Python array_ops.batch_to_space函数代码示例

 def pyr_up(batch):  # matches cv2.pyrUp()
   s = array_ops.shape(batch)
   zeros = array_ops.zeros([3 * s[0], s[1], s[2], s[3]])
   res = array_ops.concat([batch, zeros], 0)
   res = array_ops.batch_to_space(res, crops=[[0, 0], [0, 0]], block_size=2)
   res = spatial_conv(res, 4)
   return res

  def testAtrousSequence(self):
    """Tests optimization of sequence of atrous convolutions.

    Verifies that a sequence of `atrous_conv2d` operations with identical `rate`
    parameters, 'SAME' `padding`, and `filters` with odd heights/ widths:

        net = atrous_conv2d(net, filters1, rate, padding="SAME")
        net = atrous_conv2d(net, filters2, rate, padding="SAME")
        ...
        net = atrous_conv2d(net, filtersK, rate, padding="SAME")

    is equivalent to:

        pad = ...  # padding so that the input dims are multiples of rate
        net = space_to_batch(net, paddings=pad, block_size=rate)
        net = conv2d(net, filters1, strides=[1, 1, 1, 1], padding="SAME")
        net = conv2d(net, filters2, strides=[1, 1, 1, 1], padding="SAME")
        ...
        net = conv2d(net, filtersK, strides=[1, 1, 1, 1], padding="SAME")
        net = batch_to_space(net, crops=pad, block_size=rate)
    """
    padding = "SAME"  # The padding needs to be "SAME"
    np.random.seed(1)  # Make it reproducible.

    with self.session(use_gpu=True):
      # Input: [batch, height, width, input_depth]
      for height in range(15, 17):
        for width in range(15, 17):
          x_shape = [3, height, width, 2]
          x = np.random.random_sample(x_shape).astype(np.float32)

          for kernel in [1, 3, 5]:  # The kernel size needs to be odd.
            # Filter: [kernel_height, kernel_width, input_depth, output_depth]
            f_shape = [kernel, kernel, 2, 2]
            f = 1e-2 * np.random.random_sample(f_shape).astype(np.float32)

            for rate in range(2, 4):
              # y1: three atrous_conv2d in a row.
              y1 = nn_ops.atrous_conv2d(x, f, rate, padding=padding)
              y1 = nn_ops.atrous_conv2d(y1, f, rate, padding=padding)
              y1 = nn_ops.atrous_conv2d(y1, f, rate, padding=padding)
              # y2: space_to_batch, three conv2d in a row, batch_to_space
              pad_bottom = 0 if height % rate == 0 else rate - height % rate
              pad_right = 0 if width % rate == 0 else rate - width % rate
              pad = [[0, pad_bottom], [0, pad_right]]
              y2 = array_ops.space_to_batch(x, paddings=pad, block_size=rate)
              y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding)
              y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding)
              y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding)
              y2 = array_ops.batch_to_space(y2, crops=pad, block_size=rate)
              self.assertAllClose(
                  y1.eval(), self.evaluate(y2), rtol=1e-2, atol=1e-2)

def _SpaceToBatchGrad(op, grad):
  # Its gradient is the opposite op: BatchToSpace.
  block_size = op.get_attr("block_size")
  return [array_ops.batch_to_space(grad, op.inputs[1], block_size=block_size),
          None]

 def batch_to_space(*args, **kwargs):
   return array_ops.batch_to_space(*args, **kwargs)

def atrous_conv2d(value, filters, rate, padding, name=None):
  """Atrous convolution (a.k.a. convolution with holes or dilated convolution).

  Computes a 2-D atrous convolution, also known as convolution with holes or
  dilated convolution, given 4-D `value` and `filters` tensors. If the `rate`
  parameter is equal to one, it performs regular 2-D convolution. If the `rate`
  parameter is greater than one, it performs convolution with holes, sampling
  the input values every `rate` pixels in the `height` and `width` dimensions.
  This is equivalent to convolving the input with a set of upsampled filters,
  produced by inserting `rate - 1` zeros between two consecutive values of the
  filters along the `height` and `width` dimensions, hence the name atrous
  convolution or convolution with holes (the French word trous means holes in
  English).

