tensorflow:: ops:: QuantizeAndDequantizeV4

Quantizes then dequantizes a tensor.

Summary

This is almost identical to QuantizeAndDequantizeV2 , except that it returns a gradient of 1 for inputs that are within the quantization range, or 0 otherwise.

Args:

• scope: A Scope object
• input: Tensor to quantize and then dequantize.
• input_min: If range_given == True , this specifies the minimum input value that needs to be represented, otherwise it is determined from the min value of the input tensor.
• input_max: If range_given == True , this specifies the maximum input value that needs to be represented, otherwise it is determined from the max value of the input tensor.

Optional attributes (see Attrs ):

• signed_input: Whether the quantization is signed or unsigned. (actually this parameter should have been called signed_output )
• num_bits: The bitwidth of the quantization.
• range_given: Whether the range is given or should be determined from the input tensor.
• round_mode: The 'round_mode' attribute controls which rounding tie-breaking algorithm is used when rounding float values to their quantized equivalents. The following rounding modes are currently supported:
• HALF_TO_EVEN: this is the default round_mode.
• HALF_UP: round towards positive. In this mode 7.5 rounds up to 8 and -7.5 rounds up to -7.
• narrow_range: If True, then the absolute value of the quantized minimum value is the same as the quantized maximum value, instead of 1 greater. i.e. for 8 bit quantization, the minimum value is -127 instead of -128.
• axis: If specified, this axis is treated as a channel or slice axis, and a separate quantization range is used for each channel or slice along this axis.

Returns:

• Output : The output tensor.

Public attributes

Operation operation

::tensorflow::Output output

Public functions

 QuantizeAndDequantizeV4(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input input_min,
  ::tensorflow::Input input_max
)

 QuantizeAndDequantizeV4(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input input_min,
  ::tensorflow::Input input_max,
  const QuantizeAndDequantizeV4::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Public static functions

Attrs Axis(
  int64 x
)

Attrs NarrowRange(
  bool x
)

Attrs NumBits(
  int64 x
)

Attrs RangeGiven(
  bool x
)

Attrs RoundMode(
  StringPiece x
)

Attrs SignedInput(
  bool x
)