Python common_layers.shape_list方法代码示例

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def padded_accuracy_topk(predictions,
                         labels,
                         k,
                         weights_fn=common_layers.weights_nonzero):
  """Percentage of times that top-k predictions matches labels on non-0s."""
  with tf.variable_scope("padded_accuracy_topk", values=[predictions, labels]):
    padded_predictions, padded_labels = common_layers.pad_with_zeros(
        predictions, labels)
    weights = weights_fn(padded_labels)
    effective_k = tf.minimum(k,
                             common_layers.shape_list(padded_predictions)[-1])
    _, outputs = tf.nn.top_k(padded_predictions, k=effective_k)
    outputs = tf.to_int32(outputs)
    padded_labels = tf.to_int32(padded_labels)
    padded_labels = tf.expand_dims(padded_labels, axis=-1)
    padded_labels += tf.zeros_like(outputs)  # Pad to same shape.
    same = tf.to_float(tf.equal(outputs, padded_labels))
    same_topk = tf.reduce_sum(same, axis=-1)
    return same_topk, weights 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def _quantize(x, params, randomize=True):
  """Quantize x according to params, optionally randomizing the rounding."""
  if not params.quantize:
    return x

  if not randomize:
    return tf.bitcast(
        tf.cast(x / params.quantization_scale, tf.int16), tf.float16)

  abs_x = tf.abs(x)
  sign_x = tf.sign(x)
  y = abs_x / params.quantization_scale
  y = tf.floor(y + tf.random_uniform(common_layers.shape_list(x)))
  y = tf.minimum(y, tf.int16.max) * sign_x
  q = tf.bitcast(tf.cast(y, tf.int16), tf.float16)
  return q 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def decode_transformer(encoder_output, encoder_decoder_attention_bias, targets,
                       hparams, name):
  """Original Transformer decoder."""
  with tf.variable_scope(name):
    targets = common_layers.flatten4d3d(targets)

    decoder_input, decoder_self_bias = (
        transformer.transformer_prepare_decoder(targets, hparams))

    decoder_input = tf.nn.dropout(decoder_input,
                                  1.0 - hparams.layer_prepostprocess_dropout)

    decoder_output = transformer.transformer_decoder(
        decoder_input, encoder_output, decoder_self_bias,
        encoder_decoder_attention_bias, hparams)
    decoder_output = tf.expand_dims(decoder_output, axis=2)
    decoder_output_shape = common_layers.shape_list(decoder_output)
    decoder_output = tf.reshape(
        decoder_output, [decoder_output_shape[0], -1, 1, hparams.hidden_size])
    # Expand since t2t expects 4d tensors.
    return decoder_output 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def dense_bitwise_categorical_fun(action_space, config, observations):
  """Dense network with bitwise input and categorical output."""
  del config
  obs_shape = common_layers.shape_list(observations)
  x = tf.reshape(observations, [-1] + obs_shape[2:])

  with tf.variable_scope("network_parameters"):
    with tf.variable_scope("dense_bitwise"):
      x = discretization.int_to_bit_embed(x, 8, 32)
      flat_x = tf.reshape(
          x, [obs_shape[0], obs_shape[1],
              functools.reduce(operator.mul, x.shape.as_list()[1:], 1)])

      x = tf.contrib.layers.fully_connected(flat_x, 256, tf.nn.relu)
      x = tf.contrib.layers.fully_connected(flat_x, 128, tf.nn.relu)

      logits = tf.contrib.layers.fully_connected(x, action_space.n,
                                                 activation_fn=None)

      value = tf.contrib.layers.fully_connected(
          x, 1, activation_fn=None)[..., 0]
      policy = tf.contrib.distributions.Categorical(logits=logits)

  return NetworkOutput(policy, value, lambda a: a) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def add_depth_embedding(x):
  """Add n-dimensional embedding as the depth embedding (timing signal).

  Adds embeddings to represent the position of the step in the recurrent
  tower.