  More specifically:

      output[b, i, j, k] = sum_{di, dj, q} filters[di, dj, q, k] *
            value[b, i + rate * di, j + rate * dj, q]

  Atrous convolution allows us to explicitly control how densely to compute
  feature responses in fully convolutional networks. Used in conjunction with
  bilinear interpolation, it offers an alternative to `conv2d_transpose` in
  dense prediction tasks such as semantic image segmentation, optical flow
  computation, or depth estimation. It also allows us to effectively enlarge
  the field of view of filters without increasing the number of parameters or
  the amount of computation.

  For a description of atrous convolution and how it can be used for dense
  feature extraction, please see: [Semantic Image Segmentation with Deep
  Convolutional Nets and Fully Connected CRFs](http://arxiv.org/abs/1412.7062).
  The same operation is investigated further in [Multi-Scale Context Aggregation
  by Dilated Convolutions](http://arxiv.org/abs/1511.07122). Previous works
  that effectively use atrous convolution in different ways are, among others,
  [OverFeat: Integrated Recognition, Localization and Detection using
  Convolutional Networks](http://arxiv.org/abs/1312.6229) and [Fast Image
  Scanning with Deep Max-Pooling Convolutional Neural Networks]
  (http://arxiv.org/abs/1302.1700). Atrous convolution is also closely related
  to the so-called noble identities in multi-rate signal processing.

  There are many different ways to implement atrous convolution (see the refs
  above). The implementation here reduces

      atrous_conv2d(value, filters, rate, padding=padding)

  to the following three operations:

      paddings = ...
      net = space_to_batch(value, paddings, block_size=rate)
      net = conv2d(net, filters, strides=[1, 1, 1, 1], padding="VALID")
      crops = ...
      net = batch_to_space(net, crops, block_size=rate)

  Advanced usage. Note the following optimization: A sequence of `atrous_conv2d`
  operations with identical `rate` parameters, 'SAME' `padding`, and filters
  with odd heights/ widths:

      net = atrous_conv2d(net, filters1, rate, padding="SAME")
      net = atrous_conv2d(net, filters2, rate, padding="SAME")
      ...
      net = atrous_conv2d(net, filtersK, rate, padding="SAME")

  can be equivalently performed cheaper in terms of computation and memory as:

      pad = ...  # padding so that the input dims are multiples of rate
      net = space_to_batch(net, paddings=pad, block_size=rate)
      net = conv2d(net, filters1, strides=[1, 1, 1, 1], padding="SAME")
      net = conv2d(net, filters2, strides=[1, 1, 1, 1], padding="SAME")
      ...
      net = conv2d(net, filtersK, strides=[1, 1, 1, 1], padding="SAME")
      net = batch_to_space(net, crops=pad, block_size=rate)

  because a pair of consecutive `space_to_batch` and `batch_to_space` ops with
  the same `block_size` cancel out when their respective `paddings` and `crops`
  inputs are identical.

  Args:
    value: A 4-D `Tensor` of type `float`. It needs to be in the default "NHWC"
      format. Its shape is `[batch, in_height, in_width, in_channels]`.
    filters: A 4-D `Tensor` with the same type as `value` and shape
      `[filter_height, filter_width, in_channels, out_channels]`. `filters`'
      `in_channels` dimension must match that of `value`. Atrous convolution is
      equivalent to standard convolution with upsampled filters with effective
      height `filter_height + (filter_height - 1) * (rate - 1)` and effective
      width `filter_width + (filter_width - 1) * (rate - 1)`, produced by
      inserting `rate - 1` zeros along consecutive elements across the
      `filters`' spatial dimensions.
    rate: A positive int32. The stride with which we sample input values across
      the `height` and `width` dimensions. Equivalently, the rate by which we
      upsample the filter values by inserting zeros across the `height` and
      `width` dimensions. In the literature, the same parameter is sometimes
      called `input stride` or `dilation`.
    padding: A string, either `'VALID'` or `'SAME'`. The padding algorithm.
    name: Optional name for the returned tensor.

