85 lines
2.4 KiB
Python
85 lines
2.4 KiB
Python
from __future__ import absolute_import
|
|
from __future__ import print_function
|
|
import numpy as np
|
|
np.random.seed(1337) # for reproducibility
|
|
|
|
from keras.preprocessing import sequence
|
|
from keras.optimizers import SGD, RMSprop, Adagrad
|
|
from keras.utils import np_utils
|
|
from keras.models import Sequential
|
|
from keras.layers.core import Dense, Dropout, Activation
|
|
from keras.layers.embeddings import Embedding
|
|
from keras.layers.recurrent import LSTM, GRU, SimpleRNN
|
|
from keras.layers.convolutional import Convolution1D, MaxPooling1D
|
|
from keras.datasets import imdb
|
|
|
|
'''
|
|
Train a recurrent convolutional network on the IMDB sentiment classification task.
|
|
|
|
GPU command:
|
|
THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python imdb_lstm.py
|
|
|
|
Get to 0.8498 test accuracy after 2 epochs. 41s/epoch on K520 GPU.
|
|
'''
|
|
|
|
# Embedding
|
|
max_features = 20000
|
|
maxlen = 100
|
|
embedding_size = 128
|
|
|
|
# Convolution
|
|
filter_length = 3
|
|
nb_filter = 64
|
|
pool_length = 2
|
|
|
|
# LSTM
|
|
lstm_output_size = 70
|
|
|
|
# Training
|
|
batch_size = 30
|
|
nb_epoch = 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(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)
|
|
|
|
print('Build model...')
|
|
|
|
model = Sequential()
|
|
model.add(Embedding(max_features, embedding_size, input_length=maxlen))
|
|
model.add(Dropout(0.25))
|
|
model.add(Convolution1D(nb_filter=nb_filter,
|
|
filter_length=filter_length,
|
|
border_mode="valid",
|
|
activation="relu",
|
|
subsample_length=1))
|
|
model.add(MaxPooling1D(pool_length=pool_length))
|
|
model.add(LSTM(lstm_output_size))
|
|
model.add(Dense(1))
|
|
model.add(Activation('sigmoid'))
|
|
|
|
model.compile(loss='binary_crossentropy',
|
|
optimizer='adam',
|
|
class_mode="binary")
|
|
|
|
print("Train...")
|
|
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch,
|
|
validation_data=(X_test, y_test), show_accuracy=True)
|
|
score, acc = model.evaluate(X_test, y_test, batch_size=batch_size,
|
|
show_accuracy=True)
|
|
print('Test score:', score)
|
|
print('Test accuracy:', acc)
|