Keras学习教程五

原文地址：https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/4.4-overfitting-and-underfitting.ipynb

Overfitting and underfitting

以这种方式处理过度拟合的过程称为正则化。让我们回顾一些最常见的正则化技术，让我们将其应用到实践中，以改进前一章中的电影分类模型。

from keras.datasets import imdb import numpy as np  (train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)  def vectorize_sequences(sequences, dimension=10000):     # Create an all-zero matrix of shape (len(sequences), dimension)     results = np.zeros((len(sequences), dimension))     for i, sequence in enumerate(sequences):         results[i, sequence] = 1.  # set specific indices of results[i] to 1s     return results  # Our vectorized training data x_train = vectorize_sequences(train_data) # Our vectorized test data x_test = vectorize_sequences(test_data) # Our vectorized labels y_train = np.asarray(train_labels).astype('float32') y_test = np.asarray(test_labels).astype('float32')

战斗过度

减少网络的大小

让我们在我们的电影评论分类网络上试试这个。我们原来的网络是这样的：

from keras import models from keras import layers  original_model = models.Sequential() original_model.add(layers.Dense(16, activation='relu', input_shape=(10000,))) original_model.add(layers.Dense(16, activation='relu')) original_model.add(layers.Dense(1, activation='sigmoid'))  original_model.compile(optimizer='rmsprop',                        loss='binary_crossentropy',                        metrics=['acc'])

smaller_model = models.Sequential() smaller_model.add(layers.Dense(4, activation='relu', input_shape=(10000,))) smaller_model.add(layers.Dense(4, activation='relu')) smaller_model.add(layers.Dense(1, activation='sigmoid'))  smaller_model.compile(optimizer='rmsprop',                       loss='binary_crossentropy',                       metrics=['acc'])

original_hist = original_model.fit(x_train, y_train,                                    epochs=20,                                    batch_size=512,                                    validation_data=(x_test, y_test))

smaller_model_hist = smaller_model.fit(x_train, y_train,                                        epochs=20,                                        batch_size=512,                                        validation_data=(x_test, y_test))

epochs = range(1, 21) original_val_loss = original_hist.history['val_loss'] smaller_model_val_loss = smaller_model_hist.history['val_loss']  

 import matplotlib.pyplot as plt # b+ is for "blue cross" plt.plot(epochs, original_val_loss, 'b+', label='Original model') # "bo" is for "blue dot" plt.plot(epochs, smaller_model_val_loss, 'bo', label='Smaller model') plt.xlabel('Epochs') plt.ylabel('Validation loss') plt.legend() plt.show()

bigger_model = models.Sequential() bigger_model.add(layers.Dense(512, activation='relu', input_shape=(10000,))) bigger_model.add(layers.Dense(512, activation='relu')) bigger_model.add(layers.Dense(1, activation='sigmoid')) bigger_model.compile(optimizer='rmsprop',                      loss='binary_crossentropy',                      metrics=['acc'])

 bigger_model_hist = bigger_model.fit(x_train, y_train,                                      epochs=20,                                      batch_size=512,                                      validation_data=(x_test, y_test))

bigger_model_val_loss = bigger_model_hist.history['val_loss']  plt.plot(epochs, original_val_loss, 'b+', label='Original model') plt.plot(epochs, bigger_model_val_loss, 'bo', label='Bigger model') plt.xlabel('Epochs') plt.ylabel('Validation loss') plt.legend()  plt.show()

original_train_loss = original_hist.history['loss'] bigger_model_train_loss = bigger_model_hist.history['loss']  plt.plot(epochs, original_train_loss, 'b+', label='Original model') plt.plot(epochs, bigger_model_train_loss, 'bo', label='Bigger model') plt.xlabel('Epochs') plt.ylabel('Training loss') plt.legend()  plt.show()

增加体重正则化

from keras import regularizers  l2_model = models.Sequential() l2_model.add(layers.Dense(16, kernel_regularizer=regularizers.l2(0.001),                           activation='relu', input_shape=(10000,))) l2_model.add(layers.Dense(16, kernel_regularizer=regularizers.l2(0.001),                           activation='relu')) l2_model.add(layers.Dense(1, activation='sigmoid'))

l2_model.compile(optimizer='rmsprop',                  loss='binary_crossentropy',                  metrics=['acc'])

l2_model_hist = l2_model.fit(x_train, y_train,                              epochs=20,                              batch_size=512,                              validation_data=(x_test, y_test))

l2_model_val_loss = l2_model_hist.history['val_loss']  plt.plot(epochs, original_val_loss, 'b+', label='Original model') plt.plot(epochs, l2_model_val_loss, 'bo', label='L2-regularized model') plt.xlabel('Epochs') plt.ylabel('Validation loss') plt.legend()  plt.show()

from keras import regularizers  # L1 regularization regularizers.l1(0.001)  # L1 and L2 regularization at the same time regularizers.l1_l2(l1=0.001, l2=0.001)

添加丢失

# At training time: we drop out 50% of the units in the output layer_output *= np.randint(0, high=2, size=layer_output.shape)

# At test time: layer_output *= 0.5

# At training time: layer_output *= np.randint(0, high=2, size=layer_output.shape) # Note that we are scaling *up* rather scaling *down* in this case layer_output /= 0.5

model.add(layers.Dropout(0.5))

dpt_model = models.Sequential() dpt_model.add(layers.Dense(16, activation='relu', input_shape=(10000,))) dpt_model.add(layers.Dropout(0.5)) dpt_model.add(layers.Dense(16, activation='relu')) dpt_model.add(layers.Dropout(0.5)) dpt_model.add(layers.Dense(1, activation='sigmoid'))  dpt_model.compile(optimizer='rmsprop',                   loss='binary_crossentropy',                   metrics=['acc'])

 dpt_model_hist = dpt_model.fit(x_train, y_train,                                epochs=20,                                batch_size=512,                                validation_data=(x_test, y_test))

文章来源: Keras学习教程五