TensorFlow学习日记24

1. Addition RNN

解析：

# -*- coding: utf-8 -*-
'''
An implementation of sequence to sequence learning for performing addition
Padding is handled by using a repeated sentinel character (space)
'''

from __future__ import print_function
from keras.models import Sequential
from keras import layers
import numpy as np
from six.moves import range


class CharacterTable(object):
    """Given a set of characters:
    + Encode them to a one hot integer representation
    + Decode the one hot integer representation to their character output
    + Decode a vector of probabilities to their character output
    """

    def __init__(self, chars):
        """Initialize character table.

        # Arguments
            chars: Characters that can appear in the input.
        """
        self.chars = sorted(set(chars))
        self.char_indices = dict((c, i) for i, c in enumerate(self.chars))
        self.indices_char = dict((i, c) for i, c in enumerate(self.chars))

    def encode(self, C, num_rows):
        """One hot encode given string C.

        # Arguments
            num_rows: Number of rows in the returned one hot encoding. This is
                used to keep the # of rows for each data the same.
        """
        x = np.zeros((num_rows, len(self.chars)))
        for i, c in enumerate(C):
            x[i, self.char_indices[c]] = 1
        return x

    def decode(self, x, calc_argmax=True):
        if calc_argmax:
            x = x.argmax(axis=-1)
        return ''.join(self.indices_char[x] for x in x)


class colors:
    ok = '\033[92m'
    fail = '\033[91m'
    close = '\033[0m'


# Parameters for the model and dataset.
TRAINING_SIZE = 50000
DIGITS = 3
INVERT = True

# Maximum length of input is 'int + int' (e.g., '345+678'). Maximum length of
# int is DIGITS.
MAXLEN = DIGITS + 1 + DIGITS

# All the numbers, plus sign and space for padding.
chars = '0123456789+ '
ctable = CharacterTable(chars)

questions = []
expected = []
seen = set()
print('Generating data...')
while len(questions) < TRAINING_SIZE:
    f = lambda: int(''.join(np.random.choice(list('0123456789'))
                            for i in range(np.random.randint(1, DIGITS + 1))))
    a, b = f(), f()
    # Skip any addition questions we've already seen
    # Also skip any such that x+Y == Y+x (hence the sorting).
    key = tuple(sorted((a, b)))
    if key in seen:
        continue
    seen.add(key)
    # Pad the data with spaces such that it is always MAXLEN.
    q = '{}+{}'.format(a, b)
    query = q + ' ' * (MAXLEN - len(q))
    ans = str(a + b)
    # Answers can be of maximum size DIGITS + 1.
    ans += ' ' * (DIGITS + 1 - len(ans))
    if INVERT:
        # Reverse the query, e.g., '12+345  ' becomes '  543+21'. (Note the
        # space used for padding.)
        query = query[::-1]
    questions.append(query)
    expected.append(ans)
print('Total addition questions:', len(questions))

print('Vectorization...')
x = np.zeros((len(questions), MAXLEN, len(chars)), dtype=np.bool)
y = np.zeros((len(questions), DIGITS + 1, len(chars)), dtype=np.bool)
for i, sentence in enumerate(questions):
    x[i] = ctable.encode(sentence, MAXLEN)
for i, sentence in enumerate(expected):
    y[i] = ctable.encode(sentence, DIGITS + 1)

# Shuffle (x, y) in unison as the later parts of x will almost all be larger
# digits.
indices = np.arange(len(y))
np.random.shuffle(indices)
x = x[indices]
y = y[indices]

# Explicitly set apart 10% for validation data that we never train over.
split_at = len(x) - len(x) // 10
(x_train, x_val) = x[:split_at], x[split_at:]
(y_train, y_val) = y[:split_at], y[split_at:]

print('Training Data:')
print(x_train.shape)
print(y_train.shape)

print('Validation Data:')
print(x_val.shape)
print(y_val.shape)

