tensorflow::ops::QuantizedBiasAdd

#include <nn_ops.h>

Adds Tensor 'bias' to Tensor 'input' for Quantized types.

Summary

Broadcasts the values of bias on dimensions 0..N-2 of 'input'.

Arguments:

  • scope: A Scope object
  • bias: A 1D bias Tensor with size matching the last dimension of 'input'.
  • min_input: The float value that the lowest quantized input value represents.
  • max_input: The float value that the highest quantized input value represents.
  • min_bias: The float value that the lowest quantized bias value represents.
  • max_bias: The float value that the highest quantized bias value represents.

Returns:

  • Output output
  • Output min_out: The float value that the lowest quantized output value represents.
  • Output max_out: The float value that the highest quantized output value represents.

Constructors and Destructors

QuantizedBiasAdd(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input bias, ::tensorflow::Input min_input, ::tensorflow::Input max_input, ::tensorflow::Input min_bias, ::tensorflow::Input max_bias, DataType out_type)

Public attributes

max_out
min_out
output

Public attributes

max_out

::tensorflow::Output max_out

min_out

::tensorflow::Output min_out

output

::tensorflow::Output output

Public functions

QuantizedBiasAdd

 QuantizedBiasAdd(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input bias,
  ::tensorflow::Input min_input,
  ::tensorflow::Input max_input,
  ::tensorflow::Input min_bias,
  ::tensorflow::Input max_bias,
  DataType out_type
)