xinyu-intel commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r190441095
##########
File path: src/operator/quantization/quantized_conv.cc
##########
@@ -119,7 +138,7 @@ and max thresholds representing the threholds for
quantizing the float32 output
return param.no_bias? 6 : 9;
})
.set_num_outputs(3)
-.set_attr_parser(ParamParser<ConvolutionParam>)
+.set_attr_parser(ConvolutionParamParser)
Review comment:
After syncing with @zheng-da, the previous ParamParser cannot pass the param
**dilate** correctly.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
