szha commented on issue #11385: About loss URL: https://github.com/apache/incubator-mxnet/issues/11385#issuecomment-400006788 @yyl199655 if you use gluon, you can just write whatever penalty term you want using ndarray interface inside training loop. Only forward computation is needed, as long as the function is differentiable
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services