ciyongch commented on a change in pull request #14528: Performance improving
for MKL-DNN Quantized FullyConnected
URL: https://github.com/apache/incubator-mxnet/pull/14528#discussion_r269373612
##########
File path: src/operator/subgraph/mkldnn/mkldnn_fc.cc
##########
@@ -195,6 +195,13 @@ void SgMKLDNNFCOp::Forward(const OpContext &ctx,
}
MKLDNNFCForwardFullFeature(full_param_, ctx, fwd_.get(), new_inputs,
new_req, out_data);
+
+ if (mkldnn_param.quantized && !mkldnn_param.enable_float_output) {
Review comment:
I think it's straightforward here, the OutMin and OutMax are only valid when
the op is quantized and not generating fp32 output.
----------------------------------------------------------------
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
