Python tensorflow.pad方法代码示例

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def forward(self):
        pad = [[self.lay.pad, self.lay.pad]] * 2;
        temp = tf.pad(self.inp.out, [[0, 0]] + pad + [[0, 0]])

        k = self.lay.w['kernels']
        ksz = self.lay.ksize
        half = int(ksz / 2)
        out = list()
        for i in range(self.lay.h_out):
            row_i = list()
            for j in range(self.lay.w_out):
                kij = k[i * self.lay.w_out + j]
                i_, j_ = i + 1 - half, j + 1 - half
                tij = temp[:, i_ : i_ + ksz, j_ : j_ + ksz,:]
                row_i.append(
                    tf.nn.conv2d(tij, kij, 
                        padding = 'VALID', 
                        strides = [1] * 4))
            out += [tf.concat(row_i, 2)]

        self.out = tf.concat(out, 1) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def _mapper(example_proto):
  features = {
      'samples': tf.FixedLenSequenceFeature([1], tf.float32, allow_missing=True),
      'label': tf.FixedLenSequenceFeature([], tf.string, allow_missing=True)
  }
  example = tf.parse_single_example(example_proto, features)

  wav = example['samples'][:, 0]

  wav = wav[:16384]
  wav_len = tf.shape(wav)[0]
  wav = tf.pad(wav, [[0, 16384 - wav_len]])

  label = tf.reduce_join(example['label'], 0)

  return wav, label 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def structure(self, input_tensor):
        """
        Args:
            input_tensor: NHWC
        """
        rnd = tf.random_uniform((), 135, 160, dtype=tf.int32)
        rescaled = tf.image.resize_images(
            input_tensor, [rnd, rnd], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
        h_rem = 160 - rnd
        w_rem = 160 - rnd
        pad_left = tf.random_uniform((), 0, w_rem, dtype=tf.int32)
        pad_right = w_rem - pad_left
        pad_top = tf.random_uniform((), 0, h_rem, dtype=tf.int32)
        pad_bottom = h_rem - pad_top
        padded = tf.pad(rescaled, [[0, 0], [pad_top, pad_bottom], [
                        pad_left, pad_right], [0, 0]])
        padded.set_shape((input_tensor.shape[0], 160, 160, 3))
        output = tf.cond(tf.random_uniform(shape=[1])[0] < tf.constant(0.9),
                         lambda: padded, lambda: input_tensor)
        return output 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def pitch_shift(
        spectrogram,
        semitone_shift=0.0,
        method=tf.image.ResizeMethod.BILINEAR):
    """ Pitch shift a spectrogram preserving shape in tensorflow. Note that
    this is an approximation in the frequency domain.

    :param spectrogram: Input spectrogram to be pitch shifted as tensor.
    :param semitone_shift: (Optional) Pitch shift in semitone, default to 0.0.
    :param mehtod: (Optional) Interpolation method, default to BILINEAR.
    :returns: Pitch shifted spectrogram (same shape as spectrogram).
    """
    factor = 2 ** (semitone_shift / 12.)
    T = tf.shape(spectrogram)[0]
    F = tf.shape(spectrogram)[1]
    F_ps = tf.cast(tf.cast(F, tf.float32) * factor, tf.int32)[0]
    ps_spec = tf.image.resize_images(
        spectrogram,
        [T, F_ps],
        method=method,
        align_corners=True)
    paddings = [[0, 0], [0, tf.maximum(0, F - F_ps)], [0, 0]]
    return tf.pad(ps_spec[:, :F, :], paddings, 'CONSTANT') 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def _conv(self, x, kernel_size, filters, strides, is_atrous=False):
    """Convolution."""

    padding = 'SAME'
    if not is_atrous and strides > 1:
      pad = kernel_size - 1
      pad_beg = pad // 2
      pad_end = pad - pad_beg
      if self._data_format == 'channels_first':
        x = tf.pad(x, [[0, 0], [0, 0], [pad_beg, pad_end], [pad_beg, pad_end]])
      else:
        x = tf.pad(x, [[0, 0], [pad_beg, pad_end], [pad_beg, pad_end], [0, 0]])
      padding = 'VALID'
    return tf.layers.conv2d(
        inputs=x,
        kernel_size=kernel_size,
        filters=filters,
        strides=strides,
        padding=padding,
        use_bias=False,
        data_format=self._data_format) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def _PadLabels2d(logits_size, labels):
  """Pads or slices the 2nd dimension of 2-d labels to match logits_size.

  Covers the case of 1-d softmax output, when labels is [batch, seq] and
  logits is [batch, seq, onehot]
  Args:
    logits_size: Tensor returned from tf.shape giving the target size.
    labels:      2-d, but not necessarily matching in size.

  Returns:
    labels: Resized by padding or clipping the last dimension to logits_size.
  """
  pad = logits_size - tf.shape(labels)[1]

  def _PadFn():
    return tf.pad(labels, [[0, 0], [0, pad]])

  def _SliceFn():
    return tf.slice(labels, [0, 0], [-1, logits_size])

  return tf.cond(tf.greater(pad, 0), _PadFn, _SliceFn) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def _padded_batched_proposals_indicator(self,
                                          num_proposals,
                                          max_num_proposals):
    """Creates indicator matrix of non-pad elements of padded batch proposals.

    Args:
      num_proposals: Tensor of type tf.int32 with shape [batch_size].
      max_num_proposals: Maximum number of proposals per image (integer).

