python类EOS_ID的实例源码

def test(self, sess, token_ids):
        # We decode one sentence at a time.
        token_ids = data_utils.padding(token_ids)
        target_ids = data_utils.padding([data_utils.GO_ID])
        y_ids = data_utils.padding([data_utils.EOS_ID])
        encoder_inputs, decoder_inputs, _, _ = data_utils.nextRandomBatch([(token_ids, target_ids, y_ids)], batch_size=1)
        prediction = sess.run(self.prediction, feed_dict={
            self.encoder_inputs: encoder_inputs,
            self.decoder_inputs: decoder_inputs
        })
        pred_max = tf.arg_max(prediction, 1)
        # prediction = tf.split(0, self.num_steps, prediction)
        # # This is a greedy decoder - outputs are just argmaxes of output_logits.
        # outputs = [int(np.argmax(predict)) for predict in prediction]
        # # 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)]
        return pred_max.eval()

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    #print(sentence)
    #token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_vocab)
    token_ids = data_utils.sentence_to_token_ids(sentence, enc_vocab)
    print(token_ids)
    # 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 = model.get_batch({bucket_id: [(token_ids, [])]}, bucket_id)


    _, _, 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)]


    return "".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def read_data(config, source_path, target_path, max_size=None):
    data_set = [[] for _ in config.buckets]
    with gfile.GFile(source_path, mode="r") as source_file:
        with gfile.GFile(target_path, mode="r") as target_file:
            source, target = source_file.readline(), target_file.readline()
            counter = 0
            while source and target and (not max_size or counter < max_size):
                counter += 1
                if counter % 100000 == 0:
                    print("reading data line %d" % counter)
                    sys.stdout.flush()
                source_ids = [int(x) for x in source.strip().split()]
                target_ids = [int(x) for x in target.strip().split()]
                target_ids.append(data_utils.EOS_ID)
                for bucket_id, (source_size, target_size) in enumerate(config.buckets):
                    if len(source_ids) < source_size and len(target_ids) < target_size:
                        data_set[bucket_id].append([source_ids, target_ids])
                        break
                source, target = source_file.readline(), target_file.readline()
    return data_set

def get_batch(self,data_set,batch_size,random=True):
        '''get a batch of data from a data_set and do all needed preprocess
        to make them usable for the model defined above'''
        if random:
            seqs = np.random.choice(data_set,size= batch_size)
        else:
            seqs = data_set[0:batch_size]
        encoder_inputs = np.zeros((batch_size,self.max_seq_length),dtype = int)
        decoder_inputs = np.zeros((batch_size,self.max_seq_length+2),dtype = int)
        encoder_lengths = np.zeros(batch_size)
        decoder_weights = np.zeros((batch_size,self.max_seq_length+2),dtype=float)
        for i,seq in enumerate(seqs):
            encoder_inputs[i] = np.array(list(reversed(seq))+[data_utils.PAD_ID]*(self.max_seq_length-len(seq)))
            decoder_inputs[i] = np.array([data_utils.GO_ID]+seq+[data_utils.EOS_ID]+[data_utils.PAD_ID]*(self.max_seq_length-len(seq)))
            encoder_lengths[i]= len(seq)
            decoder_weights[i,0:(len(seq)+1)]=1.0
        return np.transpose(encoder_inputs), np.transpose(decoder_inputs), encoder_lengths, np.transpose(decoder_weights)

def read_data(source_path, target_path, max_size=None):

  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def read_data(source_path, target_path, max_size=None):

  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

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])

def decode_line(sess, model, enc_vocab, rev_dec_vocab, sentence):
    # Get token-ids for the input sentence.
    token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), enc_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 = 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)]

    return " ".join([tf.compat.as_str(rev_dec_vocab[output]) for output in outputs])

def get_predicted_sentence(input_sentence, vocab, rev_vocab, model, sess):
    input_token_ids = data_utils.sentence_to_token_ids(input_sentence, vocab)
    print(input_token_ids)
    # Which bucket does it belong to?
    if len(input_token_ids)>=BUCKETS[-1][0]:
      input_token_ids = input_token_ids[:BUCKETS[-1][0]-1]
    bucket_id = min([b for b in xrange(len(BUCKETS)) if BUCKETS[b][0] > len(input_token_ids)])
    outputs = []

    feed_data = {bucket_id: [(input_token_ids, outputs)]}
    # Get a 1-element batch to feed the sentence to the model.
    encoder_inputs, decoder_inputs, target_weights = model.get_batch(feed_data, bucket_id)
    global_memory['inp']=1
    # Get output logits for the sentence.
    _,_,output_logits = model.step(sess, encoder_inputs, decoder_inputs, target_weights, bucket_id, forward_only=True,beam_search=True)
    #print('global_output:')
    #print(global_output)
    outputs = []
    # This is a greedy decoder - outputs are just argmaxes of output_logits.
    for logit in output_logits:
        selected_token_id = int(np.argmax(logit, axis=1))
        if selected_token_id == data_utils.EOS_ID:
                break
        else:
            outputs.append(selected_token_id)
    # Forming output sentence on natural language
    outputs = ' '.join([rev_vocab[i] for i in outputs])

