tensorflow:: ops:: Conv2DBackpropInput

Computes the gradients of convolution with respect to the input.

Summary

Args:

• scope: A Scope object
• input_sizes: An integer vector representing the shape of input , where input is a 4-D [batch, height, width, channels] tensor.
• filter: 4-D with shape [filter_height, filter_width, in_channels, out_channels] .
• out_backprop: 4-D with shape [batch, out_height, out_width, out_channels] . Gradients w.r.t. the output of the convolution.
• strides: The stride of the sliding window for each dimension of the input of the convolution. Must be in the same order as the dimension specified with format.
• padding: The type of padding algorithm to use.

Optional attributes (see Attrs ):

• explicit_paddings: If padding is "EXPLICIT" , the list of explicit padding amounts. For the ith dimension, the amount of padding inserted before and after the dimension is explicit_paddings[2 * i] and explicit_paddings[2 * i + 1] , respectively. If padding is not "EXPLICIT" , explicit_paddings must be empty.
• data_format: Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, in_height, in_width, in_channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, in_channels, in_height, in_width].
• dilations: 1-D tensor of length 4. The dilation factor for each dimension of input . If set to k > 1, there will be k-1 skipped cells between each filter element on that dimension. The dimension order is determined by the value of data_format , see above for details. Dilations in the batch and depth dimensions must be 1.

Returns:

• Output : 4-D with shape [batch, in_height, in_width, in_channels] . Gradient w.r.t. the input of the convolution.

Public attributes

Operation operation

::tensorflow::Output output

Public functions

 Conv2DBackpropInput(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input_sizes,
  ::tensorflow::Input filter,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)

 Conv2DBackpropInput(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input_sizes,
  ::tensorflow::Input filter,
  ::tensorflow::Input out_backprop,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const Conv2DBackpropInput::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Public static functions

Attrs DataFormat(
  StringPiece x
)

Attrs Dilations(
  const gtl::ArraySlice< int > & x
)

Attrs ExplicitPaddings(
  const gtl::ArraySlice< int > & x
)

Attrs UseCudnnOnGpu(
  bool x
)