# Try replacing GRU, or SimpleRNN.
RNN = layers.LSTM
HIDDEN_SIZE = 128
BATCH_SIZE = 128
LAYERS = 1

print('Build model...')
model = Sequential()
# "Encode" the input sequence using an RNN, producing an output of HIDDEN_SIZE.
# Note: In a situation where your input sequences have a variable length,
# use input_shape=(None, num_feature).
model.add(RNN(HIDDEN_SIZE, input_shape=(MAXLEN, len(chars))))
# As the decoder RNN's input, repeatedly provide with the last hidden state of
# RNN for each time step. Repeat 'DIGITS + 1' times as that's the maximum
# length of output, e.g., when DIGITS=3, max output is 999+999=1998.
model.add(layers.RepeatVector(DIGITS + 1))
# The decoder RNN could be multiple layers stacked or a single layer.
for _ in range(LAYERS):
    # By setting return_sequences to True, return not only the last output but
    # all the outputs so far in the form of (num_samples, timesteps,
    # output_dim). This is necessary as TimeDistributed in the below expects
    # the first dimension to be the timesteps.
    model.add(RNN(HIDDEN_SIZE, return_sequences=True))

# Apply a dense layer to the every temporal slice of an input. For each of step
# of the output sequence, decide which character should be chosen.
model.add(layers.TimeDistributed(layers.Dense(len(chars))))
model.add(layers.Activation('softmax'))
model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])
model.summary()

# Train the model each generation and show predictions against the validation
# dataset.
for iteration in range(1, 200):
    print()
    print('-' * 50)
    print('Iteration', iteration)
    model.fit(x_train, y_train,
              batch_size=BATCH_SIZE,
              epochs=1,
              validation_data=(x_val, y_val))
    # Select 10 samples from the validation set at random so we can visualize
    # errors.
    for i in range(10):
        ind = np.random.randint(0, len(x_val))
        rowx, rowy = x_val[np.array([ind])], y_val[np.array([ind])]
        preds = model.predict_classes(rowx, verbose=0)
        q = ctable.decode(rowx[0])
        correct = ctable.decode(rowy[0])
        guess = ctable.decode(preds[0], calc_argmax=False)
        print('Q', q[::-1] if INVERT else q)
        print('T', correct)
        if correct == guess:
            print(colors.ok + '☑' + colors.close, end=" ")
        else:
            print(colors.fail + '☒' + colors.close, end=" ")
        print(guess)
        print('---')

2. bAbI RNN

解析：

'''
Trains two recurrent neural networks based upon a story and a question.
The resulting merged vector is then queried to answer a range of bAbI tasks.
'''

from __future__ import print_function
from functools import reduce
import re
import tarfile

import numpy as np

from keras.utils.data_utils import get_file
from keras.layers.embeddings import Embedding
from keras import layers
from keras.layers import recurrent
from keras.models import Model
from keras.preprocessing.sequence import pad_sequences


def tokenize(sent):
    '''Return the tokens of a sentence including punctuation.

    >>> tokenize('Bob dropped the apple. Where is the apple?')
    ['Bob', 'dropped', 'the', 'apple', '.', 'Where', 'is', 'the', 'apple', '?']
    '''
    return [x.strip() for x in re.split('(\W+)?', sent) if x.strip()]


def parse_stories(lines, only_supporting=False):
    '''Parse stories provided in the bAbi tasks format

    If only_supporting is true,
    only the sentences that support the answer are kept.
    '''
    data = []
    story = []
    for line in lines:
        line = line.decode('utf-8').strip()
        nid, line = line.split(' ', 1)
        nid = int(nid)
        if nid == 1:
            story = []
        if '\t' in line:
            q, a, supporting = line.split('\t')
            q = tokenize(q)
            substory = None
            if only_supporting:
                # Only select the related substory
                supporting = map(int, supporting.split())
                substory = [story[i - 1] for i in supporting]
            else:
                # Provide all the substories
                substory = [x for x in story if x]
            data.append((substory, q, a))
            story.append('')
        else:
            sent = tokenize(line)
            story.append(sent)
    return data


def get_stories(f, only_supporting=False, max_length=None):
    '''Given a file name, read the file, retrieve the stories,
    and then convert the sentences into a single story.

