\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "from tensorflow.keras import layers, models\n", "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n", "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import confusion_matrix, classification_report, precision_score, recall_score, f1_score\n", "import seaborn as sns" ] }, { "cell_type": "code", "source": [ "np.random.seed(42)\n", "tf.random.set_seed(42)\n", "\n" ], "metadata": { "id": "l_1m25PcLDiV" }, "execution_count": 2, "outputs": [] }, { "cell_type": "code", "source": [ "\n", "# CIFAR-10: 60,000 images (50,000 train, 10,000 test)\n", "# 32x32 pixels, 10 classes\n", "(X_train_full, y_train_full), (X_test, y_test) = keras.datasets.cifar10.load_data()\n", "\n", "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n", " 'dog', 'frog', 'horse', 'ship', 'truck']\n", "\n", "print(f\"Training set: {X_train_full.shape[0]} images\")\n", "print(f\"Test set: {X_test.shape[0]} images\")\n", "print(f\"Image dimensions: {X_train_full.shape[1]}x{X_train_full.shape[2]}x{X_train_full.shape[3]}\")\n", "print(f\"Number of classes: {len(class_names)}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Y6f-rwsVLiV8", "outputId": "f5520418-f778-4663-e12e-79e759bb9e83" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n", "\u001b[1m170498071/170498071\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 0us/step\n", "Training set: 50000 images\n", "Test set: 10000 images\n", "Image dimensions: 32x32x3\n", "Number of classes: 10\n" ] } ] }, { "cell_type": "code", "source": [ "# Normalize pixel values to [0, 1] range\n", "X_train_full = X_train_full.astype('float32') / 255.0\n", "X_test = X_test.astype('float32') / 255.0\n", "\n", "# Convert labels to categorical\n", "y_train_cat_full = keras.utils.to_categorical(y_train_full, 10)\n", "y_test_cat = keras.utils.to_categorical(y_test, 10)\n", "\n", "# Train/validation split (45,000/5,000)\n", "X_train = X_train_full[:45000]\n", "y_train_cat = y_train_cat_full[:45000]\n", "X_val = X_train_full[45000:]\n", "y_val_cat = y_train_cat_full[45000:]\n", "print(f\"After split - Train: {X_train.shape[0]}, Validation: {X_val.shape[0]}\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "07042_YILssr", "outputId": "07e0a314-deda-4762-9792-9eef89b103ef" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "After split - Train: 45000, Validation: 5000\n" ] } ] }, { "cell_type": "code", "source": [ "# DATA AUGMENTATION\n", "datagen = ImageDataGenerator(\n", " horizontal_flip=True, # Random horizontal flips\n", " width_shift_range=0.1, # Random cropping with padding\n", " height_shift_range=0.1,\n", " rotation_range=10, # Minor rotations\n", " fill_mode='nearest'\n", ")\n", "datagen.fit(X_train)" ], "metadata": { "id": "6xK3l7EQL1EU" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "model = models.Sequential([\n", " # Block 1: 32 filters\n", " layers.Conv2D(32, (3, 3), activation='relu', padding='same', input_shape=(32, 32, 3)),\n", " layers.Conv2D(32, (3, 3), activation='relu', padding='same'),\n", " layers.MaxPooling2D((2, 2)),\n", " layers.Dropout(0.25),\n", "\n", " # Block 2: 64 filters\n", " layers.Conv2D(64, (3, 3), activation='relu', padding='same'),\n", " layers.Conv2D(64, (3, 3), activation='relu', padding='same'),\n", " layers.MaxPooling2D((2, 2)),\n", " layers.Dropout(0.25),\n", "\n", " # Block 3: 128 filters\n", " layers.Conv2D(128, (3, 3), activation='relu', padding='same'),\n", " layers.Conv2D(128, (3, 3), activation='relu', padding='same'),\n", " layers.MaxPooling2D((2, 2)),\n", " layers.Dropout(0.25), # Fully connected layers (3 layers as per report)\n", " layers.Flatten(),\n", " layers.Dense(512, activation='relu'),\n", " layers.Dropout(0.5),\n", " layers.Dense(256, activation='relu'),\n", " layers.Dropout(0.5),\n", " layers.Dense(10, activation='softmax')\n", "])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "un33zSfWL8B7", "outputId": "87f3c90e-c267-49fd-9758-9c9135f2b2e7" }, "execution_count": 6, "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" ] } ] }, { "cell_type": "code", "source": [ "#HYPERPARAMETERS\n", "\n", "# Compile with Adam optimizer, learning rate 