wehub-resource-sync
381 lines
10 KiB
Plaintext
381 lines
10 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"This is a companion notebook for the book [Deep Learning with Python, Third Edition](https://www.manning.com/books/deep-learning-with-python-third-edition). 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.**\n\nThe book's contents are available online at [deeplearningwithpython.io](https://deeplearningwithpython.io)."
|
|
]
|
|
},
|
|
{
|
|
"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": "code",
|
|
"execution_count": 0,
|
|
"metadata": {
|
|
"cellView": "form",
|
|
"colab_type": "code"
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# @title\n",
|
|
"import os\n",
|
|
"from IPython.core.magic import register_cell_magic\n",
|
|
"\n",
|
|
"@register_cell_magic\n",
|
|
"def backend(line, cell):\n",
|
|
" current, required = os.environ.get(\"KERAS_BACKEND\", \"\"), line.split()[-1]\n",
|
|
" if current == required:\n",
|
|
" get_ipython().run_cell(cell)\n",
|
|
" else:\n",
|
|
" print(\n",
|
|
" f\"This cell requires the {required} backend. To run it, change KERAS_BACKEND to \"\n",
|
|
" f\"\\\"{required}\\\" at the top of the notebook, restart the runtime, and rerun the notebook.\"\n",
|
|
" )"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"## ConvNet architecture patterns"
|
|
]
|
|
},
|
|
{
|
|
"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"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
} |