[GitHub] [incubator-mxnet] wuxun-zhang opened a new pull request #15038: [C++] fix type inconsistent issue when loading quantized parameters

[GitBox <gi...@apache.org>]

wuxun-zhang opened a new pull request #15038: [C++] fix type inconsistent issue when loading quantized parameters
URL: https://github.com/apache/incubator-mxnet/pull/15038
 
 
   ## Description ##
   @pengzhao-intel @ZhennanQin 
   We want to use [inception_inference.cpp](https://github.com/apache/incubator-mxnet/blob/master/cpp-package/example/inference/inception_inference.cpp) to do inference with quantized models. But When I tried to run inference, there always have a type inconsistent error. We found that during loading parameters, new NDArrays will be created with default data type (float32) and copy the original NDArray to this new NDArray by using NDArray.Copy(context). So, the original int8 params will be converted into float32 params and this will raise the type inconsistent issue. 
   
   
   ## Checklist ##
   ### Essentials ###
   Please feel free to remove inapplicable items for your PR.
   - [ ] The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant [JIRA issue](https://issues.apache.org/jira/projects/MXNET/issues) created (except PRs with tiny changes)
   - [ ] Changes are complete (i.e. I finished coding on this PR)
   - [ ] All changes have test coverage:
   - Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
   - Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
   - Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
   - [ ] Code is well-documented: 
   - For user-facing API changes, API doc string has been updated. 
   - For new C++ functions in header files, their functionalities and arguments are documented. 
   - For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
   - Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
   - [ ] To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
   
   ### Changes ###
   - [ ] Feature1, tests, (and when applicable, API doc)
   - [ ] Feature2, tests, (and when applicable, API doc)
   
   ## Comments ##
   - If this change is a backward incompatible change, why must this change be made.
   - Interesting edge cases to note here
   

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services