W3cubDocs

tensorflow::ops::QuantizeAndDequantize::Attrs

#include <array_ops.h>

Optional attribute setters for QuantizeAndDequantize.

Public functions
`InputMax(float x)`	`Attrs` If range is given, this is the max of the range.
`InputMin(float x)`	`Attrs` If range is given, this is the min of the range.
`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.

float tensorflow::ops::QuantizeAndDequantize::Attrs::input_max_ = 0.0f

float tensorflow::ops::QuantizeAndDequantize::Attrs::input_min_ = 0.0f

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

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

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

Attrs tensorflow::ops::QuantizeAndDequantize::Attrs::InputMax(
  float x
)

If range is given, this is the max of the range.

Defaults to 0

Attrs tensorflow::ops::QuantizeAndDequantize::Attrs::InputMin(
  float x
)

If range is given, this is the min of the range.

Defaults to 0

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

The bitwidth of the quantization.

Defaults to 8

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

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

Defaults to false

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

If the quantization is signed or unsigned.

Defaults to true

© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/cc/struct/tensorflow/ops/quantize-and-dequantize/attrs.html