tfc.ops.soft_round

View source on GitHub

Differentiable approximation to round.

View aliases

Main aliases

tfc.soft_round 

tfc.ops.soft_round(
 x, alpha, eps=0.001
)

Larger alphas correspond to closer approximations of the round function. If alpha is close to zero, this function reduces to the identity.

This is described in Sec. 4.1. in the paper

"Universally Quantized Neural Compression"
Eirikur Agustsson & Lucas Theis
https://arxiv.org/abs/2006.09952

Args

x tf.Tensor. Inputs to the rounding function.
alpha Float or tf.Tensor. Controls smoothness of the approximation.
eps Float. Threshold below which soft_round will return identity.

Returns

tf.Tensor

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年04月26日 UTC.