WebML WG Teleconference – 11 May 2023 - 14:00-15:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md



WebML WG Teleconference – 11 May 2023 - 14:00-15:00 UTC
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2023/05/11-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-webidl-and-infra-standard-conventions>ℹ️ WebIDL and Infra standard conventions

  *   The constant() method steps

     *    meta issue: webmachinelearning/webnn#210 (comment)<https://github.com/webmachinelearning/webnn/issues/210#issuecomment-1326361748>
     *    PR: webmachinelearning/webnn#365<https://github.com/webmachinelearning/webnn/pull/365>
  *   Sync async algorithms

     *    issue: webmachinelearning/webnn#316<https://github.com/webmachinelearning/webnn/issues/316>
     *    PR: webmachinelearning/webnn#329<https://github.com/webmachinelearning/webnn/pull/329>
  *   The builder.input() method steps

     *    meta issue: webmachinelearning/webnn#210 (comment)<https://github.com/webmachinelearning/webnn/issues/210#issuecomment-1326361748>
     *    PR: webmachinelearning/webnn#364<https://github.com/webmachinelearning/webnn/pull/364>
  *   Review the rest of the standard conventions PRs (all ready for review):

     *    meta issue: webmachinelearning/webnn#210 (comment)<https://github.com/webmachinelearning/webnn/issues/210#issuecomment-1326361748>
     *    open PRs: https://github.com/webmachinelearning/webnn/pulls


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements-editorials-questions>ℹ️ Enhancements, editorials, questions

  *   Subclass MLGraph based on the context that creates it

     *    issue: webmachinelearning/webnn#344<https://github.com/webmachinelearning/webnn/issues/344>
  *   Error handling of MLNamedArrayBufferViews transfer algorithm

     *    issue: webmachinelearning/webnn#351<https://github.com/webmachinelearning/webnn/issues/351>
  *   Support depth_multiplier > 1 for a depthwise conv2d op

     *    issue: webmachinelearning/webnn#353<https://github.com/webmachinelearning/webnn/issues/353>
  *   Clarify interpolation algorithm for resample2d

     *    issue: webmachinelearning/webnn#358<https://github.com/webmachinelearning/webnn/issues/358>
     *    related issue: webmachinelearning/webnn#270<https://github.com/webmachinelearning/webnn/issues/270>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-05-11-wg-agenda.md#%E2%84%B9%EF%B8%8F-support-for-transformers>ℹ️ Support for transformers

Continue discuss transformers and related requirements and gaps. Test our improved contribution guidelines with these new ops: explore key use cases, sample models, cross-framework support, cross-platform implementability.

Status: The WG decided to start explore support for transformers in WebNN.

Next step: Identify use cases. Contributions welcome via issue 375.

  *    issue: webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>
  *   Guidelines for adding new ops: https://github.com/webmachinelearning/webnn/blob/main/CONTRIBUTING.md#proposing-and-adding-a-new-operation

  *   Minutes from the kick off: https://www.w3.org/2023/04/27-webmachinelearning-minutes.html#t11