matteosal commented on issue #15464: MKL-DNN gives wrong convolution bias gradient if weights gradient is not requested URL: https://github.com/apache/incubator-mxnet/issues/15464#issuecomment-508703278 I don't have a use case for this. I'm reporting the bug because our unittests at Wolfram Research have spotted it.
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
