This is a companion notebook for the book Deep Learning with Python, Second Edition. For readability, it only contains runnable code blocks and section titles, and omits everything else in the book: text paragraphs, figures, and pseudocode.
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.
This notebook was generated for TensorFlow 2.6.
Instantiating a small convnet
from tensorflow import keras
from tensorflow.keras import layers
inputs = keras.Input(shape=(28, 28, 1))
x = layers.Conv2D(filters=32, kernel_size=3, activation="relu")(inputs)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=64, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=128, kernel_size=3, activation="relu")(x)
x = layers.Flatten()(x)
outputs = layers.Dense(10, activation="softmax")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
Displaying the model's summary
model.summary()
Training the convnet on MNIST images
from tensorflow.keras.datasets import mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype("float32") / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype("float32") / 255
model.compile(optimizer="rmsprop",
loss="sparse_categorical_crossentropy",
metrics=["accuracy"])
model.fit(train_images, train_labels, epochs=5, batch_size=64)
Evaluating the convnet
test_loss, test_acc = model.evaluate(test_images, test_labels)
print(f"Test accuracy: {test_acc:.3f}")
An incorrectly structured convnet missing its max-pooling layers
inputs = keras.Input(shape=(28, 28, 1))
x = layers.Conv2D(filters=32, kernel_size=3, activation="relu")(inputs)
x = layers.Conv2D(filters=64, kernel_size=3, activation="relu")(x)
x = layers.Conv2D(filters=128, kernel_size=3, activation="relu")(x)
x = layers.Flatten()(x)
outputs = layers.Dense(10, activation="softmax")(x)
model_no_max_pool = keras.Model(inputs=inputs, outputs=outputs)
model_no_max_pool.summary()
from google.colab import files
files.upload()
!mkdir ~/.kaggle
!cp kaggle.json ~/.kaggle/
!chmod 600 ~/.kaggle/kaggle.json
!kaggle competitions download -c dogs-vs-cats
!unzip -qq dogs-vs-cats.zip
!unzip -qq train.zip
Copying images to training, validation, and test directories
import os, shutil, pathlib
original_dir = pathlib.Path("train")
new_base_dir = pathlib.Path("cats_vs_dogs_small")
def make_subset(subset_name, start_index, end_index):
for category in ("cat", "dog"):
dir = new_base_dir / subset_name / category
os.makedirs(dir)
fnames = [f"{category}.{i}.jpg" for i in range(start_index, end_index)]
for fname in fnames:
shutil.copyfile(src=original_dir / fname,
dst=dir / fname)
make_subset("train", start_index=0, end_index=1000)
make_subset("validation", start_index=1000, end_index=1500)
make_subset("test", start_index=1500, end_index=2500)
Instantiating a small convnet for dogs vs. cats classification
from tensorflow import keras
from tensorflow.keras import layers
inputs = keras.Input(shape=(180, 180, 3))
x = layers.Rescaling(1./255)(inputs)
x = layers.Conv2D(filters=32, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=64, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=128, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=256, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=256, kernel_size=3, activation="relu")(x)
x = layers.Flatten()(x)
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
model.summary()
Configuring the model for training
model.compile(loss="binary_crossentropy",
optimizer="rmsprop",
metrics=["accuracy"])
Using image_dataset_from_directory
to read images
from tensorflow.keras.utils import image_dataset_from_directory
train_dataset = image_dataset_from_directory(
new_base_dir / "train",
image_size=(180, 180),
batch_size=32)
validation_dataset = image_dataset_from_directory(
new_base_dir / "validation",
image_size=(180, 180),
batch_size=32)
test_dataset = image_dataset_from_directory(
new_base_dir / "test",
