[GitHub] austingg commented on issue #7393: add depthwise convolution's gpu version optimization
austingg commented on issue #7393: add depthwise convolution's gpu version optimization URL: https://github.com/apache/incubator-mxnet/pull/7393#issuecomment-325631062 @terrychenism how about the convergence, I used the symbol in `imageclassification` dir and script `train_imagenet.py`, seems not converge when using depthwise conv. 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
[GitHub] austingg commented on issue #7393: add depthwise convolution's gpu version optimization
austingg commented on issue #7393: add depthwise convolution's gpu version optimization URL: https://github.com/apache/incubator-mxnet/pull/7393#issuecomment-321261481 @solin319 , it is said grouped conv in cudnn v7 is not efficient when used in depthwise conv, where the group num == input channels 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