def predict(model, sentence):
model, vocab, setup = model
sentence = sentence.strip()
text = nlp_utils.normalize_text(sentence)
words = nlp_utils.split_text(text, char_based=setup['char_based'])
xs = nlp_utils.transform_to_array([words], vocab, with_label=False)
xs = nlp_utils.convert_seq(xs, device=-1, with_label=False) # todo use GPU
with chainer.using_config('train', False), chainer.no_backprop_mode():
prob = model.predict(xs, softmax=True)[0]
answer = int(model.xp.argmax(prob))
score = float(prob[answer])
return answer, score
def get_vectors(model, sentences):
model, vocab, setup = model
vectors = []
for sentence in sentences:
sentence = sentence.strip()
text = nlp_utils.normalize_text(sentence)
words = nlp_utils.split_text(text, char_based=setup['char_based'])
xs = nlp_utils.transform_to_array([words], vocab, with_label=False)
xs = nlp_utils.convert_seq(xs, device=-1,
with_label=False) # todo use GPU
with chainer.using_config('train', False), chainer.no_backprop_mode():
vector = model.encoder(xs)
vectors.append(vector.data[0])
vectors = numpy.asarray(vectors)
return vectors