pengzhao-intel commented on a change in pull request #14819: [MKLDNN] Enable more convolution + activation fusion URL: https://github.com/apache/incubator-mxnet/pull/14819#discussion_r279192835
########## File path: src/operator/nn/mkldnn/mkldnn_base-inl.h ########## @@ -178,7 +178,8 @@ struct SoftmaxOutputParam; struct TransposeParam; bool SupportMKLDNNAct(const ActivationParam& param); bool SupportMKLDNNAct(const ActivationParam& param, const NDArray &input); -bool SupportMKLDNNConv(const ConvolutionParam& params, const NDArray &input); +bool SupportQuantizedMKLDNNAct(const ActivationParam ¶m); Review comment: could we resue `SupportMKLDNNAct`? ---------------------------------------------------------------- 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
