tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs

#include <array_ops.h>

Optional attribute setters for FakeQuantWithMinMaxVarsGradient.

Summary

Public attributes
`narrow_range_ = false`	`bool`
`num_bits_ = 8`	`int64`

Public functions
`NarrowRange(bool x)`	`TF_MUST_USE_RESULT Attrs` Whether to quantize into 2^num_bits - 1 distinct values.
`NumBits(int64 x)`	`TF_MUST_USE_RESULT Attrs` The bitwidth of the quantization; between 2 and 8, inclusive.

bool tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::narrow_range_ = false

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

TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NarrowRange(
  bool x
)

Whether to quantize into 2^num_bits - 1 distinct values.

Defaults to false

TF_MUST_USE_RESULT Attrs tensorflow::ops::FakeQuantWithMinMaxVarsGradient::Attrs::NumBits(
  int64 x
)

The bitwidth of the quantization; between 2 and 8, inclusive.

Defaults to 8

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2021-11-15 UTC.