0.001\n", "model.compile(\n", " optimizer=keras.optimizers.Adam(learning_rate=0.001),\n", " loss='categorical_crossentropy',\n", " metrics=['accuracy']\n", ")\n", "\n", "print(\"Optimizer: Adam (learning_rate=0.001)\")\n", "print(\"Loss function: Categorical Cross-Entropy\")\n", "print(\"Batch size: 128\")\n", "print(\"Epochs: 100\")\n", "print(\"Dropout rates: 0.25 (pooling), 0.5 (dense)\")\n", "\n", "model.summary()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 792 }, "id": "64KGuf0yMJ5Y", "outputId": "f7b8089b-71e7-47c2-d905-98324dc92c2d" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Optimizer: Adam (learning_rate=0.001)\n", "Loss function: Categorical Cross-Entropy\n", "Batch size: 128\n", "Epochs: 100\n", "Dropout rates: 0.25 (pooling), 0.5 (dense)\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", "│ conv2d_1 (\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;34m9,248\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_2 (\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", "│ conv2d_3 (\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;34m36,928\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_4 (\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", "│ conv2d_5 (\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;34m147,584\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;34m512\u001b[0m) │ \u001b[38;5;34m1,049,088\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\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;34m256\u001b[0m) │ \u001b[38;5;34m131,328\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dropout_4 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m2,570\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ], "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (Conv2D)                 │ (None, 32, 32, 32)     │           896 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (Conv2D)               │ (None, 32, 32, 32)     │         9,248 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (MaxPooling2D)    │ (None, 16, 16, 32)     │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (Dropout)               │ (None, 16, 16, 32)     │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_2 (Conv2D)               │ (None, 16, 16, 64)     │        18,496 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_3 (Conv2D)               │ (None, 16, 16, 64)     │        36,928 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 8, 8, 64)       │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_1 (Dropout)             │ (None, 8, 8, 64)       │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_4 (Conv2D)               │ (None, 8, 8, 128)      │        73,856 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_5 (Conv2D)               │ (None, 8, 8, 128)      │       147,584 │\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, 512)            │     1,049,088 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (Dropout)             │ (None, 512)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (Dense)                 │ (None, 256)            │       131,328 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_4 (Dropout)             │ (None, 256)            │             0 │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (Dense)                 │ (None, 10)             │         2,570 │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,469,994\u001b[0m (5.61 MB)\n" ], "text/html": [ "
 Total params: 1,469,994 (5.61 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,469,994\u001b[0m (5.61 MB)\n" ], "text/html": [ "
 Trainable params: 1,469,994 (5.61 MB)\n",
              "
\n" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ], "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
              "
