Beam search decoder. Args: features: Dictionary of input Tensors. mode: train or eval. Keys from tf.estimator.ModeKeys. vocab: A list of strings of words in the vocabulary. encoder_outputs: output tensors from the encoder hps: Hyperparams. Returns: Decoder outputs
(features, mode, vocab, encoder_outputs, hps)
| 476 | |
| 477 | |
| 478 | def beam_decoder(features, mode, vocab, encoder_outputs, hps): |
| 479 | """Beam search decoder. |
| 480 | |
| 481 | Args: |
| 482 | features: Dictionary of input Tensors. |
| 483 | mode: train or eval. Keys from tf.estimator.ModeKeys. |
| 484 | vocab: A list of strings of words in the vocabulary. |
| 485 | encoder_outputs: output tensors from the encoder |
| 486 | hps: Hyperparams. |
| 487 | |
| 488 | Returns: |
| 489 | Decoder outputs |
| 490 | """ |
| 491 | assert mode is not tf_estimator.ModeKeys.TRAIN, "Not using beam in training." |
| 492 | embeddings = encoder_outputs.embeddings |
| 493 | mem_input = encoder_outputs.mem_input |
| 494 | batch_size = tensor_utils.shape(features["src_len"], 0) |
| 495 | |
| 496 | src_len, src_inputs = features["src_len"], features["src_inputs"] |
| 497 | src_mask = tf.sequence_mask(src_len, tf.shape(src_inputs)[1]) |
| 498 | |
| 499 | if hps.att_neighbor: |
| 500 | neighbor_len, neighbor_inputs \ |
| 501 | = features["neighbor_len"], features["neighbor_inputs"] |
| 502 | neighbor_mask = tf.sequence_mask( |
| 503 | neighbor_len, tf.shape(neighbor_inputs)[1]) |
| 504 | inputs = tf.concat([src_inputs, neighbor_inputs], 1) |
| 505 | # lens = src_len + neighbor_len |
| 506 | mask = tf.concat([src_mask, neighbor_mask], axis=1) |
| 507 | lens = tf.shape(mask)[1] * tf.ones([batch_size], tf.int32) |
| 508 | else: |
| 509 | inputs = features["src_inputs"] |
| 510 | lens = features["src_len"] |
| 511 | mask = src_mask |
| 512 | |
| 513 | sparse_inputs = None |
| 514 | float_mask = tf.cast(mask, dtype=tf.float32) |
| 515 | if hps.use_copy: |
| 516 | sparse_inputs = sparse_map( |
| 517 | tf.expand_dims(inputs, axis=2), |
| 518 | tf.expand_dims(float_mask, axis=2), |
| 519 | vocab.size()) |
| 520 | sparse_inputs = sparse_tile_batch(sparse_inputs, multiplier=hps.beam_width) |
| 521 | |
| 522 | tiled_mask = tf.contrib.seq2seq.tile_batch(mask, multiplier=hps.beam_width) |
| 523 | inputs = tf.contrib.seq2seq.tile_batch(inputs, multiplier=hps.beam_width) |
| 524 | lens = tf.contrib.seq2seq.tile_batch(lens, multiplier=hps.beam_width) |
| 525 | |
| 526 | def _beam_decode(cell): |
| 527 | """Beam decode.""" |
| 528 | with tf.variable_scope("beam_decoder"): |
| 529 | |
| 530 | initial_state = cell.zero_state( |
| 531 | batch_size=batch_size*hps.beam_width, dtype=tf.float32) |
| 532 | if hps.use_bridge: |
| 533 | h_state, c_state = encoder_outputs.states |
| 534 | h_state = tf.contrib.seq2seq.tile_batch( |
| 535 | h_state, multiplier=hps.beam_width) |
nothing calls this directly
no test coverage detected
searching dependent graphs…