[GitHub] xinyu-intel opened a new pull request #12808: MKL-DNN Quantization Examples and README

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

xinyu-intel opened a new pull request #12808: MKL-DNN Quantization Examples and README
URL: https://github.com/apache/incubator-mxnet/pull/12808
 
 
   ## Description ##
   This is a PR to add MKL-DNN Quantization Examples and README based on subgraph feature. #12530 
   @zheng-da, @azai91, @reminisce, @TaoLv, @pengzhao-intel
   ## Checklist ##
   ### Essentials ###
   Please feel free to remove inapplicable items for your PR.
   - [ ] The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant [JIRA issue](https://issues.apache.org/jira/projects/MXNET/issues) created (except PRs with tiny changes)
   - [ ] Changes are complete (i.e. I finished coding on this PR)
   - [x] All changes have test coverage:
   - Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
   - Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
   - Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
   - [x] Code is well-documented: 
   - For user-facing API changes, API doc string has been updated. 
   - For new C++ functions in header files, their functionalities and arguments are documented. 
   - For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
   - Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
   - [x] To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
   
   ### Changes ###
   - [x] Improve image-classification quantization script to support more models converted from Gluon-CV.
   - [x] Improve init_param function to support min, max node in quantized graph. Test case has been added and passed.
   - [x] Improve image-classification inference script to support dummy data inference.
   - [x] Improve SSD evaluate script to support specific num_batch and dry run.
   - [x] Add quantization script for SSD-VGG16 and improve its benchmark script to support quantized SSD.
   - [x] Add quantization README in which take ResNet50-v1, SSD-VGG16 and Squeezenet1.0 as examples and give brief introduction to quantize a custom symbol.
   - [x] Add subgraph instruction in MKLDNN_README and Performance page.
   
   ## Comments ##
   - Performance [here](https://mxnet.incubator.apache.org/faq/perf.html#intel-cpu) has not been updated.
   

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


With regards,
Apache Git Services