{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a69991d2",
   "metadata": {},
   "source": [
    "### 1. Prepare required environment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9a53a30a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from tensorflow.keras.datasets import cifar10\n",
    "from tensorflow.keras.utils import to_categorical"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7dc1f1e6",
   "metadata": {},
   "source": [
    "### 2. Load & Process Data\n",
    "in this part we prepare and process data for training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e4c0d5c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "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[1m709s\u001b[0m 4us/step\n"
     ]
    }
   ],
   "source": [
    "(Xtr, ytr), (Xte, yte) = cifar10.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4305dc86",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(50000, 32, 32, 3)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Xtr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "21541fa1",
   "metadata": {},
   "outputs": [],
   "source": [
    "Xtr = Xtr.astype('float32') / 255.0\n",
    "Xte = Xte.astype('float32') / 255.0\n",
    "\n",
    "ytr = to_categorical(ytr, 10)\n",
    "yte = to_categorical(yte, 10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b9861b4a",
   "metadata": {},
   "source": [
    "### 3. Data Augmentation & CNN\n",
    "We apply Data augmentation to prevent model from any overfitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "645bb6f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_augmentation = keras.Sequential([\n",
    "    layers.RandomFlip('horizontal'),\n",
    "    layers.RandomRotation(0.1),\n",
    "    layers.RandomZoom(0.2),\n",
    "],\n",
    "    name='data_augmentation'\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc001760",
   "metadata": {},
   "source": [
    "##### CNN\n",
    "- 1st Block: CONV => BATCHNORM => RELU => CONV => BATCHNORM => RELU => POOLING => DROPOUT\n",
    "- 2nd Block: CONV => BATCHNORM => RELU => CONV => BATCHNORM => RELU => POOLING => DROPOUT\n",
    "- Decision Head: FLATTEN => BATCHNORM => RELU => DROPOUT => SOFTMAX"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "3df3c5cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.Sequential([\n",
    "    keras.Input(shape=(32, 32, 3)),\n",
    "    \n",
    "    data_augmentation,\n",
    "\n",
    "    layers.Conv2D(32, kernel_size=(3, 3), padding='same'),\n",
    "    layers.BatchNormalization(),\n",
    "    layers.Activation('relu'),\n",
    "    layers.Conv2D(32, kernel_size=(3, 3), padding='same'),\n",
    "    layers.BatchNormalization(),\n",
    "    layers.Activation('relu'),\n",
    "    layers.MaxPooling2D(pool_size=(2, 2)),\n",
    "    layers.Dropout(0.25),\n",
    "\n",
    "    # Block 2\n",
    "    layers.Conv2D(64, kernel_size=(3, 3), padding='same'),\n",
    "    layers.BatchNormalization(),\n",
    "    layers.Activation('relu'),\n",
    "    layers.Conv2D(64, kernel_size=(3, 3), padding='same'),\n",
    "    layers.BatchNormalization(),\n",
    "    layers.Activation('relu'),\n",
    "    layers.MaxPooling2D(pool_size=(2, 2)), \n",
    "    layers.Dropout(0.25),\n",
    "\n",
    "    layers.Flatten(),\n",
    "    layers.Dense(512),\n",
    "    layers.BatchNormalization(),\n",
    "    layers.Activation('relu'),\n",
    "    layers.Dropout(0.5),\n",
    "    layers.Dense(10, activation='softmax') # 10 classes, softmax for class probabilities\n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ac086814",
   "metadata": {},
   "source": [
    "Applying;\n",
    "- adam optimizer\n",
    "- cross entropy loss\n",
    "- accuracy metric"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "5688f217",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(\n",
    "    optimizer='adam',\n",
    "    loss='categorical_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e7b59115",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.4139 - loss: 1.6679 - val_accuracy: 0.4878 - val_loss: 1.4409 - learning_rate: 0.0010\n",
      "Epoch 2/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.5308 - loss: 1.3102 - val_accuracy: 0.5882 - val_loss: 1.1511 - learning_rate: 0.0010\n",
      "Epoch 3/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.5827 - loss: 1.1725 - val_accuracy: 0.6440 - val_loss: 1.0365 - learning_rate: 0.0010\n",
      "Epoch 4/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.6097 - loss: 1.0990 - val_accuracy: 0.6296 - val_loss: 1.0582 - learning_rate: 0.0010\n",
      "Epoch 5/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 26ms/step - accuracy: 0.6314 - loss: 1.0485 - val_accuracy: 0.6626 - val_loss: 1.0083 - learning_rate: 0.0010\n",
