crazy-cat commented on a change in pull request #7393: add depthwise convolution's gpu version optimization URL: https://github.com/apache/incubator-mxnet/pull/7393#discussion_r132098910
########## File path: src/operator/convolution.cu ########## @@ -45,6 +47,18 @@ Operator* CreateOp<gpu>(ConvolutionParam param, int dtype, }) return op; } + + // depth wise conv + if (!param.depthwise_conv_off && + param.num_filter == param.num_group && + param.layout.value() == mshadow::kNCHW && + param.num_filter == (*in_shape)[conv::kData][1] && + param.kernel.ndim() == 2 && + param.dilate == mshadow::Shape2(1, 1) && + dtype == mshadow::kFloat32) { Review comment: We are no processing in cuda kernel when dtype==mshadow::kFloat16 ---------------------------------------------------------------- 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