src/trainTFalexNet.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b6d99433",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "I0000 00:00:1773977883.073784   26353 cpu_feature_guard.cc:227] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from keras import layers, models\n",
    "import matplotlib.pyplot as plt\n",
    "from utils.load_data import load_local_cifar10, preprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bc20979b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/popboat/tensorflow_projects/AlexNet/load_data.py:18: VisibleDeprecationWarning: dtype(): align should be passed as Python or NumPy boolean but got `align=0`. Did you mean to pass a tuple to create a subarray type? (Deprecated NumPy 2.4)\n",
      "  batch = pickle.load(f, encoding='latin1')\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training shapes: (50000, 32, 32, 3), (50000, 10)\n",
      "Testing shapes: (10000, 32, 32, 3), (10000, 10)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/popboat/tensorflow_projects/AlexNet/load_data.py:26: VisibleDeprecationWarning: dtype(): align should be passed as Python or NumPy boolean but got `align=0`. Did you mean to pass a tuple to create a subarray type? (Deprecated NumPy 2.4)\n",
      "  batch = pickle.load(f, encoding='latin1')\n"
     ]
    }
   ],
   "source": [
    "(x_train, y_train), (x_test, y_test) = load_local_cifar10('cifar-10-batches-py')\n",
    "\n",
    "y_train = tf.keras.utils.to_categorical(y_train, 10)\n",
    "y_test = tf.keras.utils.to_categorical(y_test, 10)\n",
    "\n",
    "print(f\"Training shapes: {x_train.shape}, {y_train.shape}\")\n",
    "print(f\"Testing shapes: {x_test.shape}, {y_test.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4bd22bb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "BATCH_SIZE = 16\n",
    "\n",
    "train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))\n",
    "train_dataset = (train_dataset\n",
    "                 .shuffle(8000)\n",
    "                 .map(preprocess, num_parallel_calls=tf.data.AUTOTUNE)\n",
    "                 .batch(BATCH_SIZE)\n",
    "                 .prefetch(tf.data.AUTOTUNE))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "376a7629",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test))\n",
    "test_dataset = (test_dataset\n",
    "                .map(preprocess, num_parallel_calls=tf.data.AUTOTUNE)\n",
    "                .batch(BATCH_SIZE)\n",
    "                .prefetch(tf.data.AUTOTUNE))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "25866940",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d89c26d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/popboat/tensorflow_projects/myenv/lib/python3.12/site-packages/keras/src/layers/preprocessing/data_layer.py:95: 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__(**kwargs)\n",
      "/home/popboat/tensorflow_projects/myenv/lib/python3.12/site-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"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ random_flip (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">RandomFlip</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ random_rotation                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">RandomRotation</span>)                │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ random_zoom (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">RandomZoom</span>)        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">227</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">55</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">55</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">96</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">34,944</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">27</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">27</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">96</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">27</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">27</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">614,656</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">384</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">885,120</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">384</span>)    │     <span style=\"color: #00af00; text-decoration-color: #00af00\">1,327,488</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">884,992</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9216</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │    <span style=\"color: #00af00; text-decoration-color: #00af00\">37,752,832</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │    <span style=\"color: #00af00; text-decoration-color: #00af00\">16,781,312</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4096</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │        <span style=\"color: #00af00; text-decoration-color: #00af00\">40,970</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "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",
       "│ random_flip (\u001b[38;5;33mRandomFlip\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ random_rotation                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "│ (\u001b[38;5;33mRandomRotation\u001b[0m)                │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ random_zoom (\u001b[38;5;33mRandomZoom\u001b[0m)        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m227\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m55\u001b[0m, \u001b[38;5;34m55\u001b[0m, \u001b[38;5;34m96\u001b[0m)     │        \u001b[38;5;34m34,944\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m27\u001b[0m, \u001b[38;5;34m27\u001b[0m, \u001b[38;5;34m96\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;34m27\u001b[0m, \u001b[38;5;34m27\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m614,656\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m256\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;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m384\u001b[0m)    │       \u001b[38;5;34m885,120\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m384\u001b[0m)    │     \u001b[38;5;34m1,327,488\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m884,992\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m256\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;34m9216\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;34m4096\u001b[0m)           │    \u001b[38;5;34m37,752,832\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\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;34m4096\u001b[0m)           │    \u001b[38;5;34m16,781,312\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4096\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;34m40,970\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">58,322,314</span> (222.48 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m58,322,314\u001b[0m (222.48 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">58,322,314</span> (222.48 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m58,322,314\u001b[0m (222.48 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model = models.Sequential([\n",
