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.
Getting started with neural networks: Classification and regression
Classifying movie reviews: A binary classification example
The IMDB dataset
Loading the IMDB dataset
from tensorflow.keras.datasets import imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(
num_words=10000)
train_data[0]
train_labels[0]
max([max(sequence) for sequence in train_data])
Decoding reviews back to text
word_index = imdb.get_word_index()
reverse_word_index = dict(
[(value, key) for (key, value) in word_index.items()])
decoded_review = " ".join(
[reverse_word_index.get(i - 3, "?") for i in train_data[0]])
Preparing the data
Encoding the integer sequences via multi-hot encoding
import numpy as np
def vectorize_sequences(sequences, dimension=10000):
results = np.zeros((len(sequences), dimension))
for i, sequence in enumerate(sequences):
for j in sequence:
results[i, j] = 1.
return results
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
x_train[0]
y_train = np.asarray(train_labels).astype("float32")
y_test = np.asarray(test_labels).astype("float32")
Building your model
Model definition
from tensorflow import keras
from tensorflow.keras import layers
model = keras.Sequential([
layers.Dense(16, activation="relu"),
layers.Dense(16, activation="relu"),
layers.Dense(1, activation="sigmoid")
])
Compiling the model
model.compile(optimizer="rmsprop",
loss="binary_crossentropy",
metrics=["accuracy"])
Validating your approach
Setting aside a validation set
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
Training your model
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))
history_dict = history.history
history_dict.keys()
Plotting the training and validation loss
import matplotlib.pyplot as plt
history_dict = history.history
loss_values = history_dict["loss"]
val_loss_values = history_dict["val_loss"]
epochs = range(1, len(loss_values) + 1)
plt.plot(epochs, loss_values, "bo", label="Training loss")
plt.plot(epochs, val_loss_values, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend()
plt.show()
Plotting the training and validation accuracy
plt.clf()
acc = history_dict["accuracy"]
val_acc = history_dict["val_accuracy"]
plt.plot(epochs, acc, "bo", label="Training acc")
plt.plot(epochs, val_acc, "b", label="Validation acc")
plt.title("Training and validation accuracy")
plt.xlabel("Epochs")
plt.ylabel("Accuracy")
plt.legend()
plt.show()
Retraining a model from scratch
model = keras.Sequential([
layers.Dense(16, activation="relu"),
layers.Dense(16, activation="relu"),
layers.Dense(1, activation="sigmoid")
])
model.compile(optimizer="rmsprop",
loss="binary_crossentropy",
metrics=["accuracy"])
model.fit(x_train, y_train, epochs=4, batch_size=512)
results = model.evaluate(x_test, y_test)
results
Using a trained model to generate predictions on new data
model.predict(x_test)
Further experiments
Wrapping up
Classifying newswires: A multiclass classification example
The Reuters dataset
Loading the Reuters dataset
from tensorflow.keras.datasets import reuters
(train_data, train_labels), (test_data, test_labels) = reuters.load_data(
num_words=10000)
len(train_data)
len(test_data)
train_data[10]
Decoding newswires back to text
word_index = reuters.get_word_index()
reverse_word_index = dict([(value, key) for (key, value) in
word_index.items()])
decoded_newswire = " ".join([reverse_word_index.get(i - 3, "?") for i in
train_data[0]])
train_labels[10]
Preparing the data
Encoding the input data
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
Encoding the labels
def to_one_hot(labels, dimension=46):
results = np.zeros((len(labels), dimension))
for i, label in enumerate(labels):
results[i, label] = 1.
