Closed huningxin closed 2 years ago
To establish the baseline of WebNN conformance test and answer the requirements raised in WebML WG Teleconference – 2 Dec 2021, including
by @wchao1115
all computation is done in double precision we don't want any intermediate casting an open source ref, anyone can look at the code and be confident
by @dontcallmedom
the codebase should be easy to review, not too many layers of abstraction
I would propose to create a baseline implementation of WebNN ops that:
I have been working with @BruceDai on a staging repo: https://github.com/huningxin/webnn-baseline, with some initial ops, like conv2d. If it looks like a right approach, we are happy to contribute it to the group repo for wider review.
/cc @anssiko @wchao1115 @dontcallmedom
As this is for w-p-t, mark it with 'cr'.
Initial implementation: https://github.com/webmachinelearning/webnn-baseline/pull/1
To establish the baseline of WebNN conformance test and answer the requirements raised in WebML WG Teleconference – 2 Dec 2021, including
by @wchao1115
by @dontcallmedom
I would propose to create a baseline implementation of WebNN ops that:
I have been working with @BruceDai on a staging repo: https://github.com/huningxin/webnn-baseline, with some initial ops, like conv2d. If it looks like a right approach, we are happy to contribute it to the group repo for wider review.
/cc @anssiko @wchao1115 @dontcallmedom