57 lines (47 sloc) 1.93 KB
'''Trains a LSTM on the IMDB sentiment classification task.
The dataset is actually too small for LSTM to be of any advantage
compared to simpler, much faster methods such as TF-IDF + LogReg.
- RNNs are tricky. Choice of batch size is important,
choice of loss and optimizer is critical, etc.
Some configurations won't converge.
- LSTM loss decrease patterns during training can be quite different
from what you see with CNNs/MLPs/etc.
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, Activation, Embedding
from keras.layers import LSTM
from keras.datasets import imdb
max_features = 20000
maxlen = 80 # 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)
print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 128, dropout=0.2))
model.add(LSTM(128, dropout_W=0.2, dropout_U=0.2)) # try using a GRU instead, for fun
# try using different optimizers and different optimizer configs
print('Train...'), y_train, batch_size=batch_size, nb_epoch=15,
validation_data=(X_test, y_test))
score, acc = model.evaluate(X_test, y_test,
print('Test score:', score)
print('Test accuracy:', acc)