return results
y_train = to_one_hot(train_labels)
y_test = to_one_hot(test_labels)
from tensorflow.keras.utils import to_categorical
y_train = to_categorical(train_labels)
y_test = to_categorical(test_labels)
Building your model
Model definition
model = keras.Sequential([
layers.Dense(64, activation="relu"),
layers.Dense(64, activation="relu"),
layers.Dense(46, activation="softmax")
])
Compiling the model
model.compile(optimizer="rmsprop",
loss="categorical_crossentropy",
metrics=["accuracy"])
Validating your approach
Setting aside a validation set
x_val = x_train[:1000]
partial_x_train = x_train[1000:]
y_val = y_train[:1000]
partial_y_train = y_train[1000:]
Training the model
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))
Plotting the training and validation loss
loss = history.history["loss"]
val_loss = history.history["val_loss"]
epochs = range(1, len(loss) + 1)
plt.plot(epochs, loss, "bo", label="Training loss")
plt.plot(epochs, val_loss, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend()
plt.show()
Plotting the training and validation accuracy
plt.clf()
acc = history.history["accuracy"]
val_acc = history.history["val_accuracy"]
plt.plot(epochs, acc, "bo", label="Training accuracy")
plt.plot(epochs, val_acc, "b", label="Validation accuracy")
plt.title("Training and validation accuracy")
plt.xlabel("Epochs")
plt.ylabel("Accuracy")
plt.legend()
plt.show()
Retraining a model from scratch
model = keras.Sequential([
layers.Dense(64, activation="relu"),
layers.Dense(64, activation="relu"),
layers.Dense(46, activation="softmax")
])
model.compile(optimizer="rmsprop",
loss="categorical_crossentropy",
metrics=["accuracy"])
model.fit(x_train,
y_train,
epochs=9,
batch_size=512)
results = model.evaluate(x_test, y_test)
results
import copy
test_labels_copy = copy.copy(test_labels)
np.random.shuffle(test_labels_copy)
hits_array = np.array(test_labels) == np.array(test_labels_copy)
hits_array.mean()
Generating predictions on new data
predictions = model.predict(x_test)
predictions[0].shape
np.sum(predictions[0])
np.argmax(predictions[0])
A different way to handle the labels and the loss
y_train = np.array(train_labels)
y_test = np.array(test_labels)
model.compile(optimizer="rmsprop",
loss="sparse_categorical_crossentropy",
metrics=["accuracy"])
The importance of having sufficiently large intermediate layers
A model with an information bottleneck
model = keras.Sequential([
layers.Dense(64, activation="relu"),
layers.Dense(4, activation="relu"),
layers.Dense(46, activation="softmax")
])
model.compile(optimizer="rmsprop",
loss="categorical_crossentropy",
metrics=["accuracy"])
model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=128,
validation_data=(x_val, y_val))
Further experiments
Wrapping up
Predicting house prices: A regression example
The Boston Housing Price dataset
Loading the Boston housing dataset
from tensorflow.keras.datasets import boston_housing
(train_data, train_targets), (test_data, test_targets) =
boston_housing.load_data()
train_data.shape
test_data.shape
train_targets
Preparing the data
Normalizing the data
mean = train_data.mean(axis=0)
train_data -= mean
std = train_data.std(axis=0)
train_data /= std
test_data -= mean
test_data /= std
Building your model
Model definition
def build_model():
model = keras.Sequential([
layers.Dense(64, activation="relu"),
layers.Dense(64, activation="relu"),
layers.Dense(1)
])
model.compile(optimizer="rmsprop", loss="mse", metrics=["mae"])
return model
Validating your approach using K-fold validation
K-fold validation
k = 4
num_val_samples = len(train_data) // k
num_epochs = 100
all_scores = []
for i in range(k):
print(f"Processing fold #{i}")
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) *
num_val_samples]
partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)
model = build_model()
model.fit(partial_train_data, partial_train_targets,
epochs=num_epochs, batch_size=16, verbose=0)
val_mse, val_mae = model.evaluate(val_data, val_targets, verbose=0)
all_scores.append(val_mae)
all_scores
np.mean(all_scores)
Saving the validation logs at each fold
num_epochs = 500
all_mae_histories = []
for i in range(k):
print(f"Processing fold #{i}")
val_data = train_data[i * num_val_samples: (i + 1) * num_val_samples]
val_targets = train_targets[i * num_val_samples: (i + 1) *
num_val_samples]
partial_train_data = np.concatenate(
[train_data[:i * num_val_samples],
train_data[(i + 1) * num_val_samples:]],
axis=0)
partial_train_targets = np.concatenate(
[train_targets[:i * num_val_samples],
train_targets[(i + 1) * num_val_samples:]],
axis=0)
model = build_model()
history = model.fit(partial_train_data, partial_train_targets,
validation_data=(val_data, val_targets),
epochs=num_epochs, batch_size=16, verbose=0)
mae_history = history.history["val_mae"]
all_mae_histories.append(mae_history)
Building the history of successive mean K-fold validation scores
average_mae_history = [
np.mean([x[i] for x in all_mae_histories]) for i in range(num_epochs)]
Plotting validation scores
plt.plot(range(1, len(average_mae_history) + 1), average_mae_history)
plt.xlabel("Epochs")
plt.ylabel("Validation MAE")
plt.show()
Plotting validation scores, excluding the first 10 data points
truncated_mae_history = average_mae_history[10:]
plt.plot(range(1, len(truncated_mae_history) + 1), truncated_mae_history)
plt.xlabel("Epochs")
plt.ylabel("Validation MAE")
plt.show()
Training the final model
model = build_model()
model.fit(train_data, train_targets,
epochs=130, batch_size=16, verbose=0)
test_mse_score, test_mae_score = model.evaluate(test_data, test_targets)
test_mae_score
Generating predictions on new data
predictions = model.predict(test_data)
predictions[0]
Wrapping up
Summary