\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "# Early stopping (monitors validation loss for 5 epochs)\n", "early_stop = EarlyStopping(\n", " monitor='val_loss',\n", " patience=10,\n", " restore_best_weights=True,\n", " verbose=1\n", ")\n", "\n", "# Learning rate scheduler (reduces by 50% when plateauing)\n", "reduce_lr = ReduceLROnPlateau(\n", " monitor='val_loss',\n", " factor=0.5,\n", " patience=5,\n", " min_lr=1e-7,\n", " verbose=1\n", ")\n", "\n", "# Model checkpoint (saves best weights)\n", "checkpoint = ModelCheckpoint(\n", " 'best_cifar10_model.h5',\n", " monitor='val_accuracy',\n", " save_best_only=True,\n", " verbose=1\n", ")" ], "metadata": { "id": "XkB7jYDvMQSX" }, "execution_count": 8, "outputs": [] }, { "cell_type": "code", "source": [ "#MODEL TRAINING\n", "\n", "batch_size = 128\n", "epochs = 100\n", "\n", "history = model.fit(\n", " datagen.flow(X_train, y_train_cat, batch_size=batch_size),\n", " steps_per_epoch=len(X_train) // batch_size,\n", " epochs=epochs,\n", " validation_data=(X_val, y_val_cat),\n", " callbacks=[early_stop, reduce_lr, checkpoint],\n", " verbose=2\n", ")\n", "\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "IAzWtYppMYso", "outputId": "f079820b-6b00-445e-ec3b-ea1032c1a0f6" }, "execution_count": 9, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n", " self._warn_if_super_not_called()\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/100\n", "\n", "Epoch 1: val_accuracy improved from -inf to 0.42780, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 44s - 126ms/step - accuracy: 0.2644 - loss: 1.9531 - val_accuracy: 0.4278 - val_loss: 1.5105 - learning_rate: 1.0000e-03\n", "Epoch 2/100\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/epoch_iterator.py:116: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n", " self._interrupted_warning()\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "\n", "Epoch 2: val_accuracy improved from 0.42780 to 0.43180, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.3828 - loss: 1.6785 - val_accuracy: 0.4318 - val_loss: 1.5041 - learning_rate: 1.0000e-03\n", "Epoch 3/100\n", "\n", "Epoch 3: val_accuracy improved from 0.43180 to 0.56520, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 70ms/step - accuracy: 0.4486 - loss: 1.5004 - val_accuracy: 0.5652 - val_loss: 1.1887 - learning_rate: 1.0000e-03\n", "Epoch 4/100\n", "\n", "Epoch 4: val_accuracy did not improve from 0.56520\n", "351/351 - 1s - 2ms/step - accuracy: 0.5469 - loss: 1.1901 - val_accuracy: 0.5594 - val_loss: 1.2102 - learning_rate: 1.0000e-03\n", "Epoch 5/100\n", "\n", "Epoch 5: val_accuracy did not improve from 0.56520\n", "351/351 - 24s - 70ms/step - accuracy: 0.5236 - loss: 1.3211 - val_accuracy: 0.5610 - val_loss: 1.2442 - learning_rate: 1.0000e-03\n", "Epoch 6/100\n", "\n", "Epoch 6: val_accuracy improved from 0.56520 to 0.57520, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.5938 - loss: 1.0692 - val_accuracy: 0.5752 - val_loss: 1.1877 - learning_rate: 1.0000e-03\n", "Epoch 7/100\n", "\n", "Epoch 7: val_accuracy improved from 0.57520 to 0.62160, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 70ms/step - accuracy: 0.5690 - loss: 1.2113 - val_accuracy: 0.6216 - val_loss: 1.1049 - learning_rate: 1.0000e-03\n", "Epoch 8/100\n", "\n", "Epoch 8: val_accuracy improved from 0.62160 to 0.62880, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.6016 - loss: 1.2199 - val_accuracy: 0.6288 - val_loss: 1.0658 - learning_rate: 1.0000e-03\n", "Epoch 9/100\n", "\n", "Epoch 9: val_accuracy improved from 0.62880 to 0.65440, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.5983 - loss: 1.1351 - val_accuracy: 0.6544 - val_loss: 0.9636 - learning_rate: 1.0000e-03\n", "Epoch 10/100\n", "\n", "Epoch 10: val_accuracy did not improve from 0.65440\n", "351/351 - 1s - 2ms/step - accuracy: 0.6016 - loss: 1.1656 - val_accuracy: 0.6542 - val_loss: 0.9702 - learning_rate: 1.0000e-03\n", "Epoch 11/100\n", "\n", "Epoch 11: val_accuracy improved from 0.65440 to 0.67160, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 71ms/step - accuracy: 0.6299 - loss: 1.0517 - val_accuracy: 0.6716 - val_loss: 0.9436 - learning_rate: 1.0000e-03\n", "Epoch 12/100\n", "\n", "Epoch 12: val_accuracy did not improve from 0.67160\n", "351/351 - 1s - 2ms/step - accuracy: 0.6328 - loss: 1.0715 - val_accuracy: 0.6596 - val_loss: 0.9764 - learning_rate: 1.0000e-03\n", "Epoch 13/100\n", "\n", "Epoch 13: val_accuracy improved from 0.67160 to 0.68300, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.6442 - loss: 1.0152 - val_accuracy: 0.6830 - val_loss: 0.9135 - learning_rate: 1.0000e-03\n", "Epoch 14/100\n", "\n", "Epoch 14: val_accuracy improved from 0.68300 to 0.69860, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.6094 - loss: 1.0993 - val_accuracy: 0.6986 - val_loss: 0.8757 - learning_rate: 1.0000e-03\n", "Epoch 15/100\n", "\n", "Epoch 15: val_accuracy improved from 0.69860 to 0.70400, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 72ms/step - accuracy: 0.6669 - loss: 0.9580 - val_accuracy: 0.7040 - val_loss: 0.8490 - learning_rate: 1.0000e-03\n", "Epoch 16/100\n", "\n", "Epoch 16: val_accuracy improved from 0.70400 to 0.72480, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.6875 - loss: 0.9438 - val_accuracy: 0.7248 - val_loss: 0.7963 - learning_rate: 1.0000e-03\n", "Epoch 17/100\n", "\n", "Epoch 17: val_accuracy improved from 0.72480 to 0.72760, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.6756 - loss: 0.9368 - val_accuracy: 0.7276 - val_loss: 0.7719 - learning_rate: 1.0000e-03\n", "Epoch 18/100\n", "\n", "Epoch 18: val_accuracy did not improve from 0.72760\n", "351/351 - 1s - 2ms/step - accuracy: 0.6875 - loss: 0.8702 - val_accuracy: 0.7270 - val_loss: 0.7680 - learning_rate: 1.0000e-03\n", "Epoch 19/100\n", "\n", "Epoch 19: val_accuracy improved from 0.72760 to 0.75160, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 71ms/step - accuracy: 0.6855 - loss: 0.9071 - val_accuracy: 0.7516 - val_loss: 0.7149 - learning_rate: 1.0000e-03\n", "Epoch 20/100\n", "\n", "Epoch 20: val_accuracy did not improve from 0.75160\n", "351/351 - 1s - 1ms/step - accuracy: 0.6797 - loss: 0.8867 - val_accuracy: 0.7442 - val_loss: 0.7345 - learning_rate: 1.0000e-03\n", "Epoch 21/100\n", "\n", "Epoch 21: val_accuracy improved from 0.75160 to 0.75180, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.6928 - loss: 0.8875 - val_accuracy: 0.7518 - val_loss: 0.7160 - learning_rate: 1.0000e-03\n", "Epoch 22/100\n", "\n", "Epoch 22: val_accuracy did not improve from 0.75180\n", "351/351 - 1s - 2ms/step - accuracy: 0.7578 - loss: 0.7691 - val_accuracy: 0.7466 - val_loss: 0.7326 - learning_rate: 1.0000e-03\n", "Epoch 23/100\n", "\n", "Epoch 23: val_accuracy improved from 0.75180 to 0.75560, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.7040 - loss: 0.8564 - val_accuracy: 0.7556 - val_loss: 0.7156 - learning_rate: 1.0000e-03\n", "Epoch 24/100\n", "\n", "Epoch 24: ReduceLROnPlateau reducing learning rate to 0.0005000000237487257.\n", "\n", "Epoch 24: val_accuracy did not improve from 0.75560\n", "351/351 - 1s - 1ms/step - accuracy: 0.6250 - loss: 1.0245 - val_accuracy: 0.7392 - val_loss: 0.7714 - learning_rate: 1.0000e-03\n", "Epoch 25/100\n", "\n", "Epoch 25: val_accuracy improved from 0.75560 to 0.75640, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 70ms/step - accuracy: 0.7261 - loss: 0.7968 - val_accuracy: 0.7564 - val_loss: 0.6988 - learning_rate: 5.0000e-04\n", "Epoch 26/100\n", "\n", "Epoch 26: val_accuracy did not improve from 0.75640\n", "351/351 - 1s - 1ms/step - accuracy: 0.6641 - loss: 0.9734 - val_accuracy: 0.7558 - val_loss: 0.7027 - learning_rate: 5.0000e-04\n", "Epoch 27/100\n", "\n", "Epoch 27: val_accuracy improved from 0.75640 to 0.77140, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 70ms/step - accuracy: 0.7347 - loss: 0.7713 - val_accuracy: 0.7714 - val_loss: 0.6738 - learning_rate: 5.0000e-04\n", "Epoch 28/100\n", "\n", "Epoch 28: val_accuracy improved from 0.77140 to 0.77220, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.7812 - loss: 0.7306 - val_accuracy: 0.7722 - val_loss: 0.6695 - learning_rate: 5.0000e-04\n", "Epoch 29/100\n", "\n", "Epoch 29: val_accuracy did not improve from 0.77220\n", "351/351 - 25s - 70ms/step - accuracy: 0.7354 - loss: 0.7658 - val_accuracy: 0.7656 - val_loss: 0.6648 - learning_rate: 5.0000e-04\n", "Epoch 30/100\n", "\n", "Epoch 30: val_accuracy did not improve from 0.77220\n", "351/351 - 1s - 2ms/step - accuracy: 0.7422 - loss: 0.6295 - val_accuracy: 0.7676 - val_loss: 0.6641 - learning_rate: 5.0000e-04\n", "Epoch 31/100\n", "\n", "Epoch 31: val_accuracy did not improve from 0.77220\n", "351/351 - 24s - 69ms/step - accuracy: 0.7439 - loss: 0.7477 - val_accuracy: 0.7662 - val_loss: 0.6726 - learning_rate: 5.0000e-04\n", "Epoch 32/100\n", "\n", "Epoch 32: val_accuracy did not improve from 0.77220\n", "351/351 - 1s - 1ms/step - accuracy: 0.7812 - loss: 0.6370 - val_accuracy: 0.7704 - val_loss: 0.6662 - learning_rate: 