    Returns:
      A Tensor of type tf.bool with shape [batch_size, max_num_proposals].
    """
    batch_size = tf.size(num_proposals)
    tiled_num_proposals = tf.tile(
        tf.expand_dims(num_proposals, 1), [1, max_num_proposals])
    tiled_proposal_index = tf.tile(
        tf.expand_dims(tf.range(max_num_proposals), 0), [batch_size, 1])
    return tf.greater(tiled_num_proposals, tiled_proposal_index) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def basic_block(input, in_features, out_features, stride, is_training, keep_prob):
  if stride == 1:
    shortcut = input
  else:
    shortcut = tf.nn.avg_pool(input, [ 1, stride, stride, 1 ], [1, stride, stride, 1 ], 'VALID')
    shortcut = tf.pad(shortcut, [[0, 0], [0, 0], [0, 0],
      [(out_features-in_features)//2, (out_features-in_features)//2]])
  current = conv2d(input, in_features, out_features, 3, stride)
  current = tf.nn.dropout(current, keep_prob)
  current = tf.contrib.layers.batch_norm(current, scale=True, is_training=is_training, updates_collections=None)
  current = tf.nn.relu(current)
  current = conv2d(current, out_features, out_features, 3, 1)
  current = tf.nn.dropout(current, keep_prob)
  current = tf.contrib.layers.batch_norm(current, scale=True, is_training=is_training, updates_collections=None)
  # No final relu as per http://torch.ch/blog/2016/02/04/resnets.html
  return current + shortcut 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [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: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def bytenet_internal(inputs, targets, hparams):
  """ByteNet, main step used for training."""
  with tf.variable_scope("bytenet"):
    # Flatten inputs and extend length by 50%.
    inputs = tf.expand_dims(common_layers.flatten4d3d(inputs), axis=2)
    extend_length = tf.to_int32(0.5 * tf.to_float(tf.shape(inputs)[1]))
    inputs_shape = inputs.shape.as_list()
    inputs = tf.pad(inputs, [[0, 0], [0, extend_length], [0, 0], [0, 0]])
    inputs_shape[1] = None
    inputs.set_shape(inputs_shape)  # Don't lose the other shapes when padding.
    # Pad inputs and targets to be the same length, divisible by 50.
    inputs, targets = common_layers.pad_to_same_length(
        inputs, targets, final_length_divisible_by=50)
    final_encoder = residual_dilated_conv(inputs, hparams.num_block_repeat,
                                          "SAME", "encoder", hparams)

    shifted_targets = common_layers.shift_right(targets)
    kernel = (hparams.kernel_height, hparams.kernel_width)
    decoder_start = common_layers.conv_block(
        tf.concat([final_encoder, shifted_targets], axis=3),
        hparams.hidden_size, [((1, 1), kernel)],
        padding="LEFT")

    return residual_dilated_conv(decoder_start, hparams.num_block_repeat,
                                 "LEFT", "decoder", hparams) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def pool(inputs, window_size, pooling_type, padding, strides=(1, 1)):
  """Pooling (supports "LEFT")."""
  with tf.name_scope("pool", values=[inputs]):
    static_shape = inputs.get_shape()
    if not static_shape or len(static_shape) != 4:
      raise ValueError("Inputs to conv must have statically known rank 4.")
    # Add support for left padding.
    if padding == "LEFT":
      assert window_size[0] % 2 == 1 and window_size[1] % 2 == 1
      if len(static_shape) == 3:
        width_padding = 2 * (window_size[1] // 2)
        padding_ = [[0, 0], [width_padding, 0], [0, 0]]
      else:
        height_padding = 2 * (window_size[0] // 2)
        cond_padding = tf.cond(
            tf.equal(shape_list(inputs)[2], 1), lambda: tf.constant(0),
            lambda: tf.constant(2 * (window_size[1] // 2)))
        width_padding = 0 if static_shape[2] == 1 else cond_padding
        padding_ = [[0, 0], [height_padding, 0], [width_padding, 0], [0, 0]]
      inputs = tf.pad(inputs, padding_)
      inputs.set_shape([static_shape[0], None, None, static_shape[3]])
      padding = "VALID"

  return tf.nn.pool(inputs, window_size, pooling_type, padding, strides=strides) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [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: import tensorflow [as 别名]
# 或者: from tensorflow import pad [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: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def _absolute_position_to_relative_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]

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

  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], [1, 0], [0, 0]])
  x = tf.reshape(x, [batch, heads, length, length + 1])
  x = tf.slice(x, [0, 0, 0, 1], [batch, heads, length, length])
  return x 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import pad [as 别名]
def get_shifted_center_blocks(x, indices):
  """Get right shifted blocks for masked local attention 2d.

  Args:
    x: A tensor with shape [batch, heads, height, width, depth]
    indices: The indices to gather blocks

  Returns:
    x_shifted: a tensor of extracted blocks, each block right shifted along
      length.
  """
  center_x = gather_blocks_2d(x, indices)

  # Shift right along the length dimension
  def shift_right_2d_blocks(x):
    """Shift the second to last dimension of x right by one."""
    shifted_targets = (
        tf.pad(x, [[0, 0], [0, 0], [0, 0], [1, 0], [0, 0]])[:, :, :, :-1, :])
    return shifted_targets

  x_shifted = shift_right_2d_blocks(center_x)
  return x_shifted