tensorflow::ops::MaxPoolGradGradWithArgmax

Computes second-order gradients of the maxpooling function.

Summary

Arguments:

• scope: A Scope object
• input: The original input.
• grad: 4-D with shape [batch, height, width, channels]. Gradients w.r.t. the input of max_pool.
• argmax: The indices of the maximum values chosen for each output of max_pool.
• ksize: The size of the window for each dimension of the input tensor.
• strides: The stride of the sliding window for each dimension of the input tensor.
• padding: The type of padding algorithm to use.

Optional attributes (see Attrs):

• include_batch_in_index: Whether to include batch dimension in flattened index of argmax.

Returns:

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

Public attributes

Operation operation

::tensorflow::Output output

 MaxPoolGradGradWithArgmax(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input grad,
  ::tensorflow::Input argmax,
  const gtl::ArraySlice< int > & ksize,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)

 MaxPoolGradGradWithArgmax(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input grad,
  ::tensorflow::Input argmax,
  const gtl::ArraySlice< int > & ksize,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding,
  const MaxPoolGradGradWithArgmax::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Attrs IncludeBatchInIndex(
  bool x
)