tensorflow::ops::MaxPoolWithArgmax

#include <nn_ops.h>

Performs max pooling on the input and outputs both max values and indices.

Summary

The indices in argmax are flattened, so that a maximum value at position [b, y, x, c] becomes flattened index ((b * height + y) * width + x) * channels + c.

The indices returned are always in [0, height) x [0, width) before flattening, even if padding is involved and the mathematically correct answer is outside (either negative or too large). This is a bug, but fixing it is difficult to do in a safe backwards compatible way, especially due to flattening.

Arguments:

• scope: A Scope object
• input: 4-D with shape [batch, height, width, channels]. Input to pool over.
• 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.

Returns:

• Output output: The max pooled output tensor.
• Output argmax: 4-D. The flattened indices of the max values chosen for each output.

Public attributes

::tensorflow::Output argmax

::tensorflow::Output output

Public functions

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

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

Public static functions

Attrs Targmax(
  DataType x
)