    If max_length is supplied,
    any stories longer than max_length tokens will be discarded.
    '''
    data = parse_stories(f.readlines(), only_supporting=only_supporting)
    flatten = lambda data: reduce(lambda x, y: x + y, data)
    data = [(flatten(story), q, answer) for story, q, answer in data if
            not max_length or len(flatten(story)) < max_length]
    return data


def vectorize_stories(data, word_idx, story_maxlen, query_maxlen):
    xs = []
    xqs = []
    ys = []
    for story, query, answer in data:
        x = [word_idx[w] for w in story]
        xq = [word_idx[w] for w in query]
        # let's not forget that index 0 is reserved
        y = np.zeros(len(word_idx) + 1)
        y[word_idx[answer]] = 1
        xs.append(x)
        xqs.append(xq)
        ys.append(y)
    return pad_sequences(xs, maxlen=story_maxlen), pad_sequences(xqs, maxlen=query_maxlen), np.array(ys)


RNN = recurrent.LSTM
EMBED_HIDDEN_SIZE = 50
SENT_HIDDEN_SIZE = 100
QUERY_HIDDEN_SIZE = 100
BATCH_SIZE = 32
EPOCHS = 40
print('RNN / Embed / Sent / Query = {}, {}, {}, {}'.format(RNN,
                                                           EMBED_HIDDEN_SIZE,
                                                           SENT_HIDDEN_SIZE,
                                                           QUERY_HIDDEN_SIZE))

try:
    path = get_file('babi-tasks-v1-2.tar.gz',
                    origin='https://s3.amazonaws.com/text-datasets/babi_tasks_1-20_v1-2.tar.gz')
except:
    print('Error downloading dataset, please download it manually:\n'
          '$ wget http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz\n'
          '$ mv tasks_1-20_v1-2.tar.gz ~/.keras/datasets/babi-tasks-v1-2.tar.gz')
    raise
tar = tarfile.open(path)
# Default QA1 with 1000 samples
# challenge = 'tasks_1-20_v1-2/en/qa1_single-supporting-fact_{}.txt'
# QA1 with 10,000 samples
# challenge = 'tasks_1-20_v1-2/en-10k/qa1_single-supporting-fact_{}.txt'
# QA2 with 1000 samples
challenge = 'tasks_1-20_v1-2/en/qa2_two-supporting-facts_{}.txt'
# QA2 with 10,000 samples
# challenge = 'tasks_1-20_v1-2/en-10k/qa2_two-supporting-facts_{}.txt'
train = get_stories(tar.extractfile(challenge.format('train')))
test = get_stories(tar.extractfile(challenge.format('test')))

vocab = set()
for story, q, answer in train + test:
    vocab |= set(story + q + [answer])
vocab = sorted(vocab)

# Reserve 0 for masking via pad_sequences
vocab_size = len(vocab) + 1
word_idx = dict((c, i + 1) for i, c in enumerate(vocab))
story_maxlen = max(map(len, (x for x, _, _ in train + test)))
query_maxlen = max(map(len, (x for _, x, _ in train + test)))

x, xq, y = vectorize_stories(train, word_idx, story_maxlen, query_maxlen)
tx, txq, ty = vectorize_stories(test, word_idx, story_maxlen, query_maxlen)

print('vocab = {}'.format(vocab))
print('x.shape = {}'.format(x.shape))
print('xq.shape = {}'.format(xq.shape))
print('y.shape = {}'.format(y.shape))
print('story_maxlen, query_maxlen = {}, {}'.format(story_maxlen, query_maxlen))

print('Build model...')

