无所不能的Embedding4 - Doc2vec第二弹[skip-thought & tf-Seq2Seq源码解析]

class SkipThoughtDataset(BaseDataset):
    def __init__(self, data_file, dict_file, epochs, batch_size, buffer_size, min_count, max_count,
                 special_token, max_len):
    ...
    def parse_example(self, line, prepend, append):
        features = {}
        tokens = tf.string_split([tf.string_strip(line)]).values

        if prepend:
            tokens = tf.concat([[self.special_token.SEQ_START], tokens], 0)
        if append:
            tokens = tf.concat([tokens, [self.special_token.SEQ_END]], 0)

        features['tokens'] = tokens
        features['seq_len'] = tf.size(tokens)
        return features
    ...

    def make_source_dataset(self, file_path, data_type, is_predict, word_table_func):
        prepend, append = self.prepend_append_logic(data_type, is_predict)

        dataset = tf.data.TextLineDataset(file_path).\
            map(lambda x: self.parse_example(x, prepend, append), num_parallel_calls=tf.data.experimental.AUTOTUNE).\
            map(lambda x: word_table_func(x), num_parallel_calls=tf.data.experimental.AUTOTUNE)

        return dataset

    def build_dataset(self, is_predict=0):
        def input_fn():
            word_table_func = self.word_table_lookup(self.build_wordtable())
            _ = self.build_tokentable() # initialize here to ensure lookup table is in the same graph

            encoder_source = self.make_source_dataset(self.data_file['encoder'], 'encoder', is_predict, word_table_func)
            decoder_source = self.make_source_dataset(self.data_file['decoder'], 'decoder', is_predict, word_table_func)

            dataset = tf.data.Dataset.zip((encoder_source, decoder_source)).\
                filter(self.sample_filter_logic)

            if not is_predict:
                dataset = dataset.\
                    repeat(self.epochs)

                dataset = dataset. \
                    padded_batch( batch_size=self.batch_size,
                                  padded_shapes=self.padded_shape,
                                  padding_values=self.padding_values,
                                  drop_remainder=True ). \
                    prefetch( tf.data.experimental.AUTOTUNE )
            else:
                dataset = dataset.batch(1)

            return dataset
        return input_fn

    def load_pretrain_embedding(self):
        if self.embedding is None:
            word_vector = gensim.downloader.load(PretrainModel)
            embedding = []
            for i in self._dictionary.keys():
                try:
                    embedding.append( word_vector.get_vector( i ) )
                except KeyError:
                    embedding.append( np.random.uniform(low=-0.1, high=0.1, size=300))
            self.embedding = np.array(embedding, dtype=np.float32)
        return self.embedding

def gru_encoder(input_emb, input_len, params):
    gru_cell = build_rnn_cell('gru', params)

    # state: batch_size * hidden_size, output: batch_size * max_len * hidden_size
    output, state = tf.nn.dynamic_rnn(
        cell=gru_cell, # one rnn units
        inputs=input_emb, # batch_size * max_len * feature_size
        sequence_length=input_len, # batch_size * seq_len
        initial_state=None,
        dtype=params['dtype'],
        time_major=False # whether reshape max_length to first dim
    )
    return ENCODER_OUTPUT(output=output, state=state)

def get_helper(encoder_output, input_emb, input_len, batch_size, embedding, mode, params):

    if mode == tf.estimator.ModeKeys.TRAIN:
        if params['conditional']:
            # conditional train helper with encoder output state as direct input
            # Reshape encoder state as auxiliary input: 1* batch_size * hidden -> batch_size * max_len * hidden
            decoder_length = tf.shape(input_emb)[1]
            state_shape = tf.shape(encoder_output.state)
            encoder_state = tf.tile(tf.reshape(encoder_output.state, [state_shape[1],
                                                                      state_shape[0],
                                                                      state_shape[2]]),
                                    [1, decoder_length, 1])
            input_emb = tf.concat([encoder_state, input_emb], axis=-1)