  Args:
    x: a tensor with shape [max_step, batch, length, depth]

  Returns:
    a Tensor the same shape as x.
  """
  x_shape = common_layers.shape_list(x)
  depth = x_shape[-1]
  num_steps = x_shape[0]
  shape = [num_steps, 1, 1, depth]
  depth_embedding = (
      tf.get_variable(
          "depth_embedding",
          shape,
          initializer=tf.random_normal_initializer(0, depth**-0.5)) * (depth**
                                                                       0.5))

  x += depth_embedding
  return x 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def decode(self, bottleneck):
    """Auto-decode from the bottleneck and return the result."""
    # Get the shape from bottleneck and num channels.
    shape = common_layers.shape_list(bottleneck)
    try:
      num_channels = self.hparams.problem.num_channels
    except AttributeError:
      num_channels = 1
    dummy_targets = tf.zeros(shape[:-1] + [num_channels])
    # Set the bottleneck to decode.
    if len(shape) > 4:
      bottleneck = tf.squeeze(bottleneck, axis=[1])
    bottleneck = 2 * bottleneck - 1  # Be -1/1 instead of 0/1.
    self._cur_bottleneck_tensor = bottleneck
    # Run decoding.
    res = self.infer({"targets": dummy_targets})
    self._cur_bottleneck_tensor = None
    return res 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def attention_lm_prepare_decoder(targets, hparams):
  """Prepare one shard of the model for the decoder.

  Args:
    targets: a Tensor.
    hparams: run hyperparameters

  Returns:
    decoder_input: a Tensor, bottom of decoder stack
    decoder_self_attention_bias: a Tensor, containing large negative values
    to implement masked attention and possibly biases for diagonal alignments
  """
  if hparams.prepend_mode == "prepend_inputs_full_attention":
    decoder_self_attention_bias = (
        common_attention.attention_bias_prepend_inputs_full_attention(
            common_attention.embedding_to_padding(targets)))
  else:
    decoder_self_attention_bias = (
        common_attention.attention_bias_lower_triangle(
            common_layers.shape_list(targets)[1]))
  decoder_input = common_layers.shift_right_3d(targets)
  if hparams.pos == "timing":
    decoder_input = common_attention.add_timing_signal_1d(decoder_input)
  return (decoder_input, decoder_self_attention_bias) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def shake_shake_skip_connection(x, output_filters, stride, is_training):
  """Adds a residual connection to the filter x for the shake-shake model."""
  curr_filters = common_layers.shape_list(x)[-1]
  if curr_filters == output_filters:
    return x
  stride_spec = [1, stride, stride, 1]
  # Skip path 1.
  path1 = tf.nn.avg_pool(x, [1, 1, 1, 1], stride_spec, "VALID")
  path1 = tf.layers.conv2d(
      path1, int(output_filters / 2), (1, 1), padding="SAME", name="path1_conv")

  # Skip path 2.
  pad_arr = [[0, 0], [0, 1], [0, 1], [0, 0]]  # First pad with 0's then crop.
  path2 = tf.pad(x, pad_arr)[:, 1:, 1:, :]
  path2 = tf.nn.avg_pool(path2, [1, 1, 1, 1], stride_spec, "VALID")
  path2 = tf.layers.conv2d(
      path2, int(output_filters / 2), (1, 1), padding="SAME", name="path2_conv")

  # Concat and apply BN.
  final_path = tf.concat(values=[path1, path2], axis=-1)
  final_path = tf.layers.batch_normalization(
      final_path, training=is_training, name="final_path_bn")
  return final_path 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def body(self, features):
    hparams = copy.copy(self._hparams)
    inputs = features["inputs"]
    targets = features["targets"]
    targets_shape = common_layers.shape_list(targets)
    if not (tf.get_variable_scope().reuse or
            hparams.mode == tf.contrib.learn.ModeKeys.INFER):
      tf.summary.image("targets", targets, max_outputs=1)

    decoder_input, rows, cols = cia.prepare_decoder(
        targets, hparams)
    # Add class label to decoder input.
    if not hparams.unconditional:
      decoder_input += tf.reshape(inputs,
                                  [targets_shape[0], 1, 1, hparams.hidden_size])

    decoder_output = cia.transformer_decoder_layers(
        decoder_input, None,
        hparams.num_decoder_layers,
        hparams,
        attention_type=hparams.dec_attention_type,
        name="decoder")