sentence = layers.Input(shape=(story_maxlen,), dtype='int32')
encoded_sentence = layers.Embedding(vocab_size, EMBED_HIDDEN_SIZE)(sentence)
encoded_sentence = layers.Dropout(0.3)(encoded_sentence)

question = layers.Input(shape=(query_maxlen,), dtype='int32')
encoded_question = layers.Embedding(vocab_size, EMBED_HIDDEN_SIZE)(question)
encoded_question = layers.Dropout(0.3)(encoded_question)
encoded_question = RNN(EMBED_HIDDEN_SIZE)(encoded_question)
encoded_question = layers.RepeatVector(story_maxlen)(encoded_question)

merged = layers.add([encoded_sentence, encoded_question])
merged = RNN(EMBED_HIDDEN_SIZE)(merged)
merged = layers.Dropout(0.3)(merged)
preds = layers.Dense(vocab_size, activation='softmax')(merged)

model = Model([sentence, question], preds)
model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

print('Training')
model.fit([x, xq], y,
          batch_size=BATCH_SIZE,
          epochs=EPOCHS,
          validation_split=0.05)
loss, acc = model.evaluate([tx, txq], ty,
                           batch_size=BATCH_SIZE)
print('Test loss / test accuracy = {:.4f} / {:.4f}'.format(loss, acc))

3. bAbI Memory Network

解析：

'''
Trains a memory network on the bAbI dataset.
'''
from __future__ import print_function

from keras.models import Sequential, Model
from keras.layers.embeddings import Embedding
from keras.layers import Input, Activation, Dense, Permute, Dropout, add, dot, concatenate
from keras.layers import LSTM
from keras.utils.data_utils import get_file
from keras.preprocessing.sequence import pad_sequences
from functools import reduce
import tarfile
import numpy as np
import re


def tokenize(sent):
    '''Return the tokens of a sentence including punctuation.

    >>> tokenize('Bob dropped the apple. Where is the apple?')
    ['Bob', 'dropped', 'the', 'apple', '.', 'Where', 'is', 'the', 'apple', '?']
    '''
    return [x.strip() for x in re.split('(\W+)?', sent) if x.strip()]


def parse_stories(lines, only_supporting=False):
    '''Parse stories provided in the bAbi tasks format

    If only_supporting is true, only the sentences
    that support the answer are kept.
    '''
    data = []
    story = []
    for line in lines:
        line = line.decode('utf-8').strip()
        nid, line = line.split(' ', 1)
        nid = int(nid)
        if nid == 1:
            story = []
        if '\t' in line:
            q, a, supporting = line.split('\t')
            q = tokenize(q)
            substory = None
            if only_supporting:
                # Only select the related substory
                supporting = map(int, supporting.split())
                substory = [story[i - 1] for i in supporting]
            else:
                # Provide all the substories
                substory = [x for x in story if x]
            data.append((substory, q, a))
            story.append('')
        else:
            sent = tokenize(line)
            story.append(sent)
    return data


def get_stories(f, only_supporting=False, max_length=None):
    '''Given a file name, read the file,
    retrieve the stories,
    and then convert the sentences into a single story.

    If max_length is supplied,
    any stories longer than max_length tokens will be discarded.
    '''
    data = parse_stories(f.readlines(), only_supporting=only_supporting)
    flatten = lambda data: reduce(lambda x, y: x + y, data)
    data = [(flatten(story), q, answer) for story, q, answer in data if
            not max_length or len(flatten(story)) < max_length]
    return data


def vectorize_stories(data):
    inputs, queries, answers = [], [], []
    for story, query, answer in data:
        inputs.append([word_idx[w] for w in story])
        queries.append([word_idx[w] for w in query])
        answers.append(word_idx[answer])
    return (pad_sequences(inputs, maxlen=story_maxlen),
            pad_sequences(queries, maxlen=query_maxlen),
            np.array(answers))


