In [1]:
import numpy as np
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
from keras.datasets import imdb
Train 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. Notes:
In [2]:
max_features=20000
maxlen = 100 # cut texts after this number of words (among top max_features most common words)
batch_size = 16
In [3]:
(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'
In [13]:
y_train
Out[13]:
In [10]:
print X_train[0]
print y_train[0]
print np.unique(y_train)
print len(X_train[0])
In [11]:
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
In [12]:
print X_train[0]
print y_train[0]
print np.unique(y_train)
print len(X_train[0])
In [23]:
print('Build model...')
model = Sequential()
model.add(Embedding(max_features, 256))
model.add(LSTM(256, 128)) # try using a GRU instead, for fun
model.add(Dropout(0.5))
model.add(Dense(128, 1))
model.add(Activation('sigmoid'))
In [24]:
# try using different optimizers and different optimizer configs
model.compile(loss='binary_crossentropy', optimizer='adam', class_mode="binary")
In [25]:
print "Train..."
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=5, validation_split=0.1, show_accuracy=True)
score = model.evaluate(X_test, y_test, batch_size=batch_size)
print 'Test score:', score
In [26]:
classes = model.predict_classes(X_test, batch_size=batch_size)
acc = np_utils.accuracy(classes, y_test)
print 'Test accuracy:', acc