5.0000e-04\n", "Epoch 33/100\n", "\n", "Epoch 33: val_accuracy improved from 0.77220 to 0.77660, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 69ms/step - accuracy: 0.7434 - loss: 0.7385 - val_accuracy: 0.7766 - val_loss: 0.6410 - learning_rate: 5.0000e-04\n", "Epoch 34/100\n", "\n", "Epoch 34: val_accuracy improved from 0.77660 to 0.77900, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.7344 - loss: 0.7271 - val_accuracy: 0.7790 - val_loss: 0.6384 - learning_rate: 5.0000e-04\n", "Epoch 35/100\n", "\n", "Epoch 35: val_accuracy improved from 0.77900 to 0.78880, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 70ms/step - accuracy: 0.7480 - loss: 0.7323 - val_accuracy: 0.7888 - val_loss: 0.6173 - learning_rate: 5.0000e-04\n", "Epoch 36/100\n", "\n", "Epoch 36: val_accuracy improved from 0.78880 to 0.79120, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.7188 - loss: 0.8111 - val_accuracy: 0.7912 - val_loss: 0.6155 - learning_rate: 5.0000e-04\n", "Epoch 37/100\n", "\n", "Epoch 37: val_accuracy improved from 0.79120 to 0.79780, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 24s - 70ms/step - accuracy: 0.7539 - loss: 0.7150 - val_accuracy: 0.7978 - val_loss: 0.5896 - learning_rate: 5.0000e-04\n", "Epoch 38/100\n", "\n", "Epoch 38: val_accuracy did not improve from 0.79780\n", "351/351 - 1s - 2ms/step - accuracy: 0.7500 - loss: 0.8415 - val_accuracy: 0.7956 - val_loss: 0.5984 - learning_rate: 5.0000e-04\n", "Epoch 39/100\n", "\n", "Epoch 39: val_accuracy did not improve from 0.79780\n", "351/351 - 26s - 74ms/step - accuracy: 0.7551 - loss: 0.7166 - val_accuracy: 0.7842 - val_loss: 0.6300 - learning_rate: 5.0000e-04\n", "Epoch 40/100\n", "\n", "Epoch 40: val_accuracy did not improve from 0.79780\n", "351/351 - 1s - 2ms/step - accuracy: 0.7031 - loss: 0.7862 - val_accuracy: 0.7856 - val_loss: 0.6267 - learning_rate: 5.0000e-04\n", "Epoch 41/100\n", "\n", "Epoch 41: val_accuracy did not improve from 0.79780\n", "351/351 - 30s - 86ms/step - accuracy: 0.7576 - loss: 0.7052 - val_accuracy: 0.7888 - val_loss: 0.6122 - learning_rate: 5.0000e-04\n", "Epoch 42/100\n", "\n", "Epoch 42: ReduceLROnPlateau reducing learning rate to 0.0002500000118743628.\n", "\n", "Epoch 42: val_accuracy did not improve from 0.79780\n", "351/351 - 1s - 1ms/step - accuracy: 0.7422 - loss: 0.8288 - val_accuracy: 0.7858 - val_loss: 0.6158 - learning_rate: 5.0000e-04\n", "Epoch 43/100\n", "\n", "Epoch 43: val_accuracy did not improve from 0.79780\n", "351/351 - 37s - 105ms/step - accuracy: 0.7688 - loss: 0.6683 - val_accuracy: 0.7964 - val_loss: 0.5920 - learning_rate: 2.5000e-04\n", "Epoch 44/100\n", "\n", "Epoch 44: val_accuracy did not improve from 0.79780\n", "351/351 - 1s - 2ms/step - accuracy: 0.7891 - loss: 0.6738 - val_accuracy: 0.7974 - val_loss: 0.5865 - learning_rate: 2.5000e-04\n", "Epoch 45/100\n", "\n", "Epoch 45: val_accuracy improved from 0.79780 to 0.80720, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 38s - 108ms/step - accuracy: 0.7753 - loss: 0.6530 - val_accuracy: 0.8072 - val_loss: 0.5713 - learning_rate: 2.5000e-04\n", "Epoch 46/100\n", "\n", "Epoch 46: val_accuracy improved from 0.80720 to 0.80740, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.8125 - loss: 0.5677 - val_accuracy: 0.8074 - val_loss: 0.5704 - learning_rate: 2.5000e-04\n", "Epoch 47/100\n", "\n", "Epoch 47: val_accuracy did not improve from 0.80740\n", "351/351 - 24s - 70ms/step - accuracy: 0.7752 - loss: 0.6533 - val_accuracy: 0.8058 - val_loss: 0.5665 - learning_rate: 2.5000e-04\n", "Epoch 48/100\n", "\n", "Epoch 48: val_accuracy improved from 0.80740 to 0.80760, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.6797 - loss: 0.8042 - val_accuracy: 0.8076 - val_loss: 0.5620 - learning_rate: 2.5000e-04\n", "Epoch 49/100\n", "\n", "Epoch 49: val_accuracy did not improve from 0.80760\n", "351/351 - 25s - 70ms/step - accuracy: 0.7778 - loss: 0.6423 - val_accuracy: 0.8074 - val_loss: 0.5733 - learning_rate: 2.5000e-04\n", "Epoch 50/100\n", "\n", "Epoch 50: val_accuracy did not improve from 0.80760\n", "351/351 - 1s - 1ms/step - accuracy: 0.7812 - loss: 0.6753 - val_accuracy: 0.8074 - val_loss: 0.5714 - learning_rate: 2.5000e-04\n", "Epoch 51/100\n", "\n", "Epoch 51: val_accuracy improved from 0.80760 to 0.81200, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 25s - 71ms/step - accuracy: 0.7789 - loss: 0.6416 - val_accuracy: 0.8120 - val_loss: 0.5486 - learning_rate: 2.5000e-04\n", "Epoch 52/100\n", "\n", "Epoch 52: val_accuracy did not improve from 0.81200\n", "351/351 - 1s - 1ms/step - accuracy: 0.8281 - loss: 0.5530 - val_accuracy: 0.8106 - val_loss: 0.5485 - learning_rate: 2.5000e-04\n", "Epoch 53/100\n", "\n", "Epoch 53: val_accuracy did not improve from 0.81200\n", "351/351 - 24s - 69ms/step - accuracy: 0.7803 - loss: 0.6405 - val_accuracy: 0.8084 - val_loss: 0.5615 - learning_rate: 2.5000e-04\n", "Epoch 54/100\n", "\n", "Epoch 54: val_accuracy did not improve from 0.81200\n", "351/351 - 1s - 1ms/step - accuracy: 0.8203 - loss: 0.5949 - val_accuracy: 0.8092 - val_loss: 0.5593 - learning_rate: 2.5000e-04\n", "Epoch 55/100\n", "\n", "Epoch 55: val_accuracy did not improve from 0.81200\n", "351/351 - 25s - 72ms/step - accuracy: 0.7838 - loss: 0.6312 - val_accuracy: 0.8106 - val_loss: 0.5550 - learning_rate: 2.5000e-04\n", "Epoch 56/100\n", "\n", "Epoch 56: ReduceLROnPlateau reducing learning rate to 0.0001250000059371814.\n", "\n", "Epoch 56: val_accuracy did not improve from 0.81200\n", "351/351 - 1s - 1ms/step - accuracy: 0.7969 - loss: 0.6824 - val_accuracy: 0.8100 - val_loss: 0.5534 - learning_rate: 2.5000e-04\n", "Epoch 57/100\n", "\n", "Epoch 57: val_accuracy did not improve from 0.81200\n", "351/351 - 48s - 138ms/step - accuracy: 0.7904 - loss: 0.6144 - val_accuracy: 0.8064 - val_loss: 0.5637 - learning_rate: 1.2500e-04\n", "Epoch 58/100\n", "\n", "Epoch 58: val_accuracy did not improve from 0.81200\n", "351/351 - 1s - 1ms/step - accuracy: 0.7656 - loss: 0.6462 - val_accuracy: 0.8058 - val_loss: 0.5633 - learning_rate: 1.2500e-04\n", "Epoch 59/100\n", "\n", "Epoch 59: val_accuracy improved from 0.81200 to 0.81840, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 40s - 115ms/step - accuracy: 0.7911 - loss: 0.6076 - val_accuracy: 0.8184 - val_loss: 0.5351 - learning_rate: 1.2500e-04\n", "Epoch 60/100\n", "\n", "Epoch 60: val_accuracy improved from 0.81840 to 0.81900, saving model to best_cifar10_model.h5\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "351/351 - 1s - 2ms/step - accuracy: 0.8047 - loss: 0.5109 - val_accuracy: 0.8190 - val_loss: 0.5349 - learning_rate: 1.2500e-04\n", "Epoch 61/100\n", "\n", "Epoch 61: val_accuracy did not improve from 0.81900\n", "351/351 - 34s - 97ms/step - accuracy: 0.7909 - loss: 0.6026 - val_accuracy: 0.8070 - val_loss: 0.5727 - learning_rate: 1.2500e-04\n", "Epoch 62/100\n", "\n", "Epoch 62: val_accuracy did not improve from 0.81900\n", "351/351 - 1s - 1ms/step - accuracy: 0.7969 - loss: 0.5960 - val_accuracy: 0.8068 - val_loss: 0.5727 - learning_rate: 1.2500e-04\n", "Epoch 63/100\n", "\n", "Epoch 63: val_accuracy did not improve from 0.81900\n", "351/351 - 24s - 69ms/step - accuracy: 0.7945 - loss: 0.5999 - val_accuracy: 0.8086 - val_loss: 0.5672 - learning_rate: 1.2500e-04\n", "Epoch 64/100\n", "\n", "Epoch 64: val_accuracy did not improve from 0.81900\n", "351/351 - 0s - 1ms/step - accuracy: 0.7812 - loss: 0.6835 - val_accuracy: 0.8080 - val_loss: 0.5645 - learning_rate: 1.2500e-04\n", "Epoch 65/100\n", "\n", "Epoch 65: ReduceLROnPlateau reducing learning rate to 6.25000029685907e-05.\n", "\n", "Epoch 65: val_accuracy did not improve from 0.81900\n", "351/351 - 25s - 70ms/step - accuracy: 0.7956 - loss: 0.5966 - val_accuracy: 0.8108 - val_loss: 0.5634 - learning_rate: 1.2500e-04\n", "Epoch 66/100\n", "\n", "Epoch 66: val_accuracy did not improve from 0.81900\n", "351/351 - 1s - 1ms/step - accuracy: 0.8125 - loss: 0.5530 - val_accuracy: 0.8104 - val_loss: 0.5622 - learning_rate: 6.2500e-05\n", "Epoch 67/100\n", "\n", "Epoch 67: val_accuracy did not improve from 0.81900\n", "351/351 - 24s - 69ms/step - accuracy: 0.7972 - loss: 0.5872 - val_accuracy: 0.8092 - val_loss: 0.5550 - learning_rate: 6.2500e-05\n", "Epoch 68/100\n", "\n", "Epoch 68: val_accuracy did not improve from 0.81900\n", "351/351 - 1s - 1ms/step - accuracy: 0.7969 - loss: 0.5455 - val_accuracy: 0.8092 - val_loss: 0.5551 - learning_rate: 6.2500e-05\n", "Epoch 69/100\n", "\n", "Epoch 69: val_accuracy did not improve from 0.81900\n", "351/351 - 25s - 71ms/step - accuracy: 0.7989 - loss: 0.5868 - val_accuracy: 0.8154 - val_loss: 0.5459 - learning_rate: 6.2500e-05\n", "Epoch 70/100\n", "\n", "Epoch 70: ReduceLROnPlateau reducing learning rate to 3.125000148429535e-05.