Aliases:
tf.fake_quant_with_min_max_args
tf.quantization.fake_quant_with_min_max_args
tf.quantization.fake_quant_with_min_max_args(
inputs,
min=-6,
max=6,
num_bits=8,
narrow_range=False,
name=None
)
Defined in generated file: tensorflow/python/ops/gen_array_ops.py
.
Fake-quantize the 'inputs' tensor, type float to 'outputs' tensor of same type.
Attributes [min; max]
define the clamping range for the inputs
data.
inputs
values are quantized into the quantization range ([0; 2^num_bits - 1]
when narrow_range
is false and [1; 2^num_bits - 1]
when it is true) and
then de-quantized and output as floats in [min; max]
interval.
num_bits
is the bitwidth of the quantization; between 2 and 16, inclusive.
Quantization is called fake since the output is still in floating point.
Args:
inputs
: ATensor
of typefloat32
.min
: An optionalfloat
. Defaults to-6
.max
: An optionalfloat
. Defaults to6
.num_bits
: An optionalint
. Defaults to8
.narrow_range
: An optionalbool
. Defaults toFalse
.name
: A name for the operation (optional).
Returns:
A Tensor
of type float32
.