image_size=(180, 180),
batch_size=32)
import numpy as np
import tensorflow as tf
random_numbers = np.random.normal(size=(1000, 16))
dataset = tf.data.Dataset.from_tensor_slices(random_numbers)
for i, element in enumerate(dataset):
print(element.shape)
if i >= 2:
break
batched_dataset = dataset.batch(32)
for i, element in enumerate(batched_dataset):
print(element.shape)
if i >= 2:
break
reshaped_dataset = dataset.map(lambda x: tf.reshape(x, (4, 4)))
for i, element in enumerate(reshaped_dataset):
print(element.shape)
if i >= 2:
break
Displaying the shapes of the data and labels yielded by the Dataset
for data_batch, labels_batch in train_dataset:
print("data batch shape:", data_batch.shape)
print("labels batch shape:", labels_batch.shape)
break
Fitting the model using a Dataset
callbacks = [
keras.callbacks.ModelCheckpoint(
filepath="convnet_from_scratch.keras",
save_best_only=True,
monitor="val_loss")
]
history = model.fit(
train_dataset,
epochs=30,
validation_data=validation_dataset,
callbacks=callbacks)
Displaying curves of loss and accuracy during training
import matplotlib.pyplot as plt
accuracy = history.history["accuracy"]
val_accuracy = history.history["val_accuracy"]
loss = history.history["loss"]
val_loss = history.history["val_loss"]
epochs = range(1, len(accuracy) + 1)
plt.plot(epochs, accuracy, "bo", label="Training accuracy")
plt.plot(epochs, val_accuracy, "b", label="Validation accuracy")
plt.title("Training and validation accuracy")
plt.legend()
plt.figure()
plt.plot(epochs, loss, "bo", label="Training loss")
plt.plot(epochs, val_loss, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.legend()
plt.show()
Evaluating the model on the test set
test_model = keras.models.load_model("convnet_from_scratch.keras")
test_loss, test_acc = test_model.evaluate(test_dataset)
print(f"Test accuracy: {test_acc:.3f}")
Define a data augmentation stage to add to an image model
data_augmentation = keras.Sequential(
[
layers.RandomFlip("horizontal"),
layers.RandomRotation(0.1),
layers.RandomZoom(0.2),
]
)
Displaying some randomly augmented training images
plt.figure(figsize=(10, 10))
for images, _ in train_dataset.take(1):
for i in range(9):
augmented_images = data_augmentation(images)
ax = plt.subplot(3, 3, i + 1)
plt.imshow(augmented_images[0].numpy().astype("uint8"))
plt.axis("off")
Defining a new convnet that includes image augmentation and dropout
inputs = keras.Input(shape=(180, 180, 3))
x = data_augmentation(inputs)
x = layers.Rescaling(1./255)(x)
x = layers.Conv2D(filters=32, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=64, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=128, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=256, kernel_size=3, activation="relu")(x)
x = layers.MaxPooling2D(pool_size=2)(x)
x = layers.Conv2D(filters=256, kernel_size=3, activation="relu")(x)
x = layers.Flatten()(x)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs=inputs, outputs=outputs)
model.compile(loss="binary_crossentropy",
optimizer="rmsprop",
metrics=["accuracy"])
Training the regularized convnet
callbacks = [
keras.callbacks.ModelCheckpoint(
filepath="convnet_from_scratch_with_augmentation.keras",
save_best_only=True,
monitor="val_loss")
]
history = model.fit(
train_dataset,
epochs=100,
validation_data=validation_dataset,
callbacks=callbacks)
Evaluating the model on the test set
test_model = keras.models.load_model(
"convnet_from_scratch_with_augmentation.keras")
test_loss, test_acc = test_model.evaluate(test_dataset)
print(f"Test accuracy: {test_acc:.3f}")
Instantiating the VGG16 convolutional base
conv_base = keras.applications.vgg16.VGG16(
weights="imagenet",
include_top=False,
input_shape=(180, 180, 3))
conv_base.summary()
Extracting the VGG16 features and corresponding labels
import numpy as np
def get_features_and_labels(dataset):
all_features = []
