bartekkuncer commented on issue #20826: URL: https://github.com/apache/incubator-mxnet/issues/20826#issuecomment-1073960486
After further investigation found out that the real problem was reading from neither updated nor cleared register during convolution with weights stored in blocked format. This problem does not occur when the amount of input channels is 4 and higher as full register is being overwritten. Fix for this issue is coming in v2.6 of oneDNN. Original shapes have been restored in the test. There was a temporary fix in place: https://github.com/apache/incubator-mxnet/pull/20847 forcing blocking the weights by 8 instead of 16, but it turned out only to make the problem occur less often. Therefore until v2.6 of oneDNN arrives there will be no blocking the weights for convolutions with the amount of input channels lower than 4: https://github.com/apache/incubator-mxnet/pull/20970. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