  Returns:
    A `Tensor` with the same type as `value`.

  Raises:
    ValueError: If input/output depth does not match `filters`' shape, or if
      padding is other than `'VALID'` or `'SAME'`.
#.........这里部分代码省略.........

def atrous_pool2d(value,ksize, rate, padding, name=None, pooling_type="MAX"):
  with ops.name_scope(name, "atrous_pool2d", [value]) as name:
    value = ops.convert_to_tensor(value, name="value")
    if rate < 1:
      raise ValueError("rate {} cannot be less than one".format(rate))

    if rate == 1:
      if pooling_type == "MAX":
        value = nn_ops.max_pool(value=value,
                                ksize=ksize,
                                strides=[1, 1, 1, 1],
                                padding=padding)
        return value
      elif pooling_type == "AVG":
        value = nn_ops.avg_pool(value=value,
                                ksize=ksize,
                                strides=[1, 1, 1, 1],
                                padding=padding)
        return value
      else:
        raise ValueError("Invalid pooling type")


    # We have two padding contributions. The first is used for converting "SAME"
    # to "VALID". The second is required so that the height and width of the
    # zero-padded value tensor are multiples of rate.

    # Padding required to reduce to "VALID" convolution
    if padding == "SAME":
      # Handle filters whose shape is unknown during graph creation.
      # if filters.get_shape().is_fully_defined():
      #   filter_shape = filters.get_shape().as_list()
      # else:
      #   filter_shape = array_ops.shape(filters)
      # filter_height, filter_width = filter_shape[0], filter_shape[1]
      kernel_height, kernel_width = ksize[1], ksize[2]


      # Spatial dimensions of the filters and the upsampled filters in which we
      # introduce (rate - 1) zeros between consecutive filter values.
      kernel_height_up = kernel_height + (kernel_height - 1) * (rate - 1)
      kernel_width_up = kernel_width + (kernel_width - 1) * (rate - 1)

      pad_height = kernel_height_up - 1
      pad_width = kernel_width_up - 1

      # When pad_height (pad_width) is odd, we pad more to bottom (right),
      # following the same convention as conv2d().
      pad_top = pad_height // 2
      pad_bottom = pad_height - pad_top
      pad_left = pad_width // 2
      pad_right = pad_width - pad_left
    elif padding == "VALID":
      pad_top = 0
      pad_bottom = 0
      pad_left = 0
      pad_right = 0
    else:
      raise ValueError("Invalid padding")

    # Handle input whose shape is unknown during graph creation.
    if value.get_shape().is_fully_defined():
      value_shape = value.get_shape().as_list()
    else:
      value_shape = array_ops.shape(value)

    in_height = value_shape[1] + pad_top + pad_bottom
    in_width = value_shape[2] + pad_left + pad_right

    # More padding so that rate divides the height and width of the input.
    pad_bottom_extra = (rate - in_height % rate) % rate
    pad_right_extra = (rate - in_width % rate) % rate

    # The paddings argument to space_to_batch includes both padding components.
    space_to_batch_pad = [[pad_top, pad_bottom + pad_bottom_extra],
                          [pad_left, pad_right + pad_right_extra]]

    value = array_ops.space_to_batch(input=value,
                                     paddings=space_to_batch_pad,
                                     block_size=rate)
    if pooling_type == "MAX":
      value = nn_ops.max_pool(value=value,
                                ksize=ksize,
                                strides=[1, 1, 1, 1],
                                padding="VALID",
                                name=name)

    elif pooling_type == "AVG":
      value = nn_ops.avg_pool(value=value,
                                ksize=ksize,
                                strides=[1, 1, 1, 1],
                                padding="VALID",
                                name=name)
    else:
      raise ValueError("Invalid pooling type")

    # The crops argument to batch_to_space is just the extra padding component.
    batch_to_space_crop = [[0, pad_bottom_extra], [0, pad_right_extra]]

    value = array_ops.batch_to_space(input=value,
#.........这里部分代码省略.........