    output = cia.create_output(decoder_output, rows, cols, targets, hparams)
    return output 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def top(self, body_output, _):
    # TODO(lukaszkaiser): is this a universal enough way to get channels?
    num_channels = self._model_hparams.problem.num_channels
    with tf.variable_scope("rgb_softmax"):
      body_output_shape = common_layers.shape_list(body_output)
      reshape_shape = body_output_shape[:3]
      reshape_shape.extend([num_channels, self.top_dimensionality])
      res = tf.layers.dense(body_output, self.top_dimensionality * num_channels)
      res = tf.reshape(res, reshape_shape)
      if not tf.get_variable_scope().reuse:
        res_argmax = tf.argmax(res, axis=-1)
        tf.summary.image(
            "result",
            common_layers.tpu_safe_image_summary(res_argmax),
            max_outputs=1)
      return res 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def targets_bottom(self, x, summary_prefix="targets_bottom"):  # pylint: disable=arguments-differ
    inputs = x
    with tf.variable_scope(self.name, reuse=tf.AUTO_REUSE):
      common_layers.summarize_video(inputs, summary_prefix)
      inputs_shape = common_layers.shape_list(inputs)
      # We embed each of 256=self.top_dimensionality possible pixel values.
      embedding_var = tf.get_variable(
          "pixel_embedding",
          [self.top_dimensionality, self.PIXEL_EMBEDDING_SIZE])
      hot_inputs = tf.one_hot(tf.to_int32(inputs), self.top_dimensionality)
      hot_inputs = tf.reshape(hot_inputs, [-1, self.top_dimensionality])
      embedded = tf.matmul(hot_inputs, embedding_var)
      # Let's now merge all channels that were embedded into a single vector.
      merged_size = self.PIXEL_EMBEDDING_SIZE * inputs_shape[4]
      embedded = tf.reshape(embedded, inputs_shape[:4] + [merged_size])
      transposed = common_layers.time_to_channels(embedded)
      return tf.layers.dense(
          transposed,
          self._body_input_depth,
          name="merge_pixel_embedded_frames") 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def add_layer_timing_signal_learned_1d(x, layer, num_layers):
  """Add n-dimensional embedding as the layer (vertical) timing signal.

  Adds embeddings to represent the position of the layer in the tower.

  Args:
    x: a tensor with shape [batch, length, depth]
    layer: layer num
    num_layers: total number of layers

  Returns:
    a Tensor the same shape as x.
  """
  channels = common_layers.shape_list(x)[-1]
  signal = get_layer_timing_signal_learned_1d(channels, layer, num_layers)
  x += signal
  return x 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def add_positional_embedding(x, max_length, name, positions=None):
  """Add positional embedding.

  Args:
    x: a Tensor with shape [batch, length, depth]
    max_length: an integer.  static maximum size of any dimension.
    name: a name for this layer.
    positions: an optional tensor with shape [batch, length]

  Returns:
    a Tensor the same shape as x.
  """
  _, length, depth = common_layers.shape_list(x)
  var = tf.cast(tf.get_variable(name, [max_length, depth]), x.dtype)
  if positions is None:
    sliced = tf.cond(
        tf.less(length, max_length),
        lambda: tf.slice(var, [0, 0], [length, -1]),
        lambda: tf.pad(var, [[0, length - max_length], [0, 0]]))
    return x + tf.expand_dims(sliced, 0)
  else:
    return x + tf.gather(var, tf.to_int32(positions)) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def _relative_position_to_absolute_position_masked(x):
  """Helper to dot_product_self_attention_relative_v2.

  Rearrange an attention logits or weights Tensor.

  The dimensions of the input represent:
  [batch, heads, query_position, memory_position - query_position + length - 1]

  The dimensions of the output represent:
  [batch, heads, query_position, memory_position]

  Only works with masked_attention.  Undefined behavior for regions of the
  input where memory_position > query_position.

  Args:
    x: a Tensor with shape [batch, heads, length, length]

  Returns:
    a Tensor with shape [batch, heads, length, length]
  """
  batch, heads, length, _ = common_layers.shape_list(x)
  x = tf.pad(x, [[0, 0], [0, 0], [0, 0], [1, 0]])
  x = tf.reshape(x, [batch, heads, 1 + length, length])
  x = tf.slice(x, [0, 0, 1, 0], [-1, -1, -1, -1])
  return x 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import shape_list [as 别名]
def gather_indices_2d(x, block_shape, block_stride):
  """Getting gather indices."""
  # making an identity matrix kernel
  kernel = tf.eye(block_shape[0] * block_shape[1])
  kernel = reshape_range(kernel, 0, 1, [block_shape[0], block_shape[1], 1])
  # making indices [1, h, w, 1] to appy convs
  x_shape = common_layers.shape_list(x)
  indices = tf.range(x_shape[2] * x_shape[3])
  indices = tf.reshape(indices, [1, x_shape[2], x_shape[3], 1])
  indices = tf.nn.conv2d(
      tf.cast(indices, tf.float32),
      kernel,
      strides=[1, block_stride[0], block_stride[1], 1],
      padding="VALID")
  # making indices [num_blocks, dim] to gather
  dims = common_layers.shape_list(indices)[:3]
  if all([isinstance(dim, int) for dim in dims]):
    num_blocks = functools.reduce(operator.mul, dims, 1)
  else:
    num_blocks = tf.reduce_prod(dims)
  indices = tf.reshape(indices, [num_blocks, -1])
  return tf.cast(indices, tf.int32)