            helper = seq2seq.TrainingHelper( inputs=input_emb, # batch_size * max_len-1 * emb_size
                                             sequence_length=input_len-1, # exclude last token
                                             time_major=False,
                                             name='training_helper' )
    else:
        helper = seq2seq.GreedyEmbeddingHelper( embedding=embedding_func( embedding ),
                                                start_tokens=tf.fill([batch_size], params['start_token']),
                                                end_token=params['end_token'] )

    return helper
    
def get_decoder(decoder_cell, encoder_output, input_emb, input_len, embedding, output_layer, mode, params):
    batch_size = tf.shape(encoder_output.output)[0]
    if params['beam_width'] >1 :
        # If beam search multiple prediction are uesd at each time step
        decoder = seq2seq.BeamSearchDecoder( cell=decoder_cell,
                                             embedding=embedding_func( embedding ),
                                             initial_state=encoder_output,
                                             beam_width=params['beam_width'],
                                             start_tokens=tf.fill([batch_size], params['start_token']),
                                             end_token=params['end_token'],
                                             output_layer=output_layer )

    else:
        helper = get_helper(encoder_output, input_emb, input_len, batch_size, embedding, mode, params)

        decoder = seq2seq.BasicDecoder( cell=decoder_cell,
                                        helper=helper,
                                        initial_state=encoder_output.state,
                                        output_layer=output_layer )

    return decoder

def gru_decoder(encoder_output, input_emb, input_len, embedding, params, mode):
    gru_cell = build_rnn_cell( 'gru', params )

    if mode == tf.estimator.ModeKeys.TRAIN:
        max_iteration = None
    elif mode == tf.estimator.ModeKeys.EVAL:
        max_iteration = tf.reduce_max(input_len) # decode max sequence length(=padded_length)in EVAL
    else:
        max_iteration = params['max_decode_iter']  # decode pre-defined max_decode iter in predict

    output_layer=tf.layers.Dense(units=params['vocab_size'])  # used for infer helper sample or train loss calculation
    decoder = get_decoder(gru_cell, encoder_output, input_emb, input_len, embedding, output_layer, mode, params)

    output, state, seq_len = seq2seq.dynamic_decode(decoder=decoder,
                                                    output_time_major=False,
                                                    impute_finished=True,
                                                    maximum_iterations=max_iteration)

    return DECODER_OUTPUT(output=output, state = state, seq_len=seq_len)

def sequence_loss(logits, target, mask, mode):
    with tf.variable_scope('Sequence_loss_matrix'):
        n_class = tf.shape(logits)[2]
        decode_len = tf.shape(logits)[1] # used for infer only, max_len is determined by decoder
        logits = tf.reshape(logits, [-1, n_class])

        if mode == tf.estimator.ModeKeys.TRAIN:
            # In train, target
            target = tf.reshape(target[:, 1:], [-1]) # (batch * (padded_len-1)) * 1
        elif mode == tf.estimator.ModeKeys.EVAL:
            # In eval, target has paded_len, logits have decode_len
            target = tf.reshape(target[:, : decode_len], [-1]) # batch * (decode_len) *1
        else:
            raise Exception('sequence loss is only used in train or eval, not in pure prediction')
        loss_mat = tf.nn.sparse_softmax_cross_entropy_with_logits(labels = target, logits = logits)
        loss_mat = tf.multiply(loss_mat, tf.reshape(mask, [-1])) # apply padded mask on output loss
    return loss_mat
    
