gilbertfrancois commented on issue #18751: URL: https://github.com/apache/incubator-mxnet/issues/18751#issuecomment-662755383
Coming back to mxnet: it looks like it is possible to do a forward pass (inference mode) on cpu when the BatchNorm is placed with Dense layers. But on gpu, it tries to update the values on the forward pass, instead of the backward pass, resulting in NaN when the batch size = 1. ---------------------------------------------------------------- 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