i've been using following code tflearn examples:
""" simple example using lstm recurrent neural network classify imdb sentiment dataset. references: - long short term memory, sepp hochreiter & jurgen schmidhuber, neural computation 9(8): 1735-1780, 1997. - andrew l. maas, raymond e. daly, peter t. pham, dan huang, andrew y. ng, , christopher potts. (2011). learning word vectors sentiment analysis. 49th annual meeting of association computational linguistics (acl 2011). links: - http://deeplearning.cs.cmu.edu/pdfs/hochreiter97_lstm.pdf - http://ai.stanford.edu/~amaas/data/sentiment/ """ __future__ import division, print_function, absolute_import import os import tflearn tflearn.data_utils import to_categorical, pad_sequences tflearn.datasets import imdb # imdb dataset loading train, test, _ = imdb.load_data(path='imdb.pkl', n_words=100, valid_portion=0.1) trainx, trainy = train testx, testy = test # data preprocessing # sequence padding trainx = pad_sequences(trainx, maxlen=100, value=0.) testx = pad_sequences(testx, maxlen=100, value=0.) # converting labels binary vectors trainy = to_categorical(trainy, nb_classes=2) testy = to_categorical(testy, nb_classes=2) # network building net = tflearn.input_data([none, 100]) net = tflearn.embedding(net, input_dim=10000, output_dim=128) net = tflearn.lstm(net, 128) net = tflearn.fully_connected(net, 2, activation='softmax') net = tflearn.regression(net, optimizer='adam', learning_rate=0.001, loss='categorical_crossentropy') # training model = tflearn.dnn(net, tensorboard_verbose=0) model.fit(trainx, trainy, validation_set=(testx, testy), show_metric=true, batch_size=32) the model trains , manages 83% accuracy on test set. want apply trained model new unseen data.
for example, like: model.predict("i happy today") should return positive sentiment value.
i new tensorflow , python, since i've been using r sentiment analysis , looks using lstm model in tensorflow has higher accuracy i've used in past.
any appreciated.
Comments
Post a Comment