eec61d9d49
* Update mnist_transfer_cnn for new API * Update mnist_siamese_graph.py for new API * Refactor example a little bit for clarity * Update mnist_irnn.py for new API * Fix variable name * Update mnist_heirarchial_rnn.py for new api * Fix a few api calls i missed * Update mnist_acgan.py for new API * Fix variable name * Update imdb_cnn for new API * Update benchmark.py to work with new API * PEP8 fix * Change filter_length to kernel_size * Update imdb_cnn_lstm.py for new API * PEP8 indentation fix
78 lines
2.0 KiB
Python
78 lines
2.0 KiB
Python
'''Train a recurrent convolutional network on the IMDB sentiment
|
|
classification task.
|
|
|
|
Gets to 0.8498 test accuracy after 2 epochs. 41s/epoch on K520 GPU.
|
|
'''
|
|
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, 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)
|