f25e894558
* Add Bidirectional Wrapper * Fix example * Update wrappers.py * Add reverse op * Update tensorflow_backend.py * Update wrappers.py * Update test_wrappers.py * bug fix * Update test_wrappers.py * Update test_wrappers.py * bug fix * Add test for reverse op * Enable reverse along multiple axes * Update theano_backend.py * Update theano_backend.py * Update test_wrappers.py * Speed up tests * Validate merge_mode arg, Add None mode * Update test_wrappers.py * Update test_wrappers.py * Add properties; reverse -> backward * Bug fix * Resolve naming conflict * Whitespace fix * Update imdb_bidirectional_lstm.py * Fix imports
48 lines
1.5 KiB
Python
48 lines
1.5 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 Sequential
|
|
from keras.layers import Dense, Dropout, Embedding, LSTM, Input, Bidirectional
|
|
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)
|
|
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,
|
|
nb_epoch=4,
|
|
validation_data=[X_test, y_test])
|