def agg_sequence_loss(loss_mat, mask,  axis):
    with tf.variable_scope('Loss_{}'.format(axis)):
        if axis == 'scaler':
            loss = tf.reduce_sum(loss_mat)
            n_sample = tf.reduce_sum(mask)
            loss = loss/n_sample
        else:
            loss_mat = tf.reshape(loss_mat, tf.shape(mask)) # (batch_size * max_len) * 1-> batch_size * max_len
            if axis == 'batch':
                loss = tf.reduce_sum(loss_mat, axis=1) # batch
                n_sample = tf.reduce_sum(mask, axis=1) # batch
                loss = tf.math.divide_no_nan(loss, n_sample) # batch
            elif axis == 'time':
                loss = tf.reduce_sum(loss_mat, axis=0) # max_len
                n_sample = tf.reduce_sum(mask, axis=0) # max_len
                loss = tf.math.divide_no_nan(loss, n_sample) # max_len
            else:
                raise Exception('Only scaler/batch/time are supported in axis param')
    return loss

class QuickThought(object):
    def __init__(self, params):
        self.params = params
        self.init()

    def init(self):
        with tf.variable_scope('embedding', reuse=tf.AUTO_REUSE):
            self.embedding = tf.get_variable(dtype = self.params['dtype'],
                                             initializer=tf.constant(self.params['pretrain_embedding']),
                                             name='word_embedding' )

            add_layer_summary(self.embedding.name, self.embedding)

    def build_model(self, features, labels, mode):
        encoder_output = self._encode(features)
        decoder_output = self._decode(encoder_output, labels, mode )

        loss_output = self.compute_loss( decoder_output, labels, mode )

        ...
    def _encode(self, features):
        with tf.variable_scope('encoding'):
            encoder = ENCODER_FAMILY[self.params['encoder_type']]

            seq_emb_input = tf.nn.embedding_lookup(self.embedding, features['tokens']) # batch_size * max_len * emb_size

            encoder_output = encoder(seq_emb_input, features['seq_len'], self.params) # batch_size
        return encoder_output

    def _decode(self, encoder_output, labels, mode):
        with tf.variable_scope('decoding'):
            decoder = DECODER_FAMILY[self.params['decoder_type']]

            if mode == tf.estimator.ModeKeys.TRAIN:
                seq_emb_output = tf.nn.embedding_lookup(self.embedding, labels['tokens']) # batch_size * max_len * emb_size
                input_len = labels['seq_len']
            elif mode == tf.estimator.ModeKeys.EVAL:
                seq_emb_output = None
                input_len = labels['seq_len']
            else:
                seq_emb_output = None
                input_len = None

            decoder_output = decoder(encoder_output, seq_emb_output, input_len,\
                                     self.embedding, self.params, mode)
        return decoder_output
    def compute_loss(self, decoder_output, labels, mode):
        with tf.variable_scope('compute_loss'):
            mask = sequence_mask(decoder_output, labels, self.params, mode)

            loss_mat = sequence_loss(logits=decoder_output.output.rnn_output,
                                     target=labels['tokens'],
                                     mask=mask,
                                     mode=mode)
            loss = []
            for axis in ['scaler', 'batch', 'time']:
                loss.append(agg_sequence_loss(loss_mat, mask, axis))

        return SEQ_LOSS_OUTPUT(loss_id=loss_mat,
                               loss_scaler=loss[0],
                               loss_per_batch=loss[1],
                               loss_per_time=loss[2])

def dynamic_rnn(cell, inputs, sequence_length=None, initial_state=None,
                dtype=None, parallel_iterations=None, swap_memory=False,
                time_major=False, scope=None):
    flat_input = nest.flatten(inputs)

    if not time_major:
      flat_input = [ops.convert_to_tensor(input_) for input_ in flat_input]
      flat_input = tuple(_transpose_batch_time(input_) for input_ in flat_input)

    batch_size = _best_effort_input_batch_size(flat_input)
    state = cell.zero_state(batch_size, dtype)

    inputs = nest.pack_sequence_as(structure=inputs, flat_sequence=flat_input)