try:
    path = get_file('babi-tasks-v1-2.tar.gz',
                    origin='https://s3.amazonaws.com/text-datasets/babi_tasks_1-20_v1-2.tar.gz')
except:
    print('Error downloading dataset, please download it manually:\n'
          '$ wget http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz\n'
          '$ mv tasks_1-20_v1-2.tar.gz ~/.keras/datasets/babi-tasks-v1-2.tar.gz')
    raise
tar = tarfile.open(path)

challenges = {
    # QA1 with 10,000 samples
    'single_supporting_fact_10k': 'tasks_1-20_v1-2/en-10k/qa1_single-supporting-fact_{}.txt',
    # QA2 with 10,000 samples
    'two_supporting_facts_10k': 'tasks_1-20_v1-2/en-10k/qa2_two-supporting-facts_{}.txt',
}
challenge_type = 'single_supporting_fact_10k'
challenge = challenges[challenge_type]

print('Extracting stories for the challenge:', challenge_type)
train_stories = get_stories(tar.extractfile(challenge.format('train')))
test_stories = get_stories(tar.extractfile(challenge.format('test')))

vocab = set()
for story, q, answer in train_stories + test_stories:
    vocab |= set(story + q + [answer])
vocab = sorted(vocab)

# Reserve 0 for masking via pad_sequences
vocab_size = len(vocab) + 1
story_maxlen = max(map(len, (x for x, _, _ in train_stories + test_stories)))
query_maxlen = max(map(len, (x for _, x, _ in train_stories + test_stories)))

print('-')
print('Vocab size:', vocab_size, 'unique words')
print('Story max length:', story_maxlen, 'words')
print('Query max length:', query_maxlen, 'words')
print('Number of training stories:', len(train_stories))
print('Number of test stories:', len(test_stories))
print('-')
print('Here\'s what a "story" tuple looks like (input, query, answer):')
print(train_stories[0])
print('-')
print('Vectorizing the word sequences...')

word_idx = dict((c, i + 1) for i, c in enumerate(vocab))
inputs_train, queries_train, answers_train = vectorize_stories(train_stories)
inputs_test, queries_test, answers_test = vectorize_stories(test_stories)

print('-')
print('inputs: integer tensor of shape (samples, max_length)')
print('inputs_train shape:', inputs_train.shape)
print('inputs_test shape:', inputs_test.shape)
print('-')
print('queries: integer tensor of shape (samples, max_length)')
print('queries_train shape:', queries_train.shape)
print('queries_test shape:', queries_test.shape)
print('-')
print('answers: binary (1 or 0) tensor of shape (samples, vocab_size)')
print('answers_train shape:', answers_train.shape)
print('answers_test shape:', answers_test.shape)
print('-')
print('Compiling...')

# placeholders
input_sequence = Input((story_maxlen,))
question = Input((query_maxlen,))

# encoders
# embed the input sequence into a sequence of vectors
input_encoder_m = Sequential()
input_encoder_m.add(Embedding(input_dim=vocab_size,
                              output_dim=64))
input_encoder_m.add(Dropout(0.3))
# output: (samples, story_maxlen, embedding_dim)

# embed the input into a sequence of vectors of size query_maxlen
input_encoder_c = Sequential()
input_encoder_c.add(Embedding(input_dim=vocab_size,
                              output_dim=query_maxlen))
input_encoder_c.add(Dropout(0.3))
# output: (samples, story_maxlen, query_maxlen)

# embed the question into a sequence of vectors
question_encoder = Sequential()
question_encoder.add(Embedding(input_dim=vocab_size,
                               output_dim=64,
                               input_length=query_maxlen))
question_encoder.add(Dropout(0.3))
# output: (samples, query_maxlen, embedding_dim)

# encode input sequence and questions (which are indices)
# to sequences of dense vectors
input_encoded_m = input_encoder_m(input_sequence)
input_encoded_c = input_encoder_c(input_sequence)
question_encoded = question_encoder(question)