      "Epoch 6/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.6502 - loss: 0.9956 - val_accuracy: 0.6586 - val_loss: 1.0506 - learning_rate: 0.0010\n",
      "Epoch 7/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.6613 - loss: 0.9693 - val_accuracy: 0.7202 - val_loss: 0.8084 - learning_rate: 0.0010\n",
      "Epoch 8/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.6707 - loss: 0.9412 - val_accuracy: 0.7402 - val_loss: 0.7369 - learning_rate: 0.0010\n",
      "Epoch 9/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.6845 - loss: 0.9067 - val_accuracy: 0.7156 - val_loss: 0.8599 - learning_rate: 0.0010\n",
      "Epoch 10/50\n",
      "\u001b[1m1405/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - accuracy: 0.6854 - loss: 0.8968\n",
      "Epoch 10: ReduceLROnPlateau reducing learning rate to 0.0005000000237487257.\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.6897 - loss: 0.8859 - val_accuracy: 0.7142 - val_loss: 0.8188 - learning_rate: 0.0010\n",
      "Epoch 11/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7094 - loss: 0.8366 - val_accuracy: 0.7564 - val_loss: 0.7208 - learning_rate: 5.0000e-04\n",
      "Epoch 12/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7203 - loss: 0.8090 - val_accuracy: 0.7668 - val_loss: 0.6780 - learning_rate: 5.0000e-04\n",
      "Epoch 13/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7245 - loss: 0.7948 - val_accuracy: 0.7670 - val_loss: 0.6759 - learning_rate: 5.0000e-04\n",
      "Epoch 14/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.7263 - loss: 0.7880 - val_accuracy: 0.7760 - val_loss: 0.6576 - learning_rate: 5.0000e-04\n",
      "Epoch 15/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 26ms/step - accuracy: 0.7334 - loss: 0.7680 - val_accuracy: 0.7586 - val_loss: 0.7052 - learning_rate: 5.0000e-04\n",
      "Epoch 16/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.7339 - loss: 0.7657 - val_accuracy: 0.7786 - val_loss: 0.6400 - learning_rate: 5.0000e-04\n",
      "Epoch 17/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7374 - loss: 0.7573 - val_accuracy: 0.7762 - val_loss: 0.6578 - learning_rate: 5.0000e-04\n",
      "Epoch 18/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7411 - loss: 0.7508 - val_accuracy: 0.7826 - val_loss: 0.6224 - learning_rate: 5.0000e-04\n",
      "Epoch 19/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7423 - loss: 0.7434 - val_accuracy: 0.7828 - val_loss: 0.6330 - learning_rate: 5.0000e-04\n",
      "Epoch 20/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7442 - loss: 0.7346 - val_accuracy: 0.7876 - val_loss: 0.6353 - learning_rate: 5.0000e-04\n",
      "Epoch 21/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7462 - loss: 0.7285 - val_accuracy: 0.7854 - val_loss: 0.6322 - learning_rate: 5.0000e-04\n",
      "Epoch 22/50\n",
      "\u001b[1m1406/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - accuracy: 0.7499 - loss: 0.7167\n",
      "Epoch 22: ReduceLROnPlateau reducing learning rate to 0.0002500000118743628.\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7479 - loss: 0.7248 - val_accuracy: 0.7106 - val_loss: 0.9257 - learning_rate: 5.0000e-04\n",
      "Epoch 23/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.7578 - loss: 0.6975 - val_accuracy: 0.8050 - val_loss: 0.5673 - learning_rate: 2.5000e-04\n",
      "Epoch 24/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7620 - loss: 0.6848 - val_accuracy: 0.7980 - val_loss: 0.5858 - learning_rate: 2.5000e-04\n",
      "Epoch 25/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.7626 - loss: 0.6848 - val_accuracy: 0.8108 - val_loss: 0.5560 - learning_rate: 2.5000e-04\n",
      "Epoch 26/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 27ms/step - accuracy: 0.7627 - loss: 0.6812 - val_accuracy: 0.8082 - val_loss: 0.5583 - learning_rate: 2.5000e-04\n",
      "Epoch 27/50\n",
      "\u001b[1m1406/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - accuracy: 0.7727 - loss: 0.6616\n",
      "Epoch 27: ReduceLROnPlateau reducing learning rate to 0.0001250000059371814.\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 25ms/step - accuracy: 0.7695 - loss: 0.6695 - val_accuracy: 0.8090 - val_loss: 0.5588 - learning_rate: 2.5000e-04\n",
      "Epoch 28/50\n",
      "\u001b[1m1407/1407\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m35s\u001b[0m 25ms/step - accuracy: 0.7692 - loss: 0.6672 - val_accuracy: 0.8026 - val_loss: 0.5804 - learning_rate: 1.2500e-04\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n",
    "\n",
    "reduce_lr = ReduceLROnPlateau(monitor='val_accuracy', factor=0.5,\n",
    "                            patience=2, min_lr=1e-6, verbose=1)\n",
