WebML WG Teleconference – 24 August 2023 - 14:00-15:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md


WebML WG Teleconference – 24 August 2023 - 14:00-15:00 UTC
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-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/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2023/08/24-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-google-chrome-teams-feedback-on-webnn-api>ℹ️ Google Chrome team's feedback on WebNN API

Vivek and Joshua B have gathered feedback from various Google teams interested in WebNN and will share their thoughts with the WG for discussion.

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-v2-review-proposed-new-ops-and-data-types>ℹ️ WebNN v2: review proposed new ops and data types

Review and discuss the proposed new ops and data types informed by v2 model targets and recent prototyping efforts.

Proposed models:

  *   Text-to-image: Stable Diffusion unet/VAE/text encoder
  *   Image segmentation: Segment Everything decoder
  *   Speech-to-text: Whisper Tiny
  *   Text-to-text? Summarization, translation, code completion demonstrated by Transformers.js?

Proposed new ops:

  *   Logical elementwise comparison/selection operations: equal, greater, lesser, logicalNot, elementwiseIf/ternary, greaterOrEqual/lesserOrEqual
  *   More elementwise unary operations: identity, sqrt, erf (Gauss err func), reciprocal
  *   Reshaping operations: squeeze, unsqueeze, flattenTo2d
  *   Data rearrangement operations: expand, gather
  *   Normalization operations: meanVarianceNormalization
  *   Index seeking operations: argMin/argMax
  *   Misc: cast, fillSequence, triangularMatrix, shape
  *   Others?

Proposed new data types: int64, uint64

Details: webmachinelearning/webnn#375 (comment)<https://github.com/webmachinelearning/webnn/issues/375#issuecomment-1674224992>

Background material:

  *   Transformers.js presentation by Joshua Lochner<https://lists.w3.org/Archives/Public/www-archive/2023Jun/att-0000/Transformers_js.pdf>
  *   Transformer models presentation by Dwayne Robinson<https://lists.w3.org/Archives/Public/www-archive/2023Jun/att-0005/2023-06-29_WebNN_and_Transformers_Progress_W3C.pdf>
  *   Transformer-based models and use cases discussion: webmachinelearning/webnn#375<https://github.com/webmachinelearning/webnn/issues/375>
  *   Proposed v2 ops<https://github.com/webmachinelearning/webnn/issues?q=is%3Aopen+label%3A%22operation+set%22+label%3A%22v2%22> (open new issues for v2 op proposals)

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-webidl-and-infra-standard-conventions>ℹ️ WebIDL and Infra standard conventions

Decide whether we're ready to merge the zk-conventions-integration integration branch to main.

These changes align the entire specification with modern specification conventions and add stylistic improvements on top that make navigating this specification more delightful experience.

The following resources are made available to the group to assist in this review task:

  *   Preview<https://pr-preview.s3.amazonaws.com/zolkis/webnn/pull/446.html> of zk-conventions-integration PR
  *   Diff<https://pr-preview.s3.amazonaws.com/zolkis/webnn/pull/446.html> between main and zk-conventions-integration PR
  *   Issues addressed and PRs merged to<https://github.com/webmachinelearning/webnn/issues/210#issuecomment-1326361748> zk-conventions-integration (see "🟡 review feedback" annotations)
  *   Commits<https://github.com/webmachinelearning/webnn/compare/main...zk-conventions-integration> ahead of main

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-08-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-enhancements>ℹ️ Enhancements

  *   split() into sizes not widely supported
     *    issue: webmachinelearning/webnn#392<https://github.com/webmachinelearning/webnn/issues/392>
  *   Clarify the restriction for minValue and maxValue of MLClampOptions
     *    issue: webmachinelearning/webnn#396<https://github.com/webmachinelearning/webnn/issues/396>