Third edition

chapter09_convnet-architecture-patterns.ipynb

@@ -0,0 +1,356 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "This is a companion notebook for the book [Deep Learning with Python, Third Edition](TODO). For readability, it only contains runnable code blocks and section titles, and omits everything else in the book: text paragraphs, figures, and pseudocode.\n\n**If you want to be able to follow what's going on, I recommend reading the notebook side by side with your copy of the book.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "!pip install keras keras-hub --upgrade -q"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"KERAS_BACKEND\"] = \"jax\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Modularity, hierarchy, and reuse"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Residual connections"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "from keras import layers\n",
+    "\n",
+    "inputs = keras.Input(shape=(32, 32, 3))\n",
+    "x = layers.Conv2D(32, 3, activation=\"relu\")(inputs)\n",
+    "residual = x\n",
+    "x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
+    "residual = layers.Conv2D(64, 1)(residual)\n",
+    "x = layers.add([x, residual])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "inputs = keras.Input(shape=(32, 32, 3))\n",
+    "x = layers.Conv2D(32, 3, activation=\"relu\")(inputs)\n",
+    "residual = x\n",
+    "x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
+    "x = layers.MaxPooling2D(2, padding=\"same\")(x)\n",
+    "residual = layers.Conv2D(64, 1, strides=2)(residual)\n",
+    "x = layers.add([x, residual])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "inputs = keras.Input(shape=(32, 32, 3))\n",
+    "x = layers.Rescaling(1.0 / 255)(inputs)\n",
+    "\n",
+    "def residual_block(x, filters, pooling=False):\n",
+    "    residual = x\n",
+    "    x = layers.Conv2D(filters, 3, activation=\"relu\", padding=\"same\")(x)\n",
+    "    x = layers.Conv2D(filters, 3, activation=\"relu\", padding=\"same\")(x)\n",
+    "    if pooling:\n",
+    "        x = layers.MaxPooling2D(2, padding=\"same\")(x)\n",
+    "        residual = layers.Conv2D(filters, 1, strides=2)(residual)\n",
+    "    elif filters != residual.shape[-1]:\n",
+    "        residual = layers.Conv2D(filters, 1)(residual)\n",
+    "    x = layers.add([x, residual])\n",
+    "    return x\n",
+    "\n",
+    "x = residual_block(x, filters=32, pooling=True)\n",
+    "x = residual_block(x, filters=64, pooling=True)\n",
+    "x = residual_block(x, filters=128, pooling=False)\n",
+    "\n",
+    "x = layers.GlobalAveragePooling2D()(x)\n",
+    "outputs = layers.Dense(1, activation=\"sigmoid\")(x)\n",
+    "model = keras.Model(inputs=inputs, outputs=outputs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Batch normalization"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Depthwise separable convolutions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Putting it together: a mini Xception-like model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import kagglehub\n",
+    "\n",
+    "kagglehub.login()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import zipfile\n",
+    "\n",
+    "download_path = kagglehub.competition_download(\"dogs-vs-cats\")\n",
+    "\n",
+    "with zipfile.ZipFile(download_path + \"/train.zip\", \"r\") as zip_ref:\n",
+    "    zip_ref.extractall(\".\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import os, shutil, pathlib\n",
+    "from keras.utils import image_dataset_from_directory\n",
+    "\n",
+    "original_dir = pathlib.Path(\"train\")\n",
+    "new_base_dir = pathlib.Path(\"dogs_vs_cats_small\")\n",
+    "\n",
+    "def make_subset(subset_name, start_index, end_index):\n",
+    "    for category in (\"cat\", \"dog\"):\n",
+    "        dir = new_base_dir / subset_name / category\n",
