anko-intel opened a new pull request, #21127: URL: https://github.com/apache/incubator-mxnet/pull/21127
## Description ## Added tutorial showing advantage of using INC with MXNet for quantization. It shows that INC can find operators mostly introduced loss of accuracy and eliminate it from quantization. This way partially quantized model achieves accuracy results almost the same as original floating point model, but with about 3 times performance improvement in comparison to optimized floating point model (or 30 times in comparison to not optimized floating point model)   ## Checklist ## ### Essentials ### - [ ] PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc) - [ ] Changes are complete (i.e. I finished coding on this PR) - [ ] All changes have test coverage - [ ] Code is well-documented -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
