tensorflow::ops::MaxPool3DGradGrad

#include <nn_ops.h>

Computes second-order gradients of the maxpooling function.

Summary

Arguments:

• scope: A Scope object
• orig_input: The original input tensor.
• orig_output: The original output tensor.
• grad: Output backprop of shape [batch, depth, rows, cols, channels].
• ksize: 1-D tensor of length 5. The size of the window for each dimension of the input tensor. Must have ksize[0] = ksize[4] = 1.
• strides: 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1.
• padding: The type of padding algorithm to use.

Optional attributes (see Attrs):

• data_format: The data format of the input and output data. With the default format "NDHWC", the data is stored in the order of: [batch, in_depth, in_height, in_width, in_channels]. Alternatively, the format could be "NCDHW", the data storage order is: [batch, in_channels, in_depth, in_height, in_width].

Returns:

• Output: Gradients of gradients w.r.t. the input to max_pool.

Public attributes

Operation operation

::tensorflow::Output output

Public functions

 MaxPool3DGradGrad(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input orig_input,
  ::tensorflow::Input orig_output,
  ::tensorflow::Input grad,
  const gtl::ArraySlice< int > & ksize,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)

 MaxPool3DGradGrad(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input orig_input,
  ::tensorflow::Input orig_output,
  ::tensorflow::Input grad,
  const gtl::ArraySlice< int > & ksize,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const MaxPool3DGradGrad::Attrs & attrs
)

::tensorflow::Node * node() const 

operator::tensorflow::Input() const 

operator::tensorflow::Output() const 

Public static functions

Attrs DataFormat(
  StringPiece x
)