tensorflow::ops::QuantizedMaxPool

#include <nn_ops.h>

Produces the max pool of the input tensor for quantized types.

Summary

Args:

  • scope: A Scope object
  • input: The 4D (batch x rows x cols x depth) Tensor to MaxReduce over.
  • min_input: The float value that the lowest quantized input value represents.
  • max_input: The float value that the highest quantized input value represents.
  • ksize: The size of the window for each dimension of the input tensor. The length must be 4 to match the number of dimensions of the input.
  • strides: The stride of the sliding window for each dimension of the input tensor. The length must be 4 to match the number of dimensions of the input.
  • padding: The type of padding algorithm to use.

Returns:

  • Output output
  • Output min_output: The float value that the lowest quantized output value represents.
  • Output max_output: The float value that the highest quantized output value represents.

Constructors and Destructors

QuantizedMaxPool(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input min_input, ::tensorflow::Input max_input, const gtl::ArraySlice< int > & ksize, const gtl::ArraySlice< int > & strides, StringPiece padding)

Public attributes

max_output
min_output
operation
output

Public attributes

max_output

::tensorflow::Output max_output

min_output

::tensorflow::Output min_output

operation

Operation operation

output

::tensorflow::Output output

Public functions

QuantizedMaxPool

 QuantizedMaxPool(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input min_input,
  ::tensorflow::Input max_input,
  const gtl::ArraySlice< int > & ksize,
  const gtl::ArraySlice< int > & strides,
  StringPiece padding
)