Files
deep-learning-with-python-n…/chapter09_part02_modern-convnet-architecture-patterns.ipynb
2021-06-25 14:03:50 -07:00

321 lines
8.7 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"This is a companion notebook for the book [Deep Learning with Python, Second Edition](https://www.manning.com/books/deep-learning-with-python-second-edition?a_aid=keras&a_bid=76564dff). 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\nThis notebook was generated for TensorFlow 2.6."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"## Modern 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": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"**Case where the target block changes the number of output filters**"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"from tensorflow import keras\n",
"from tensorflow.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": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"**Case where the target block includes a max pooling layer**"
]
},
{
"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./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)\n",
"model.summary()"
]
},
{
"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": [
"from google.colab import files\n",
"files.upload()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"!mkdir ~/.kaggle\n",
"!cp kaggle.json ~/.kaggle/\n",
"!chmod 600 ~/.kaggle/kaggle.json\n",
"!kaggle competitions download -c dogs-vs-cats\n",
"!unzip -qq train.zip"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import os, shutil, pathlib\n",
"from tensorflow.keras.utils import image_dataset_from_directory\n",
"\n",
"original_dir = pathlib.Path(\"train\")\n",
"new_base_dir = pathlib.Path(\"cats_vs_dogs_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,\n",
" 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",
"train_dataset = image_dataset_from_directory(\n",
" new_base_dir / \"train\",\n",
" image_size=(180, 180),\n",
" batch_size=32)\n",
"validation_dataset = image_dataset_from_directory(\n",
" new_base_dir / \"validation\",\n",
" image_size=(180, 180),\n",
" batch_size=32)\n",
"test_dataset = image_dataset_from_directory(\n",
" new_base_dir / \"test\",\n",
" image_size=(180, 180),\n",
" batch_size=32)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"data_augmentation = keras.Sequential(\n",
" [\n",
" layers.RandomFlip(\"horizontal\"),\n",
" layers.RandomRotation(0.1),\n",
" layers.RandomZoom(0.2),\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"inputs = keras.Input(shape=(180, 180, 3))\n",
"x = data_augmentation(inputs)\n",
"\n",
"x = layers.Rescaling(1./255)(x)\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)(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(loss=\"binary_crossentropy\",\n",
" optimizer=\"rmsprop\",\n",
" metrics=[\"accuracy\"])\n",
"history = model.fit(\n",
" train_dataset,\n",
" epochs=100,\n",
" validation_data=validation_dataset)"
]
}
],
"metadata": {
"colab": {
"collapsed_sections": [],
"name": "chapter09_part02_modern-convnet-architecture-patterns.i",
"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": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 0
}