    return outputs

def main(_):
    print("Loading vocabulary")
    cn_vocab_path = os.path.join(FLAGS.data_dir, "source_vocab.txt")
    en_vocab_path = os.path.join(FLAGS.data_dir, "target_vocab.txt")

    cn_vocab, _ = data_utils.initialize_vocabulary(cn_vocab_path)
    _, rev_en_vocab = data_utils.initialize_vocabulary(en_vocab_path)

    print("Building model...")
    config = tf.ConfigProto(allow_soft_placement=True)
    with tf.Session(config=config) as sess:
        model = create_model(sess, False)
        # Decode from standard input.
        sys.stdout.write("> ")
        sys.stdout.flush()
        sentence = sys.stdin.readline()
        while sentence:
            seg_list = jieba.lcut(sentence.strip())
            #print(" ".join(seg_list))
            token_ids = [cn_vocab.get(w.encode(encoding="utf-8"), data_utils.UNK_ID) for w in seg_list]
            #print(token_ids)
            outputs = model.test(sess, token_ids)
            outputs = outputs.tolist()
            if data_utils.EOS_ID in outputs:
                outputs = outputs[:outputs.index(data_utils.EOS_ID)]
            output = " ".join([tf.compat.as_str(rev_en_vocab[output]) for output in outputs])
            print(output.capitalize())
            print("> ")
            sys.stdout.flush()
            sentence = sys.stdin.readline()

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def decode():
  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.
    src_vocab_path = os.path.join(FLAGS.data_dir,
                                 "vocab%d.source" % FLAGS.src_vocab_size)
    tar_vocab_path = os.path.join(FLAGS.data_dir,
                                 "vocab%d.target" % FLAGS.tar_vocab_size)
    src_vocab, _ = data_utils.initialize_vocabulary(src_vocab_path)
    _, rev_tar_vocab = data_utils.initialize_vocabulary(tar_vocab_path)

    # Decode from standard input.
    sys.stdout.write("> ")
    sys.stdout.flush()
    sentence = sys.stdin.readline()
    tokenizer = data_utils.basic_char_tokenizer if FLAGS.char else None
    while sentence:
      # Get token-ids for the input sentence.
      token_ids = data_utils.sentence_to_token_ids(tf.compat.as_bytes(sentence), src_vocab, tokenizer)
      # 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 = 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 target-text sentence corresponding to outputs.
      print(("" if FLAGS.char else " ").join([tf.compat.as_str(rev_tar_vocab[output]) for output in outputs]))
      print("> ", end="")
      sys.stdout.flush()
      sentence = sys.stdin.readline()

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def decode():
  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.
    _, _, _, _, en_vocab_path, fr_vocab_path = data_utils.prepare_my_data(
      FLAGS.data_dir, FLAGS.en_vocab_size, FLAGS.fr_vocab_size)
    en_vocab, _ = data_utils.initialize_vocabulary(en_vocab_path)
    _, rev_fr_vocab = data_utils.initialize_vocabulary(fr_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(tf.compat.as_bytes(sentence), 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 = 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_fr_vocab[output]) for output in outputs]))
      print("> ", end="")
      sys.stdout.flush()
      sentence = sys.stdin.readline()

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 1000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def decode():
  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" % gConfig['enc_vocab_size'])
    dec_vocab_path = os.path.join(gConfig['working_directory'],"vocab%d.dec" % 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(tf.compat.as_bytes(sentence), enc_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 = 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()

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def decode():
  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" % gConfig['enc_vocab_size'])
    dec_vocab_path = os.path.join(gConfig['working_directory'],"vocab%d.dec" % 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(tf.compat.as_bytes(sentence), enc_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 = 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()

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with gfile.GFile(source_path, mode="r") as source_file:
    with gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with gfile.GFile(source_path, mode="r") as source_file:
    with gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set

def read_data(source_path, target_path, max_size=None):
  """Read data from source and target files and put into buckets.

  Args:
    source_path: path to the files with token-ids for the source language.
    target_path: path to the file with token-ids for the target language;
      it must be aligned with the source file: n-th line contains the desired
      output for n-th line from the source_path.
    max_size: maximum number of lines to read, all other will be ignored;
      if 0 or None, data files will be read completely (no limit).

  Returns:
    data_set: a list of length len(_buckets); data_set[n] contains a list of
      (source, target) pairs read from the provided data files that fit
      into the n-th bucket, i.e., such that len(source) < _buckets[n][0] and
      len(target) < _buckets[n][1]; source and target are lists of token-ids.
  """
  data_set = [[] for _ in _buckets]
  with tf.gfile.GFile(source_path, mode="r") as source_file:
    with tf.gfile.GFile(target_path, mode="r") as target_file:
      source, target = source_file.readline(), target_file.readline()
      counter = 0
      while source and target and (not max_size or counter < max_size):
        counter += 1
        if counter % 100000 == 0:
          print("  reading data line %d" % counter)
          sys.stdout.flush()
        source_ids = [int(x) for x in source.split()]
        target_ids = [int(x) for x in target.split()]
        target_ids.append(data_utils.EOS_ID)
        for bucket_id, (source_size, target_size) in enumerate(_buckets):
          if len(source_ids) < source_size and len(target_ids) < target_size:
            data_set[bucket_id].append([source_ids, target_ids])
            break
        source, target = source_file.readline(), target_file.readline()
  return data_set