# compute a 'match' between the first input vector sequence
# and the question vector sequence
# shape: `(samples, story_maxlen, query_maxlen)`
match = dot([input_encoded_m, question_encoded], axes=(2, 2))
match = Activation('softmax')(match)

# add the match matrix with the second input vector sequence
response = add([match, input_encoded_c])  # (samples, story_maxlen, query_maxlen)
response = Permute((2, 1))(response)  # (samples, query_maxlen, story_maxlen)

# concatenate the match matrix with the question vector sequence
answer = concatenate([response, question_encoded])

# the original paper uses a matrix multiplication for this reduction step.
# we choose to use a RNN instead.
answer = LSTM(32)(answer)  # (samples, 32)

# one regularization layer -- more would probably be needed.
answer = Dropout(0.3)(answer)
answer = Dense(vocab_size)(answer)  # (samples, vocab_size)
# we output a probability distribution over the vocabulary
answer = Activation('softmax')(answer)

# build the final model
model = Model([input_sequence, question], answer)
model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# train
model.fit([inputs_train, queries_train], answers_train,
          batch_size=32,
          epochs=120,
          validation_data=([inputs_test, queries_test], answers_test))

4. IMDB Bidirectional LSTM

解析：

'''
Train a Bidirectional LSTM on the IMDB sentiment classification task.
'''

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
# cut texts after this number of words
# (among top max_features most common words)
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'))

# try using different optimizers and different optimizer configs
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])

5. IMDB CNN

解析：

'''
This example demonstrates the use of Convolution1D for text classification.
'''

from __future__ import print_function

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import Embedding
from keras.layers import Conv1D, GlobalMaxPooling1D
from keras.datasets import imdb

# set parameters:
max_features = 5000
maxlen = 400
batch_size = 32
embedding_dims = 50
filters = 250
kernel_size = 3
hidden_dims = 250
epochs = 2

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)

print('Build model...')
model = Sequential()

# we start off with an efficient embedding layer which maps
# our vocab indices into embedding_dims dimensions
model.add(Embedding(max_features,
                    embedding_dims,
                    input_length=maxlen))
model.add(Dropout(0.2))

# we add a Convolution1D, which will learn filters
# word group filters of size filter_length:
model.add(Conv1D(filters,
                 kernel_size,
                 padding='valid',
                 activation='relu',
                 strides=1))
# we use max pooling:
model.add(GlobalMaxPooling1D())

# We add a vanilla hidden layer:
model.add(Dense(hidden_dims))
model.add(Dropout(0.2))
model.add(Activation('relu'))

# We project onto a single unit output layer, and squash it with a sigmoid:
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          validation_data=(x_test, y_test))

6. IMDB CNN LSTM

解析：

'''
Train a recurrent convolutional network on the IMDB sentiment classification task.
'''
from __future__ import print_function

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import Embedding
from keras.layers import LSTM
from keras.layers import Conv1D, MaxPooling1D
from keras.datasets import imdb

# Embedding
max_features = 20000
maxlen = 100
embedding_size = 128

# Convolution
kernel_size = 5
filters = 64
pool_size = 4

# LSTM
lstm_output_size = 70

# Training
batch_size = 30
epochs = 2

'''
Note:
batch_size is highly sensitive.
Only 2 epochs are needed as the dataset is very small.
'''

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)

print('Build model...')

model = Sequential()
model.add(Embedding(max_features, embedding_size, input_length=maxlen))
model.add(Dropout(0.25))
model.add(Conv1D(filters,
                 kernel_size,
                 padding='valid',
                 activation='relu',
                 strides=1))
model.add(MaxPooling1D(pool_size=pool_size))
model.add(LSTM(lstm_output_size))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

print('Train...')
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          validation_data=(x_test, y_test))
score, acc = model.evaluate(x_test, y_test, batch_size=batch_size)
print('Test score:', score)
print('Test accuracy:', acc)

参考文献：

[1] Keras Examples：https://github.com/fchollet/keras/tree/master/examples