def atrous_conv2d(value, filters, rate, padding, name=None):
  with ops.op_scope([value, filters], name, "atrous_conv2d") as name:
    value = ops.convert_to_tensor(value, name="value")
    filters = ops.convert_to_tensor(filters, name="filters")
    value_shape = value.get_shape()
    filter_shape = filters.get_shape()
    if not value_shape[3].is_compatible_with(filter_shape[2]):
      raise ValueError(
          "value's input channels does not match filters' input channels, "
          "{} != {}".format(value_shape[3], filter_shape[2]))
    if rate < 1:
      raise ValueError("rate {} cannot be less than one".format(rate))

    if rate == 1:
      value = gen_nn_ops.conv2d(input=value,
                                filter=filters,
                                strides=[1, 1, 1, 1],
                                padding=padding)
      return value

    # We have two padding contributions. The first is used for converting "SAME"
    # to "VALID". The second is required so that the height and width of the
    # zero-padded value tensor are multiples of rate.

    # Spatial dimensions of original input
    value_shape = array_ops.shape(value)
    in_height = value_shape[1]
    in_width = value_shape[2]

    # Spatial dimensions of the filters and the upsampled filters in which we
    # introduce (rate - 1) zeros between consecutive filter values.
    filter_shape = array_ops.shape(filters)
    filter_height = filter_shape[0]
    filter_width = filter_shape[1]
    filter_height_up = filter_height + (filter_height - 1) * (rate - 1)
    filter_width_up = filter_width + (filter_width - 1) * (rate - 1)

    # Padding required to reduce to "VALID" convolution
    if padding == "SAME":
      pad_height = filter_height_up - 1
      pad_width = filter_width_up - 1
    elif padding == "VALID":
      pad_height = 0
      pad_width = 0
    else:
      raise ValueError("Invalid padding")
    # When padding is "SAME" and the pad_height (pad_width) is odd, we pad more
    # to bottom (right), following the same convention as conv2d().
    pad_top = math_ops.floordiv(pad_height, 2)
    pad_bottom = pad_height - pad_top
    pad_left = math_ops.floordiv(pad_width, 2)
    pad_right = pad_width - pad_left

    # More padding so that rate divides the height and width of the input value
    in_height = in_height + pad_top + pad_bottom
    in_width = in_width + pad_left + pad_right

    mod_height = math_ops.mod(in_height, rate)
    mod_width = math_ops.mod(in_width, rate)
    null = constant_op.constant(0)
    pad_bottom_extra = control_flow_ops.cond(gen_math_ops.equal(mod_height, 0), lambda: null, lambda: rate - mod_height)
    pad_right_extra = control_flow_ops.cond(gen_math_ops.equal(mod_width, 0), lambda: null, lambda: rate - mod_width)

    # The paddings argument to space_to_batch includes both padding components
    pad_bottom = pad_bottom + pad_bottom_extra
    pad_right = pad_right + pad_right_extra
    print 'hahahaha'
    v = array_ops.expand_dims(array_ops.pack([pad_top, pad_bottom]),1)
    h = array_ops.expand_dims(array_ops.pack([pad_left, pad_right]),1)
    space_to_batch_pad = array_ops.concat(1, [v,h])
    space_to_batch_pad = [[pad_top, pad_bottom],
                          [pad_left, pad_right]]

    value = array_ops.space_to_batch(input=value,
                                     paddings=space_to_batch_pad,
                                     block_size=rate)

    value = gen_nn_ops.conv2d(input=value,
                              filter=filters,
                              strides=[1, 1, 1, 1],
                              padding="VALID",
                              name=name)

    # The crops argument to batch_to_space is just the extra padding component
    v = array_ops.expand_dims(array_ops.pack([0, pad_bottom_extra]),1)
    h = array_ops.expand_dims(array_ops.pack([0, pad_right_extra]),1)
    batch_to_space_crop = array_ops.concat(1, [v,h])
    batch_to_space_crop = [[0, pad_bottom_extra], [0, pad_right_extra]]
    value = array_ops.batch_to_space(input=value,
                                     crops=batch_to_space_crop,
                                     block_size=rate)

    return value