all_labels = []
for images, labels in dataset:
preprocessed_images = keras.applications.vgg16.preprocess_input(images)
features = conv_base.predict(preprocessed_images)
all_features.append(features)
all_labels.append(labels)
return np.concatenate(all_features), np.concatenate(all_labels)
train_features, train_labels = get_features_and_labels(train_dataset)
val_features, val_labels = get_features_and_labels(validation_dataset)
test_features, test_labels = get_features_and_labels(test_dataset)
train_features.shape
Defining and training the densely connected classifier
inputs = keras.Input(shape=(5, 5, 512))
x = layers.Flatten()(inputs)
x = layers.Dense(256)(x)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs, outputs)
model.compile(loss="binary_crossentropy",
optimizer="rmsprop",
metrics=["accuracy"])
callbacks = [
keras.callbacks.ModelCheckpoint(
filepath="feature_extraction.keras",
save_best_only=True,
monitor="val_loss")
]
history = model.fit(
train_features, train_labels,
epochs=20,
validation_data=(val_features, val_labels),
callbacks=callbacks)
Plotting the results
import matplotlib.pyplot as plt
acc = history.history["accuracy"]
val_acc = history.history["val_accuracy"]
loss = history.history["loss"]
val_loss = history.history["val_loss"]
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, "bo", label="Training accuracy")
plt.plot(epochs, val_acc, "b", label="Validation accuracy")
plt.title("Training and validation accuracy")
plt.legend()
plt.figure()
plt.plot(epochs, loss, "bo", label="Training loss")
plt.plot(epochs, val_loss, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.legend()
plt.show()
Instantiating and freezing the VGG16 convolutional base
conv_base = keras.applications.vgg16.VGG16(
weights="imagenet",
include_top=False)
conv_base.trainable = False
Printing the list of trainable weights before and after freezing
conv_base.trainable = True
print("This is the number of trainable weights "
"before freezing the conv base:", len(conv_base.trainable_weights))
conv_base.trainable = False
print("This is the number of trainable weights "
"after freezing the conv base:", len(conv_base.trainable_weights))
Adding a data augmentation stage and a classifier to the convolutional base
data_augmentation = keras.Sequential(
[
layers.RandomFlip("horizontal"),
layers.RandomRotation(0.1),
layers.RandomZoom(0.2),
]
)
inputs = keras.Input(shape=(180, 180, 3))
x = data_augmentation(inputs)
x = keras.applications.vgg16.preprocess_input(x)
x = conv_base(x)
x = layers.Flatten()(x)
x = layers.Dense(256)(x)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs, outputs)
model.compile(loss="binary_crossentropy",
optimizer="rmsprop",
metrics=["accuracy"])
callbacks = [
keras.callbacks.ModelCheckpoint(
filepath="feature_extraction_with_data_augmentation.keras",
save_best_only=True,
monitor="val_loss")
]
history = model.fit(
train_dataset,
epochs=50,
validation_data=validation_dataset,
callbacks=callbacks)
Evaluating the model on the test set
test_model = keras.models.load_model(
"feature_extraction_with_data_augmentation.keras")
test_loss, test_acc = test_model.evaluate(test_dataset)
print(f"Test accuracy: {test_acc:.3f}")
conv_base.summary()
Freezing all layers until the fourth from the last
conv_base.trainable = True
for layer in conv_base.layers[:-4]:
layer.trainable = False
Fine-tuning the model
model.compile(loss="binary_crossentropy",
optimizer=keras.optimizers.RMSprop(learning_rate=1e-5),
metrics=["accuracy"])
callbacks = [
keras.callbacks.ModelCheckpoint(
filepath="fine_tuning.keras",
save_best_only=True,
monitor="val_loss")
]
history = model.fit(
train_dataset,
epochs=30,
validation_data=validation_dataset,
callbacks=callbacks)
model = keras.models.load_model("fine_tuning.keras")
test_loss, test_acc = model.evaluate(test_dataset)
print(f"Test accuracy: {test_acc:.3f}")