    "early_stopping = EarlyStopping(monitor='val_accuracy',\n",
    "                            patience=3, mode='max', restore_best_weights=True)\n",
    "\n",
    "hist = model.fit(\n",
    "    Xtr, ytr,\n",
    "    batch_size=32,\n",
    "    epochs = 50,\n",
    "    validation_split = 0.1,\n",
    "    callbacks=[early_stopping, reduce_lr],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "30547d0d",
   "metadata": {},
   "source": [
    "##### Plotting\n",
    "Plotting the results to see easier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "ceb0393e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step - accuracy: 0.7998 - loss: 0.5865\n",
      "Test loss: 0.586500883102417\n",
      "Test accuracy: 0.7997999787330627\n"
     ]
    }
   ],
   "source": [
    "# Plot accuracy\n",
    "plt.figure(figsize=(12, 4))\n",
    "\n",
    "plt.subplot(1, 2, 1)\n",
    "plt.plot(hist.history['accuracy'], label='Train Accuracy')\n",
    "plt.plot(hist.history['val_accuracy'], label='Val Accuracy')\n",
    "plt.title('Model Accuracy')\n",
    "plt.xlabel('Epoch')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "\n",
    "# Plot loss\n",
    "plt.subplot(1, 2, 2)\n",
    "plt.plot(hist.history['loss'], label='Train Loss')\n",
    "plt.plot(hist.history['val_loss'], label='Val Loss')\n",
    "plt.title('Model Loss')\n",
    "plt.xlabel('Epoch')\n",
    "plt.ylabel('Loss')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "# Score trained model.\n",
    "scores = model.evaluate(Xte, yte, verbose=1)\n",
    "print('Test loss:', scores[0])\n",
    "print('Test accuracy:', scores[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a6647869",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step\n",
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step\n"
     ]
    }
   ],
   "source": [
    "# make prediction.\n",
    "pred = model.predict(Xte)\n",
    "y_pred = model.predict(Xte)\n",
    "y_pred_classes = np.argmax(y_pred, axis=1)\n",
    "y_true = np.argmax(yte, axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db1b573d",
   "metadata": {},
   "source": [
    "##### Confusion Matrix\n",
    "We use Confusion Matrix to see how model performed and where the errors are"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "ec63e4c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x800 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "import seaborn as sns\n",
    "\n",
    "labels = ['Airplane', 'Automobile', 'Bird', 'Cat', 'Deer', 'Dog', 'Frog', 'Horse', 'Ship', 'Truck']\n",
    "\n",
    "cm = confusion_matrix(y_true, y_pred_classes)\n",
    "\n",
    "cm = confusion_matrix(y_true, y_pred_classes)\n",
    "\n",
    "plt.figure(figsize=(10, 8))\n",
    "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', \n",
    "            xticklabels=labels, yticklabels=labels)\n",
    "plt.title('Confusion Matrix - Test Set')\n",
    "plt.ylabel('True Label')\n",
    "plt.xlabel('Predicted Label')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "0d952198",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.84      0.83      1000\n",
      "           1       0.84      0.94      0.89      1000\n",
      "           2       0.77      0.71      0.74      1000\n",
      "           3       0.79      0.55      0.65      1000\n",
      "           4       0.81      0.73      0.76      1000\n",
      "           5       0.83      0.65      0.73      1000\n",
      "           6       0.72      0.93      0.81      1000\n",
      "           7       0.78      0.90      0.84      1000\n",
      "           8       0.89      0.88      0.88      1000\n",
      "           9       0.79      0.89      0.83      1000\n",
      "\n",
      "    accuracy                           0.80     10000\n",
      "   macro avg       0.80      0.80      0.80     10000\n",
      "weighted avg       0.80      0.80      0.80     10000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(classification_report(y_true, y_pred_classes))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "16b54842",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step - accuracy: 0.7998 - loss: 0.5865\n",
      "Test loss: 0.586500883102417\n",
      "Test accuracy: 0.7997999787330627\n"
     ]
    }
   ],
   "source": [
    "# Score trained model.\n",
    "scores = model.evaluate(Xte, yte, verbose=1)\n",
    "print('Test loss:', scores[0])\n",
    "print('Test accuracy:', scores[1])\n",
    "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', \n",
    "               'dog', 'frog', 'horse', 'ship', 'truck']\n",
    "\n",
    "y_pred_labels = [class_names[i] for i in y_pred_classes]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}