    "    \tlayers.RandomFlip(\"horizontal\", input_shape=(227, 227, 3)),\n",
    "    \tlayers.RandomRotation(0.1),\n",
    "    \tlayers.RandomZoom(0.1),\n",
    "        layers.Conv2D(96, 11, strides=4, padding='valid', activation='relu', input_shape=(227, 227, 3)),\n",
    "        layers.MaxPooling2D(3, strides=2),\n",
    "        \n",
    "        layers.Conv2D(256, 5, strides=1, padding='same', activation='relu'),\n",
    "        layers.MaxPooling2D(3, strides=2),\n",
    "        \n",
    "        layers.Conv2D(384, 3, strides=1, padding='same', activation='relu'),\n",
    "        layers.Conv2D(384, 3, strides=1, padding='same', activation='relu'),\n",
    "        layers.Conv2D(256, 3, strides=1, padding='same', activation='relu'),\n",
    "        layers.MaxPooling2D(3, strides=2),\n",
    "        \n",
    "        layers.Flatten(),\n",
    "        \n",
    "        layers.Dense(4096, activation='relu'),\n",
    "        layers.Dropout(0.5),\n",
    "        layers.Dense(4096, activation='relu'),\n",
    "        layers.Dropout(0.5),\n",
    "        layers.Dense(10, activation='softmax')\n",
    "    ])\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "dfa678fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(\n",
    "    optimizer=tf.keras.optimizers.SGD(learning_rate=0.001, momentum=0.9),\n",
    "    loss='categorical_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ba1d4796",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m212s\u001b[0m 68ms/step - accuracy: 0.7707 - loss: 0.6613 - val_accuracy: 0.7908 - val_loss: 0.6233\n",
      "Epoch 2/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m215s\u001b[0m 69ms/step - accuracy: 0.7824 - loss: 0.6325 - val_accuracy: 0.8052 - val_loss: 0.5784\n",
      "Epoch 3/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m212s\u001b[0m 68ms/step - accuracy: 0.7927 - loss: 0.5994 - val_accuracy: 0.8021 - val_loss: 0.5787\n",
      "Epoch 4/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m227s\u001b[0m 73ms/step - accuracy: 0.8028 - loss: 0.5692 - val_accuracy: 0.8141 - val_loss: 0.5624\n",
      "Epoch 5/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m224s\u001b[0m 72ms/step - accuracy: 0.8112 - loss: 0.5449 - val_accuracy: 0.8182 - val_loss: 0.5353\n",
      "Epoch 6/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m223s\u001b[0m 71ms/step - accuracy: 0.8214 - loss: 0.5156 - val_accuracy: 0.8173 - val_loss: 0.5394\n",
      "Epoch 7/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m221s\u001b[0m 71ms/step - accuracy: 0.8267 - loss: 0.5026 - val_accuracy: 0.8293 - val_loss: 0.5179\n",
      "Epoch 8/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m218s\u001b[0m 70ms/step - accuracy: 0.8325 - loss: 0.4778 - val_accuracy: 0.8358 - val_loss: 0.4949\n",
      "Epoch 9/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m220s\u001b[0m 70ms/step - accuracy: 0.8405 - loss: 0.4610 - val_accuracy: 0.8327 - val_loss: 0.5024\n",
      "Epoch 10/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m223s\u001b[0m 71ms/step - accuracy: 0.8493 - loss: 0.4379 - val_accuracy: 0.8424 - val_loss: 0.4753\n",
      "Epoch 11/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m223s\u001b[0m 71ms/step - accuracy: 0.8548 - loss: 0.4208 - val_accuracy: 0.8425 - val_loss: 0.4792\n",
      "Epoch 12/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m212s\u001b[0m 68ms/step - accuracy: 0.8592 - loss: 0.4067 - val_accuracy: 0.8325 - val_loss: 0.5153\n",
      "Epoch 13/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m220s\u001b[0m 70ms/step - accuracy: 0.8647 - loss: 0.3895 - val_accuracy: 0.8405 - val_loss: 0.4925\n",
      "Epoch 14/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m223s\u001b[0m 71ms/step - accuracy: 0.8694 - loss: 0.3784 - val_accuracy: 0.8400 - val_loss: 0.4927\n",
      "Epoch 15/30\n",
      "\u001b[1m3125/3125\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m212s\u001b[0m 68ms/step - accuracy: 0.8735 - loss: 0.3633 - val_accuracy: 0.8399 - val_loss: 0.4853\n"
     ]
    }
   ],
   "source": [
    "early_stopping = tf.keras.callbacks.EarlyStopping(\n",
    "    monitor='val_loss', \n",
    "    patience=5,\n",
    "    restore_best_weights=True\n",
    ")\n",
    "\n",
    "history = model.fit(\n",
    "    train_dataset,\n",
    "    epochs=30,\n",
    "    validation_data=test_dataset,\n",
    "    callbacks=[early_stopping]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a60f6199",
   "metadata": {},
   "outputs": [],
   "source": [
    "acc = history.history['accuracy']\n",
    "val_acc = history.history['val_accuracy']\n",
    "loss = history.history['loss']\n",
    "val_loss = history.history['val_loss']\n",
    "\n",
    "epochs = range(1, len(acc) + 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "daf75b4b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.plot(epochs, loss, 'b-', label='Training Loss')\n",
    "plt.plot(epochs, val_loss, 'r-', label='Validation Loss')\n",
    "plt.title('Model Loss')\n",
    "plt.xlabel('Epochs')\n",
    "plt.ylabel('Loss')\n",
    "plt.legend()\n",
    "plt.grid(True, linestyle=':', alpha=0.6)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "953cfbf5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.plot(epochs, acc, 'b-', label='Training Acc')\n",
    "plt.plot(epochs, val_acc, 'r-', label='Validation Acc')\n",
    "plt.title('Model Acc')\n",
    "plt.xlabel('Epochs')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.legend()\n",
    "plt.grid(True, linestyle=':', alpha=0.6)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "a333362a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "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"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model saved successfully!\n"
     ]
    }
   ],
   "source": [
    "model.save('alexnet_cifar10_keras.h5')\n",
    "print(\"Model saved successfully!\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "myenv",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}