+    "        os.makedirs(dir)\n",
+    "        fnames = [f\"{category}.{i}.jpg\" for i in range(start_index, end_index)]\n",
+    "        for fname in fnames:\n",
+    "            shutil.copyfile(src=original_dir / fname, dst=dir / fname)\n",
+    "\n",
+    "make_subset(\"train\", start_index=0, end_index=1000)\n",
+    "make_subset(\"validation\", start_index=1000, end_index=1500)\n",
+    "make_subset(\"test\", start_index=1500, end_index=2500)\n",
+    "\n",
+    "batch_size = 64\n",
+    "image_size = (180, 180)\n",
+    "train_dataset = image_dataset_from_directory(\n",
+    "    new_base_dir / \"train\",\n",
+    "    image_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    ")\n",
+    "validation_dataset = image_dataset_from_directory(\n",
+    "    new_base_dir / \"validation\",\n",
+    "    image_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    ")\n",
+    "test_dataset = image_dataset_from_directory(\n",
+    "    new_base_dir / \"test\",\n",
+    "    image_size=image_size,\n",
+    "    batch_size=batch_size,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf\n",
+    "from keras import layers\n",
+    "\n",
+    "data_augmentation_layers = [\n",
+    "    layers.RandomFlip(\"horizontal\"),\n",
+    "    layers.RandomRotation(0.1),\n",
+    "    layers.RandomZoom(0.2),\n",
+    "]\n",
+    "\n",
+    "def data_augmentation(images, targets):\n",
+    "    for layer in data_augmentation_layers:\n",
+    "        images = layer(images)\n",
+    "    return images, targets\n",
+    "\n",
+    "augmented_train_dataset = train_dataset.map(\n",
+    "    data_augmentation, num_parallel_calls=8\n",
+    ")\n",
+    "augmented_train_dataset = augmented_train_dataset.prefetch(tf.data.AUTOTUNE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "\n",
+    "inputs = keras.Input(shape=(180, 180, 3))\n",
+    "x = layers.Rescaling(1.0 / 255)(inputs)\n",
+    "x = layers.Conv2D(filters=32, kernel_size=5, use_bias=False)(x)\n",
+    "\n",
+    "for size in [32, 64, 128, 256, 512]:\n",
+    "    residual = x\n",
+    "\n",
+    "    x = layers.BatchNormalization()(x)\n",
+    "    x = layers.Activation(\"relu\")(x)\n",
+    "    x = layers.SeparableConv2D(size, 3, padding=\"same\", use_bias=False)(x)\n",
+    "\n",
+    "    x = layers.BatchNormalization()(x)\n",
+    "    x = layers.Activation(\"relu\")(x)\n",
+    "    x = layers.SeparableConv2D(size, 3, padding=\"same\", use_bias=False)(x)\n",
+    "\n",
+    "    x = layers.MaxPooling2D(3, strides=2, padding=\"same\")(x)\n",
+    "\n",
+    "    residual = layers.Conv2D(\n",
+    "        size, 1, strides=2, padding=\"same\", use_bias=False\n",
+    "    )(residual)\n",
+    "    x = layers.add([x, residual])\n",
+    "\n",
+    "x = layers.GlobalAveragePooling2D()(x)\n",
+    "x = layers.Dropout(0.5)(x)\n",
+    "outputs = layers.Dense(1, activation=\"sigmoid\")(x)\n",
+    "model = keras.Model(inputs=inputs, outputs=outputs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 0,
+   "metadata": {
+    "colab_type": "code"
+   },
+   "outputs": [],
+   "source": [
+    "model.compile(\n",
+    "    loss=\"binary_crossentropy\",\n",
+    "    optimizer=\"adam\",\n",
+    "    metrics=[\"accuracy\"],\n",
+    ")\n",
+    "history = model.fit(\n",
+    "    augmented_train_dataset,\n",
+    "    epochs=100,\n",
+    "    validation_data=validation_dataset,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Beyond convolution: Vision Transformers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text"
+   },
+   "source": [
+    "### Chapter summary"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "collapsed_sections": [],
+   "name": "chapter09_convnet-architecture-patterns",
+   "private_outputs": false,
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}