\n", "\n", "Epoch 70: val_accuracy did not improve from 0.81900\n", "351/351 - 1s - 1ms/step - accuracy: 0.8203 - loss: 0.5498 - val_accuracy: 0.8140 - val_loss: 0.5471 - learning_rate: 6.2500e-05\n", "Epoch 70: early stopping\n", "Restoring model weights from the end of the best epoch: 60.\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "# Load best model\n", "model = keras.models.load_model('best_cifar10_model.h5')\n", "\n", "# Evaluate on test set\n", "test_loss, test_accuracy = model.evaluate(X_test, y_test_cat, verbose=0)\n", "\n", "print(f\"\\nFinal Results:\")\n", "print(f\"Test Loss: {test_loss:.4f}\")\n", "print(f\"Test Accuracy: {test_accuracy*100:.2f}%\")\n", "\n", "final_train_acc = history.history['accuracy'][-1] * 100\n", "final_val_acc = history.history['val_accuracy'][-1] * 100\n", "\n", "print(f\"Training Accuracy: {final_train_acc:.2f}%\")\n", "print(f\"Validation Accuracy: {final_val_acc:.2f}%\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "uWKseNNjN17I", "outputId": "db6ea015-2f58-445a-c666-4550ab4c3fa1" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "\n", "Final Results:\n", "Test Loss: 0.5723\n", "Test Accuracy: 80.64%\n", "Training Accuracy: 82.03%\n", "Validation Accuracy: 81.40%\n" ] } ] }, { "cell_type": "code", "source": [ "# Predictions\n", "y_pred = model.predict(X_test, verbose=0)\n", "y_pred_classes = np.argmax(y_pred, axis=1)\n", "y_true = y_test.flatten()\n", "\n", "# Confusion Matrix\n", "cm = confusion_matrix(y_true, y_pred_classes)\n", "\n", "# Per-class accuracy\n", "per_class_acc = cm.diagonal() / cm.sum(axis=1) * 100\n", "\n", "print(\"\\n\" + \"=\"*60)\n", "print(\"PER-CLASS ACCURACY (as discussed in Results)\")\n", "print(\"=\"*60)\n", "for i, class_name in enumerate(class_names):\n", " print(f\"{class_name:12s}: {per_class_acc[i]:.2f}%\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "KNSuSkSGPHOA", "outputId": "61f23db8-990c-4be8-bf91-885dc2debc4e" }, "execution_count": 11, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "============================================================\n", "PER-CLASS ACCURACY (as discussed in Results)\n", "============================================================\n", "airplane : 84.70%\n", "automobile : 92.30%\n", "bird : 63.40%\n", "cat : 59.60%\n", "deer : 80.80%\n", "dog : 62.40%\n", "frog : 94.50%\n", "horse : 86.10%\n", "ship : 90.20%\n", "truck : 92.40%\n" ] } ] }, { "cell_type": "code", "source": [ "# Precision, Recall, F1-Score\n", "precision = precision_score(y_true, y_pred_classes, average=None)\n", "recall = recall_score(y_true, y_pred_classes, average=None)\n", "f1 = f1_score(y_true, y_pred_classes, average=None)\n", "\n", "print(\"\\n\" + \"=\"*60)\n", "print(\"PRECISION, RECALL, F1-SCORE\")\n", "print(\"=\"*60)\n", "print(f\"{'Class':<12} {'Precision':<12} {'Recall':<12} {'F1-Score':<12}\")\n", "print(\"-\"*60)\n", "for i, class_name in enumerate(class_names):\n", " print(f\"{class_name:<12} {precision[i]:.4f} {recall[i]:.4f} {f1[i]:.4f}\")\n", "\n", "# Weighted averages\n", "weighted_f1 = f1_score(y_true, y_pred_classes, average='weighted')\n", "print(f\"\\nWeighted Average F1-Score: {weighted_f1:.4f}\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UU3GktWMPIfE", "outputId": "1d112427-83be-4f36-c5d7-4540c4b6a6b6" }, "execution_count": 12, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "============================================================\n", "PRECISION, RECALL, F1-SCORE\n", "============================================================\n", "Class Precision Recall F1-Score \n", "------------------------------------------------------------\n", "airplane 0.8199 0.8470 0.8333\n", "automobile 0.9112 0.9230 0.9170\n", "bird 0.8066 0.6340 0.7100\n", "cat 0.7095 0.5960 0.6478\n", "deer 0.7454 0.8080 0.7754\n", "dog 0.8157 0.6240 0.7071\n", "frog 0.6969 0.9450 0.8022\n", "horse 0.8375 0.8610 0.8491\n", "ship 0.8984 0.9020 0.9002\n", "truck 0.8469 0.9240 0.8838\n", "\n", "Weighted