在 IMDB 情感分类任务上训练双向 LSTM。

Output after 4 epochs on CPU: ~0.8146. Time per epoch on CPU (Core i7): ~150s.

在 CPU 上经过 4 个轮次后的输出：〜0.8146。 CPU（Core i7）上每个轮次的时间：〜150s。

from __future__ import print_function
import numpy as np

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Dropout, Embedding, LSTM, Bidirectional
from keras.datasets import imdb


max_features = 20000
# 在此数量的单词之后剪切文本（取最常见的 max_features 个单词）
maxlen = 100
batch_size = 32

print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
y_train = np.array(y_train)
y_test = np.array(y_test)

model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
model.add(Bidirectional(LSTM(64)))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

# 尝试使用不同的优化器和优化器配置
model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])

print('Train...')
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=4,
          validation_data=[x_test, y_test])