    (outputs, final_state) = _dynamic_rnn_loop(
        cell,
        inputs,
        state,
        parallel_iterations=parallel_iterations,
        swap_memory=swap_memory,
        sequence_length=sequence_length,
        dtype=dtype)

    if not time_major:
      # (T,B,D) => (B,T,D)
      outputs = nest.map_structure(_transpose_batch_time, outputs)
    return (outputs, final_state)

  def _time_step(time, output_ta_t, state):

    input_t = tuple(ta.read(time) for ta in input_ta)
    input_t = nest.pack_sequence_as(structure=inputs, flat_sequence=input_t)
    call_cell = lambda: cell(input_t, state)

    if sequence_length is not None:
      (output, new_state) = _rnn_step(
          time=time,
          sequence_length=sequence_length,
          min_sequence_length=min_sequence_length,
          max_sequence_length=max_sequence_length,
          zero_output=zero_output,
          state=state,
          call_cell=call_cell,
          state_size=state_size,
          skip_conditionals=True)
    else:
      (output, new_state) = call_cell()

    # Pack state if using state tuples
    output = nest.flatten(output)
    output_ta_t = tuple(ta.write(time, out) for ta, out in zip(output_ta_t, output))

    return (time + 1, output_ta_t, new_state)

time_steps = input_shape[0]

if sequence_length is not None:
    min_sequence_length = math_ops.reduce_min(sequence_length)
    max_sequence_length = math_ops.reduce_max(sequence_length)
else:
    max_sequence_length = time_steps

loop_bound = math_ops.minimum(time_steps, math_ops.maximum(1, max_sequence_length))
        
  _, output_final_ta, final_state = control_flow_ops.while_loop(
      cond=lambda time, *_: time < loop_bound,
      body=_time_step,
      loop_vars=(time, output_ta, state),
      parallel_iterations=parallel_iterations,
      maximum_iterations=time_steps,
      swap_memory=swap_memory)

def initialize(self, name=None):
    return self._helper.initialize() + (self._initial_state,)

class BasicDecoderOutput(
    collections.namedtuple("BasicDecoderOutput", ("rnn_output", "sample_id"))):
  pass

class BasicDecoder(decoder.Decoder):
  """Basic sampling decoder."""

  def __init__(self, cell, helper, initial_state, output_layer=None):

  def step(self, time, inputs, state, name=None):
    with ops.name_scope(name, "BasicDecoderStep", (time, inputs, state)):
      cell_outputs, cell_state = self._cell(inputs, state)
      if self._output_layer is not None:
        cell_outputs = self._output_layer(cell_outputs)
      sample_ids = self._helper.sample(
          time=time, outputs=cell_outputs, state=cell_state)
      (finished, next_inputs, next_state) = self._helper.next_inputs(
          time=time,
          outputs=cell_outputs,
          state=cell_state,
          sample_ids=sample_ids)
    outputs = BasicDecoderOutput(cell_outputs, sample_ids)
    return (outputs, next_state, next_inputs, finished)

class TrainingHelper(Helper):

  def __init__(self, inputs, sequence_length, time_major=False, name=None):
    ...

  def initialize(self, name=None):
    with ops.name_scope(name, "TrainingHelperInitialize"):
      finished = math_ops.equal(0, self._sequence_length)
      all_finished = math_ops.reduce_all(finished)
      next_inputs = control_flow_ops.cond(
          all_finished, lambda: self._zero_inputs,
          lambda: nest.map_structure(lambda inp: inp.read(0), self._input_tas))
      return (finished, next_inputs)
      
  def next_inputs(self, time, outputs, state, name=None, **unused_kwargs):
    """next_inputs_fn for TrainingHelper."""
    with ops.name_scope(name, "TrainingHelperNextInputs",
                        [time, outputs, state]):
      next_time = time + 1
      finished = (next_time >= self._sequence_length)
      all_finished = math_ops.reduce_all(finished)
      def read_from_ta(inp):
        return inp.read(next_time)
      next_inputs = control_flow_ops.cond(
          all_finished, lambda: self._zero_inputs,
          lambda: nest.map_structure(read_from_ta, self._input_tas))
      return (finished, next_inputs, state)

