jinhuang415 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_r190488482
########## File path: src/operator/quantization/quantized_flatten-inl.h ########## @@ -96,10 +106,10 @@ inline bool QuantizedFlattenType(const nnvm::NodeAttrs& attrs, std::vector<int> *out_attrs) { CHECK_EQ(in_attrs->size(), 3U); CHECK_EQ(out_attrs->size(), 3U); - TYPE_ASSIGN_CHECK(*in_attrs, 0, mshadow::kInt8); TYPE_ASSIGN_CHECK(*in_attrs, 1, mshadow::kFloat32); TYPE_ASSIGN_CHECK(*in_attrs, 2, mshadow::kFloat32); - TYPE_ASSIGN_CHECK(*out_attrs, 0, mshadow::kInt8); + const int dtype = (*in_attrs)[0]; Review comment: Yes, that's a better way, will change. ---------------------------------------------------------------- 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