AINDNet icon indicating copy to clipboard operation
AINDNet copied to clipboard
Published 5 years ago • verified publisher icon terryoo

Weight coefficient for asymmetric loss

Open eastchun opened this issue 5 years ago • 0 comments

In your paper, you mentioned that the weight term of the noise-level estimator is empirically determined to 0.05 (i.e., lambda_ms-asymm = 0.05).

Isn't this typo for lambda_ms-asymm = 0.5 ???

eastchun avatar Jun 05 '20 14:06 eastchun