- finished: 都是False，因为infer阶段不用判断input\_sequence长度
- next\_inputs: 返回start\_token对应的embedding，和训练保持一致sample返回sample_id

class GreedyEmbeddingHelper(Helper):
  def __init__(self, embedding, start_tokens, end_token):
    self._start_tokens = ops.convert_to_tensor(
        start_tokens, dtype=dtypes.int32, name="start_tokens")
    self._end_token = ops.convert_to_tensor(
        end_token, dtype=dtypes.int32, name="end_token")
    self._start_inputs = self._embedding_fn(self._start_tokens)
    。。。
  def sample(self, time, outputs, state, name=None):
    sample_ids = math_ops.cast(
        math_ops.argmax(outputs, axis=-1), dtypes.int32)
    return sample_ids

  def initialize(self, name=None):
    finished = array_ops.tile([False], [self._batch_size])
    return (finished, self._start_inputs)
    
  def next_inputs(self, time, outputs, state, sample_ids, name=None):
    finished = math_ops.equal(sample_ids, self._end_token)
    all_finished = math_ops.reduce_all(finished)
    next_inputs = control_flow_ops.cond(
        all_finished,
        lambda: self._start_inputs,
        lambda: self._embedding_fn(sample_ids))
    return (finished, next_inputs, state)

- initial\_finished, initial\_inputs, initial\_state是上面decoder的initialize返回
- initial\_time, initial\_sequennce=0
- initial\_output\_ta是每个elemennt都是batch \* decoder.output\_size的不定长TensorArray, 这里output\_size=(rnn\_output\_size,sample\_id\_shape),预测返回1个token的sample\_id\_shape都是scaler, 有output\_layer时rnn\_output\_size=output\_layer\_size, default= hidden\_sizecondition: 判断是否所有finished都为True，都遍历完则停止loop

-  step：调用Decoder进行每一步的decode计算

-  finished: 这里finished主要由三个逻辑判断（tracks\_own\_finished我没用过先忽略了哈哈）其余两个是：

    - helper的next\_inputs回传的finished：trainHelper判断输入sequence是否遍历完，GreedyEmbeddingHelper判断预测token是否为end\_token。
    - max\_iteration：只用于预测，为了避免预测token一直不是end\_token导致预测无限循环下去，设置一个最大预测长度，训练时max\_iteraion应该为空
-  sequence\_length: 记录实际预测sequence长度，没有finished的sequence+1

-  impute\_finished: 如果sequence已遍历完, 后面的output补0，后面的state不再计算直接pass through当前state

def body(time, outputs_ta, state, inputs, finished, sequence_lengths):
  (next_outputs, decoder_state, next_inputs,
   decoder_finished) = decoder.step(time, inputs, state)

  if maximum_iterations is not None:
    next_finished = math_ops.logical_or(
        next_finished, time + 1 >= maximum_iterations)
  next_sequence_lengths = array_ops.where(
      math_ops.logical_and(math_ops.logical_not(finished), next_finished),
      array_ops.fill(array_ops.shape(sequence_lengths), time + 1),
      sequence_lengths)

  # Zero out output values past finish
  if impute_finished:
    emit = nest.map_structure(
        lambda out, zero: array_ops.where(finished, zero, out),
        next_outputs,
        zero_outputs)
  else:
    emit = next_outputs

  # Copy through states past finish
  def _maybe_copy_state(new, cur):
    # TensorArrays and scalar states get passed through.
    if isinstance(cur, tensor_array_ops.TensorArray):
      pass_through = True
    else:
      new.set_shape(cur.shape)
      pass_through = (new.shape.ndims == 0)
    return new if pass_through else array_ops.where(finished, cur, new)

  if impute_finished:
    next_state = nest.map_structure(
        _maybe_copy_state, decoder_state, state)
  else:
    next_state = decoder_state

  outputs_ta = nest.map_structure(lambda ta, out: ta.write(time, out),
                                  outputs_ta, emit)
  return (time + 1, outputs_ta, next_state, next_inputs, next_finished,
          next_sequence_lengths)