Average F1-Score: 0.8026\n" ] } ] }, { "cell_type": "code", "source": [ "# Training History (Results Para 2 & 3)\n", "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n", "\n", "# Accuracy\n", "axes[0].plot(history.history['accuracy'], label='Training Accuracy', linewidth=2)\n", "axes[0].plot(history.history['val_accuracy'], label='Validation Accuracy', linewidth=2)\n", "axes[0].set_title('Training and Validation Accuracy', fontsize=14, fontweight='bold')\n", "axes[0].set_xlabel('Epoch', fontsize=12)\n", "axes[0].set_ylabel('Accuracy', fontsize=12)\n", "axes[0].legend(fontsize=11)\n", "axes[0].grid(True, alpha=0.3)\n", "# Loss\n", "axes[1].plot(history.history['loss'], label='Training Loss', linewidth=2)\n", "axes[1].plot(history.history['val_loss'], label='Validation Loss', linewidth=2)\n", "axes[1].set_title('Training and Validation Loss', fontsize=14, fontweight='bold')\n", "axes[1].set_xlabel('Epoch', fontsize=12)\n", "axes[1].set_ylabel('Loss', fontsize=12)\n", "axes[1].legend(fontsize=11)\n", "axes[1].grid(True, alpha=0.3)\n", "\n", "plt.tight_layout()\n", "plt.savefig('training_curves.png', dpi=300, bbox_inches='tight')\n", "print(\"✓ Training curves saved as 'training_curves.png'\")\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 507 }, "id": "hhEisyeIQAV8", "outputId": "53423f65-f206-4d3b-9f3e-eb8e719e7117" }, "execution_count": 14, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "✓ Training curves saved as 'training_curves.png'\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "# Confusion Matrix\n", "plt.figure(figsize=(10, 8))\n", "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n", " xticklabels=class_names, yticklabels=class_names,\n", " cbar_kws={'label': 'Count'})\n", "plt.title('Confusion Matrix - CIFAR-10 Classification', fontsize=14, fontweight='bold')\n", "plt.ylabel('True Label', fontsize=12)\n", "plt.xlabel('Predicted Label', fontsize=12)\n", "plt.xticks(rotation=45, ha='right')\n", "plt.yticks(rotation=0)\n", "plt.tight_layout()\n", "plt.savefig('confusion_matrix.png', dpi=300, bbox_inches='tight')\n", "print(\"✓ Confusion matrix saved as 'confusion_matrix.png'\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 824 }, "id": "0ocZvyGkQD6j", "outputId": "7b2c8feb-3ed4-4044-c6fc-0e55b6cb1cc6" }, "execution_count": 15, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "✓ Confusion matrix saved as 'confusion_matrix.png'\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "#RESULTS\n", "# Save model\n", "model.save('final_cifar10_cnn.h5')\n", "\n", "# Save history\n", "np.save('training_history.npy', history.history)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yol_vKDEQNwZ", "outputId": "7d84a4a1-2a27-4a2d-aff2-83ba9c45e46d" }, "execution_count": 16, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" ] } ] }, { "cell_type": "code", "source": [ "print(\"\\n\" + \"=\"*60)\n", "print(\"EXPERIMENT SUMMARY\")\n", "print(\"=\"*60)\n", "print(f\" Model successfully trained on CIFAR-10 dataset\")\n", "print(f\" Final Test Accuracy: {test_accuracy*100:.2f}%\")\n", "print(f\" Training Accuracy: {final_train_acc:.2f}%\")\n", "print(f\" Validation Accuracy: {final_val_acc:.2f}%\")\n", "print(f\" Best performing classes: automobile, ship, airplane\")\n", "print(f\" Challenging classes: cat, dog (animal categories)\")\n", "print(f\" No severe overfitting observed\")\n", "print(f\"Results align with published benchmarks\")\n", "print(\"=\"*60)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-haxweNIQWKs", "outputId": "616c657b-8c1f-46df-f40a-2bc3c4f3e35c" }, "execution_count": 18, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "============================================================\n", "EXPERIMENT SUMMARY\n", "============================================================\n", " Model successfully trained on CIFAR-10 dataset\n", " Final Test Accuracy: 80.64%\n", " Training Accuracy: 82.03%\n", " Validation Accuracy: 81.40%\n", " Best performing classes: automobile, ship, airplane\n", " Challenging classes: cat, dog (animal categories)\n", " No severe overfitting observed\n", "Results align with published benchmarks\n", "============================================================\n" ] } ] } ] }