translate.py 文件源码

def run(self, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(sentence, self.en_vocab)
    # Which bucket does it belong to?
    bucket_id = min([b for b in xrange(len(_buckets))
                     if _buckets[b][0] > len(token_ids)])
    # Get a 1-element batch to feed the sentence to the model.
    encoder_inputs, decoder_inputs, target_weights = self.model.get_batch(
        {bucket_id: [(token_ids, [])]}, bucket_id)
    # Get output logits for the sentence.
    _, _, output_logits = self.model.step(self.sess, encoder_inputs, decoder_inputs,
                                     target_weights, bucket_id, True)
    # This is a greedy decoder - outputs are just argmaxes of output_logits.
    outputs = [int(np.argmax(logit, axis=1)) for logit in output_logits]
    # If there is an EOS symbol in outputs, cut them at that point.
    if data_utils.EOS_ID in outputs:
      outputs = outputs[:outputs.index(data_utils.EOS_ID)]
    # Print out French sentence corresponding to outputs.
    return "".join([self.rev_fr_vocab[output] for output in outputs])