Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
fixed, designed and repositioned "Supported Feature" section
Added dividers between features in features section
added API column to the quantization methods table
added links to relevant notebooks in relevant places
made images of tasks (under results) a bit smaller
Fixed Headers issue (some headers were in wrong level.)
added more capabilities under debug feature - Xquant & network editor (including links to tutorial
centered all section titles (makes the page more clean in my opinion)
fixed according to review:
-- - added tutorials to qadvanced quatntization & Quantization parameter search.
-- - Updated EPTQ paper title and added E. Cohen as contributer
-- - changed type (on the how to -> on how to)
Pull Request Description:
Checklist before requesting a review:
[ ] I set the appropriate labels on the pull request.
[ ] I have added/updated the release note draft (if necessary).
[ ] I have updated the documentation to reflect my changes (if necessary).
[ ] All function and files are well documented.
[ ] All function and classes have type hints.
[ ] There is a licenses in all file.
[ ] The function and variable names are informative.
Round 2 of updaing readme.
Pull Request Description:
Checklist before requesting a review: