wehub/fchollet--deep-learning-with-python-notebooks
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Packages Projects Releases Wiki Activity
Files
main
fchollet--deep-learning-wit…/chapter02_mathematical-building-blocks.ipynb
T
wehub-resource-sync 612b28061b chore: import upstream snapshot with attribution
2026-07-13 13:25:23 +08:00

1457 lines
29 KiB
Plaintext
Raw Permalink Blame History

{
"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\"] = \"tensorflow\""
]
},
{
"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": [
"## The mathematical building blocks of neural networks"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"### A first look at a neural network"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"from keras.datasets import mnist\n",
"\n",
"(train_images, train_labels), (test_images, test_labels) = mnist.load_data()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"len(train_labels)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_labels"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"test_images.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"len(test_labels)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"test_labels"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import keras\n",
"from keras import layers\n",
"\n",
"model = keras.Sequential(\n",
" [\n",
" layers.Dense(512, activation=\"relu\"),\n",
" layers.Dense(10, activation=\"softmax\"),\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model.compile(\n",
" optimizer=\"adam\",\n",
" loss=\"sparse_categorical_crossentropy\",\n",
" metrics=[\"accuracy\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images = train_images.reshape((60000, 28 * 28))\n",
"train_images = train_images.astype(\"float32\") / 255\n",
"test_images = test_images.reshape((10000, 28 * 28))\n",
"test_images = test_images.astype(\"float32\") / 255"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model.fit(train_images, train_labels, epochs=5, batch_size=128)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"test_digits = test_images[0:10]\n",
"predictions = model.predict(test_digits)\n",
"predictions[0]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"predictions[0].argmax()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"predictions[0][7]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"test_labels[0]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"test_loss, test_acc = model.evaluate(test_images, test_labels)\n",
"print(f\"test_acc: {test_acc}\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"### Data representations for neural networks"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Scalars (rank-0 tensors)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import numpy as np\n",
"x = np.array(12)\n",
"x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x.ndim"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Vectors (rank-1 tensors)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.array([12, 3, 6, 14, 7])\n",
"x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x.ndim"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Matrices (rank-2 tensors)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.array([[5, 78, 2, 34, 0],\n",
" [6, 79, 3, 35, 1],\n",
" [7, 80, 4, 36, 2]])\n",
"x.ndim"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Rank-3 tensors and higher-rank tensors"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.array([[[5, 78, 2, 34, 0],\n",
" [6, 79, 3, 35, 1],\n",
" [7, 80, 4, 36, 2]],\n",
" [[5, 78, 2, 34, 0],\n",
" [6, 79, 3, 35, 1],\n",
" [7, 80, 4, 36, 2]],\n",
" [[5, 78, 2, 34, 0],\n",
" [6, 79, 3, 35, 1],\n",
" [7, 80, 4, 36, 2]]])\n",
"x.ndim"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Key attributes"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"from keras.datasets import mnist\n",
"\n",
"(train_images, train_labels), (test_images, test_labels) = mnist.load_data()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images.ndim"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images.dtype"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"digit = train_images[4]\n",
"plt.imshow(digit, cmap=plt.cm.binary)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_labels[4]"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Manipulating tensors in NumPy"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"my_slice = train_images[10:100]\n",
"my_slice.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"my_slice = train_images[10:100, :, :]\n",
"my_slice.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"my_slice = train_images[10:100, 0:28, 0:28]\n",
"my_slice.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"my_slice = train_images[:, 14:, 14:]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"my_slice = train_images[:, 7:-7, 7:-7]"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### The notion of data batches"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"batch = train_images[:128]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"batch = train_images[128:256]"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"n = 3\n",
"batch = train_images[128 * n : 128 * (n + 1)]"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Real-world examples of data tensors"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Vector data"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Timeseries data or sequence data"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Image data"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Video data"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"### The gears of neural networks: Tensor operations"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Element-wise operations"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_relu(x):\n",
