Aliases:
tf.fake_quant_with_min_max_vars_gradient
tf.quantization.fake_quant_with_min_max_vars_gradient
tf.quantization.fake_quant_with_min_max_vars_gradient(
gradients,
inputs,
min,
max,
num_bits=8,
narrow_range=False,
name=None
)
Defined in generated file: tensorflow/python/ops/gen_array_ops.py
.
Compute gradients for a FakeQuantWithMinMaxVars operation.
Args:
gradients
: ATensor
of typefloat32
. Backpropagated gradients above the FakeQuantWithMinMaxVars operation.inputs
: ATensor
of typefloat32
. Values passed as inputs to the FakeQuantWithMinMaxVars operation. min, max: Quantization interval, scalar floats.min
: ATensor
of typefloat32
.max
: ATensor
of typefloat32
.num_bits
: An optionalint
. Defaults to8
. The bitwidth of the quantization; between 2 and 8, inclusive.narrow_range
: An optionalbool
. Defaults toFalse
. Whether to quantize into 2^num_bits - 1 distinct values.name
: A name for the operation (optional).
Returns:
A tuple of Tensor
objects (backprops_wrt_input, backprop_wrt_min, backprop_wrt_max).
backprops_wrt_input
: ATensor
of typefloat32
.backprop_wrt_min
: ATensor
of typefloat32
.backprop_wrt_max
: ATensor
of typefloat32
.