zachgk commented on issue #16010: DropConnect Layer URL: https://github.com/apache/incubator-mxnet/issues/16010#issuecomment-533298429 The tensorflow workaround you gave is to call dropout on the weight layer and then multiply by the probability for the dropout layer to undo the weight change. This should work in MXNet and other frameworks as well
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to 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