" assert len(x.shape) == 2\n",
" x = x.copy()\n",
" for i in range(x.shape[0]):\n",
" for j in range(x.shape[1]):\n",
" x[i, j] = max(x[i, j], 0)\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_add(x, y):\n",
" assert len(x.shape) == 2\n",
" assert x.shape == y.shape\n",
" x = x.copy()\n",
" for i in range(x.shape[0]):\n",
" for j in range(x.shape[1]):\n",
" x[i, j] += y[i, j]\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import time\n",
"\n",
"x = np.random.random((20, 100))\n",
"y = np.random.random((20, 100))\n",
"\n",
"t0 = time.time()\n",
"for _ in range(1000):\n",
" z = x + y\n",
" z = np.maximum(z, 0.0)\n",
"print(\"Took: {0:.2f} s\".format(time.time() - t0))"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"t0 = time.time()\n",
"for _ in range(1000):\n",
" z = naive_add(x, y)\n",
" z = naive_relu(z)\n",
"print(\"Took: {0:.2f} s\".format(time.time() - t0))"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Broadcasting"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"X = np.random.random((32, 10))\n",
"y = np.random.random((10,))"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"y = np.expand_dims(y, axis=0)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"Y = np.tile(y, (32, 1))"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_add_matrix_and_vector(x, y):\n",
" assert len(x.shape) == 2\n",
" assert len(y.shape) == 1\n",
" assert x.shape[1] == y.shape[0]\n",
" x = x.copy()\n",
" for i in range(x.shape[0]):\n",
" for j in range(x.shape[1]):\n",
" x[i, j] += y[j]\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import numpy as np\n",
"\n",
"x = np.random.random((64, 3, 32, 10))\n",
"y = np.random.random((32, 10))\n",
"z = np.maximum(x, y)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Tensor product"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.random.random((32,))\n",
"y = np.random.random((32,))\n",
"\n",
"z = np.matmul(x, y)\n",
"z = x @ y"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_vector_product(x, y):\n",
" assert len(x.shape) == 1\n",
" assert len(y.shape) == 1\n",
" assert x.shape[0] == y.shape[0]\n",
" z = 0.0\n",
" for i in range(x.shape[0]):\n",
" z += x[i] * y[i]\n",
" return z"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_matrix_vector_product(x, y):\n",
" assert len(x.shape) == 2\n",
" assert len(y.shape) == 1\n",
" assert x.shape[1] == y.shape[0]\n",
" z = np.zeros(x.shape[0])\n",
" for i in range(x.shape[0]):\n",
" for j in range(x.shape[1]):\n",
" z[i] += x[i, j] * y[j]\n",
" return z"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_matrix_vector_product(x, y):\n",
" z = np.zeros(x.shape[0])\n",
" for i in range(x.shape[0]):\n",
" z[i] = naive_vector_product(x[i, :], y)\n",
" return z"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"def naive_matrix_product(x, y):\n",
" assert len(x.shape) == 2\n",
" assert len(y.shape) == 2\n",
" assert x.shape[1] == y.shape[0]\n",
" z = np.zeros((x.shape[0], y.shape[1]))\n",
" for i in range(x.shape[0]):\n",
" for j in range(y.shape[1]):\n",
" row_x = x[i, :]\n",
" column_y = y[:, j]\n",
" z[i, j] = naive_vector_product(row_x, column_y)\n",
" return z"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Tensor reshaping"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"train_images = train_images.reshape((60000, 28 * 28))"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.array([[0., 1.],\n",
" [2., 3.],\n",
" [4., 5.]])\n",
"x.shape"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = x.reshape((6, 1))\n",
"x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = x.reshape((2, 3))\n",
"x"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"x = np.zeros((300, 20))\n",
"x = np.transpose(x)\n",
"x.shape"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Geometric interpretation of tensor operations"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### A geometric interpretation of deep learning"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"### The engine of neural networks: Gradient-based optimization"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### What's a derivative?"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Derivative of a tensor operation: The gradient"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Stochastic gradient descent"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Chaining derivatives: The Backpropagation algorithm"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### The chain rule"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Automatic differentiation with computation graphs"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"### Looking back at our first example"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"(train_images, train_labels), (test_images, test_labels) = mnist.load_data()\n",
"train_images = train_images.reshape((60000, 28 * 28))\n",
"train_images = train_images.astype(\"float32\") / 255\n",
"test_images = test_images.reshape((10000, 28 * 28))\n",
"test_images = test_images.astype(\"float32\") / 255"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model = keras.Sequential(\n",
" [\n",
" layers.Dense(512, activation=\"relu\"),\n",
" layers.Dense(10, activation=\"softmax\"),\n",
" ]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model.compile(\n",
" optimizer=\"adam\",\n",
" loss=\"sparse_categorical_crossentropy\",\n",
" metrics=[\"accuracy\"],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model.fit(\n",
" train_images,\n",
" train_labels,\n",
" epochs=5,\n",
" batch_size=128,\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Reimplementing our first example from scratch"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### A simple Dense class"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import keras\n",
"from keras import ops\n",
"\n",
"class NaiveDense:\n",
" def __init__(self, input_size, output_size, activation=None):\n",
" self.activation = activation\n",
" self.W = keras.Variable(\n",
" shape=(input_size, output_size), initializer=\"uniform\"\n",
" )\n",
" self.b = keras.Variable(shape=(output_size,), initializer=\"zeros\")\n",
"\n",
" def __call__(self, inputs):\n",
" x = ops.matmul(inputs, self.W)\n",
" x = x + self.b\n",
" if self.activation is not None:\n",
" x = self.activation(x)\n",
" return x\n",
"\n",
" @property\n",
" def weights(self):\n",
" return [self.W, self.b]"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### A simple Sequential class"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"class NaiveSequential:\n",
" def __init__(self, layers):\n",
" self.layers = layers\n",
"\n",
" def __call__(self, inputs):\n",
" x = inputs\n",
" for layer in self.layers:\n",
" x = layer(x)\n",
" return x\n",
"\n",
" @property\n",
" def weights(self):\n",
" weights = []\n",
" for layer in self.layers:\n",
" weights += layer.weights\n",
" return weights"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"model = NaiveSequential(\n",
" [\n",
" NaiveDense(input_size=28 * 28, output_size=512, activation=ops.relu),\n",
" NaiveDense(input_size=512, output_size=10, activation=ops.softmax),\n",
" ]\n",
")\n",
"assert len(model.weights) == 4"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### A batch generator"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"import math\n",
"\n",
"class BatchGenerator:\n",
" def __init__(self, images, labels, batch_size=128):\n",
" assert len(images) == len(labels)\n",
" self.index = 0\n",
" self.images = images\n",
" self.labels = labels\n",
" self.batch_size = batch_size\n",
" self.num_batches = math.ceil(len(images) / batch_size)\n",
"\n",
" def next(self):\n",
" images = self.images[self.index : self.index + self.batch_size]\n",
" labels = self.labels[self.index : self.index + self.batch_size]\n",
" self.index += self.batch_size\n",
" return images, labels"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Running one training step"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### The weight update step"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"learning_rate = 1e-3\n",
"\n",
"def update_weights(gradients, weights):\n",
" for g, w in zip(gradients, weights):\n",
" w.assign(w - g * learning_rate)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"from keras import optimizers\n",
"\n",
"optimizer = optimizers.SGD(learning_rate=1e-3)\n",
"\n",
"def update_weights(gradients, weights):\n",
" optimizer.apply_gradients(zip(gradients, weights))"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"##### Gradient computation"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"%%backend tensorflow\n",
"import tensorflow as tf\n",
"\n",
"x = tf.zeros(shape=())\n",
"with tf.GradientTape() as tape:\n",
" y = 2 * x + 3\n",
"grad_of_y_wrt_x = tape.gradient(y, x)"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"%%backend tensorflow\n",
"def one_training_step(model, images_batch, labels_batch):\n",
" with tf.GradientTape() as tape:\n",
" predictions = model(images_batch)\n",
" loss = ops.sparse_categorical_crossentropy(labels_batch, predictions)\n",
" average_loss = ops.mean(loss)\n",
" gradients = tape.gradient(average_loss, model.weights)\n",
" update_weights(gradients, model.weights)\n",
" return average_loss"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### The full training loop"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"%%backend tensorflow\n",
"def fit(model, images, labels, epochs, batch_size=128):\n",
" for epoch_counter in range(epochs):\n",
" print(f\"Epoch {epoch_counter}\")\n",
" batch_generator = BatchGenerator(images, labels)\n",
" for batch_counter in range(batch_generator.num_batches):\n",
" images_batch, labels_batch = batch_generator.next()\n",
" loss = one_training_step(model, images_batch, labels_batch)\n",
" if batch_counter % 100 == 0:\n",
" print(f\"loss at batch {batch_counter}: {loss:.2f}\")"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"%%backend tensorflow\n",
"from keras.datasets import mnist\n",
"\n",
"(train_images, train_labels), (test_images, test_labels) = mnist.load_data()\n",
"\n",
"train_images = train_images.reshape((60000, 28 * 28))\n",
"train_images = train_images.astype(\"float32\") / 255\n",
"test_images = test_images.reshape((10000, 28 * 28))\n",
"test_images = test_images.astype(\"float32\") / 255\n",
"\n",
"fit(model, train_images, train_labels, epochs=10, batch_size=128)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text"
},
"source": [
"#### Evaluating the model"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"colab_type": "code"
},
"outputs": [],
"source": [
"%%backend tensorflow\n",
"predictions = model(test_images)\n",
"predicted_labels = ops.argmax(predictions, axis=1)\n",
"matches = predicted_labels == test_labels\n",
"f\"accuracy: {ops.mean(matches):.2f}\""
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"name": "chapter02_mathematical-building-blocks",
"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
}
Reference in New Issue View Git Blame Copy Permalink