execute.py 文件源码

def decode_input():
  with tf.Session() as sess:
    # Create model and load parameters.
    model = create_model(sess, True)
    model.batch_size = 1  # We decode one sentence at a time.

    # Load vocabularies.
    enc_vocab_path = os.path.join(gConfig['working_directory'],"vocab%d_enc.txt" % gConfig['enc_vocab_size'])
    dec_vocab_path = os.path.join(gConfig['working_directory'],"vocab%d_dec.txt" % gConfig['dec_vocab_size'])

    enc_vocab, _ = data_utils.initialize_vocabulary(enc_vocab_path)
    _, rev_dec_vocab = data_utils.initialize_vocabulary(dec_vocab_path)


    # Decode from standard input.
    sys.stdout.write("> ")
    sys.stdout.flush()
    sentence = sys.stdin.readline()

    while sentence:
      # Get token-ids for the input sentence.
      token_ids = data_utils.sentence_to_token_ids(sentence, enc_vocab)
      # Which bucket does it belong to? And place the sentence to the last bucket if its token length is larger then the bucket length.
      bucket_id = min([b for b in range(len(_buckets)) if _buckets[b][0] > len(token_ids)] + [len(_buckets)-1])
      # Get a 1-element batch to feed the sentence to the model.
      encoder_inputs, decoder_inputs, target_weights = model.get_batch(
          {bucket_id: [(token_ids, [])]}, bucket_id)
      # Get output logits for the sentence.
      _, _, output_logits = model.step(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.
      print(" ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs]))

      print("> ", end="")
      sys.stdout.flush()
      sentence = sys.stdin.readline()