tensorflow::ops::QuantizeAndDequantizeV2::Attrs

#include <array_ops.h>

Optional attribute setters for QuantizeAndDequantizeV2.

Summary

Public functions
`NumBits(int64 x)`	`Attrs` The bitwidth of the quantization.
`RangeGiven(bool x)`	`Attrs` If the range is given or should be computed from the tensor.
`SignedInput(bool x)`	`Attrs` If the quantization is signed or unsigned.

int64 tensorflow::ops::QuantizeAndDequantizeV2::Attrs::num_bits_ = 8

bool tensorflow::ops::QuantizeAndDequantizeV2::Attrs::range_given_ = false

bool tensorflow::ops::QuantizeAndDequantizeV2::Attrs::signed_input_ = true

Attrs tensorflow::ops::QuantizeAndDequantizeV2::Attrs::NumBits(
  int64 x
)

The bitwidth of the quantization.

Defaults to 8

Attrs tensorflow::ops::QuantizeAndDequantizeV2::Attrs::RangeGiven(
  bool x
)

If the range is given or should be computed from the tensor.

Defaults to false

Attrs tensorflow::ops::QuantizeAndDequantizeV2::Attrs::SignedInput(
  bool x
)

If the quantization is signed or unsigned.

Defaults to true

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 3.0 License, and code samples are licensed under the Apache 2.0 License. For details, see our Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated April 26, 2017.