Quantizes then dequantizes a tensor.
tf.quantize_and_dequantize_v4(
input, input_min, input_max, signed_input=True, num_bits=8, range_given=False,
round_mode='HALF_TO_EVEN', narrow_range=False, axis=-1, name=None
)
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 | |
---|---|
input
|
A Tensor . Must be one of the following types: bfloat16 , half , float32 , float64 .
Tensor to quantize and then dequantize.
|
input_min
|
A Tensor . Must have the same type as input .
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
|
A Tensor . Must have the same type as input .
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.
|
signed_input
|
An optional bool . Defaults to True .
Whether the quantization is signed or unsigned. (actually this parameter should
have been called signed_output )
|
num_bits
|
An optional int . Defaults to 8 .
The bitwidth of the quantization.
|
range_given
|
An optional bool . Defaults to False .
Whether the range is given or should be determined from the input tensor.
|
round_mode
|
An optional string from: "HALF_TO_EVEN", "HALF_UP" . Defaults to "HALF_TO_EVEN" .
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:
|
narrow_range
|
An optional bool . Defaults to False .
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
|
An optional int . Defaults to -1 .
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.
|
name
|
A name for the operation (optional). |
Returns | |
---|---|
A Tensor . Has the same type as input .
|