tf.quantization.fake_quant_with_min_max_vars_gradient | TensorFlow v2.16.1 (original) (raw)

tf.quantization.fake_quant_with_min_max_vars_gradient

Stay organized with collections Save and categorize content based on your preferences.

Compute gradients for a FakeQuantWithMinMaxVars operation.

View aliases

Compat aliases for migration

tf.compat.v1.fake_quant_with_min_max_vars_gradient, tf.compat.v1.quantization.fake_quant_with_min_max_vars_gradient

tf.quantization.fake_quant_with_min_max_vars_gradient(
    gradients: Annotated[Any, _atypes.Float32],
    inputs: Annotated[Any, _atypes.Float32],
    min: Annotated[Any, _atypes.Float32],
    max: Annotated[Any, _atypes.Float32],
    num_bits: int = 8,
    narrow_range: bool = False,
    name=None
)

Args
gradients	A Tensor of type float32. Backpropagated gradients above the FakeQuantWithMinMaxVars operation.
inputs	A Tensor of type float32. Values passed as inputs to the FakeQuantWithMinMaxVars operation. min, max: Quantization interval, scalar floats.
min	A Tensor of type float32.
max	A Tensor of type float32.
num_bits	An optional int. Defaults to 8. The bitwidth of the quantization; between 2 and 8, inclusive.
narrow_range	An optional bool. Defaults to False. 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	A Tensor of type float32.
backprop_wrt_min	A Tensor of type float32.
backprop_wrt_max	A Tensor of type float32.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.