def _predict(self, strings, beam_search=True):
if self._translation_model:
encoded = [
self._encoder.encode(translation_textcleaning(string)) + [1]
for string in strings
]
else:
encoded = self._encoder.encode(strings)
batch_x = pad_sentence_batch(encoded, 0)[0]
if beam_search:
output = 'beam'
else:
output = 'greedy'
r = self._execute(
inputs=[batch_x],
input_labels=['Placeholder'],
output_labels=[output],
)
p = r[output].tolist()
if self._translation_model:
result = []
for row in p:
result.append(
self._encoder.decode([i for i in row if i not in [0, 1]]))
else:
result = self._encoder.decode(p)
return result
def _translate(self, strings, beam_search=True):
encoded = [
self._tokenizer.encode(translation_textcleaning(string)) + [1]
for string in strings
]
if beam_search:
output = self._beam
else:
output = self._greedy
batch_x = pad_sentence_batch(encoded, 0)[0]
p = self._sess.run(output, feed_dict={self._X: batch_x}).tolist()
result = []
for row in p:
result.append(
self._tokenizer.decode([i for i in row if i not in [0, 1]]))
return result
def _translate(self, strings):
encoded = [
self._encoder.encode(translation_textcleaning(string)) + [1]
for string in strings
]
batch_x = pad_sequences(encoded, padding='post', maxlen=self._maxlen)
r = self._execute(
inputs=[batch_x],
input_labels=['Placeholder'],
output_labels=['logits'],
)
p = r['logits']
result = []
for r in p:
result.append(
self._encoder.decode([i for i in r.tolist() if i > 0]))
return result