62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
'''Train a Bidirectional LSTM on the IMDB sentiment classification task.
|
|
|
|
Output after 4 epochs on CPU: ~0.8146
|
|
Time per epoch on CPU (Core i7): ~150s.
|
|
'''
|
|
|
|
from __future__ import print_function
|
|
import numpy as np
|
|
np.random.seed(1337) # for reproducibility
|
|
|
|
from keras.preprocessing import sequence
|
|
from keras.models import Model
|
|
from keras.layers import Dense, Dropout, Embedding, LSTM, Input, merge
|
|
from keras.datasets import imdb
|
|
|
|
|
|
max_features = 20000
|
|
maxlen = 100 # cut texts after this number of words (among top max_features most common words)
|
|
batch_size = 32
|
|
|
|
print('Loading data...')
|
|
(X_train, y_train), (X_test, y_test) = imdb.load_data(nb_words=max_features,
|
|
test_split=0.2)
|
|
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)
|
|
|
|
|
|
# this is the placeholder tensor for the input sequences
|
|
sequence = Input(shape=(maxlen,), dtype='int32')
|
|
# this embedding layer will transform the sequences of integers
|
|
# into vectors of size 128
|
|
embedded = Embedding(max_features, 128, input_length=maxlen)(sequence)
|
|
|
|
# apply forwards LSTM
|
|
forwards = LSTM(64)(embedded)
|
|
# apply backwards LSTM
|
|
backwards = LSTM(64, go_backwards=True)(embedded)
|
|
|
|
# concatenate the outputs of the 2 LSTMs
|
|
merged = merge([forwards, backwards], mode='concat', concat_axis=-1)
|
|
after_dp = Dropout(0.5)(merged)
|
|
output = Dense(1, activation='sigmoid')(after_dp)
|
|
|
|
model = Model(input=sequence, output=output)
|
|
|
|
# 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,
|
|
nb_epoch=4,
|
|
validation_data=[X_test, y_test])
|