Compute gradients for a FakeQuantWithMinMaxArgs operation.
tf.quantization.fake_quant_with_min_max_args_gradient(
gradients: Annotated[Any, _atypes.Float32],
inputs: Annotated[Any, _atypes.Float32],
min: float = -6,
max: float = 6,
num_bits: int = 8,
narrow_range: bool = False,
name=None
) -> Annotated[Any, _atypes.Float32]
Returns | |
---|---|
A Tensor of type float32 .
|