WebML CG Teleconference – 7 January 2021 - 15:00-16:00 UTC+0

Welcome to 2021!
This is the new year's first call that gets us back to our bi-weekly cadence after the break.

We have developments and discussions underway that line up for an exciting start for 2021.

As usual, please check out the latest agenda for any last-minute changes at: https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md


Please find the agenda snapshot from below.

Talk to you soon!

-Anssi

WebML CG Teleconference – 7 January 2021 - 15:00-16:00 UTC+0
San Francisco (U.S.A. - California)     Thu, 7 January 2021     07:00   UTC-8 hours
Boston (U.S.A. - Massachusetts) Thu, 7 January 2021     10:00   UTC-5 hours
London (United Kingdom - England)       Thu, 7 January 2021     15:00   UTC+0 hours
Berlin (Germany)        Thu, 7 January 2021     16:00   UTC+1 hours
Helsinki (Finland)      Thu, 7 January 2021     17:00   UTC+2 hours
Shanghai (China)        Thu, 7 January 2021     23:00   UTC+8 hours
Tokyo (Japan)   Fri, 8 January 2021     00:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 7 January 2021     15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20210107T15


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ?
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

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

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2021Apr/0000.html (login with your W3C account<https://www.w3.org/Help/Account/>) - Zoom app install<https://zoom.us/download> recommended
  *   Minutes: https://www.w3.org/2021/01/07-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#webnn-api-tag-review-progress-report>WebNN API TAG review progress report

Review TAG review feedback:

https://github.com/w3ctag/design-reviews/issues/570


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#security-and-privacy-considerations>Security and Privacy considerations

Review proposed questionnaire responses, fill in TBDs:

https://github.com/webmachinelearning/webnn/issues/119


Discuss Security and Privacy considerations for the spec:

https://github.com/webmachinelearning/webnn/issues/122


Review TAG guidelines:

https://www.w3.org/TR/security-privacy-questionnaire/#considerations


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#support-style-transfer-models>Support style transfer models

Review PR:

https://github.com/webmachinelearning/webnn/pull/123


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#dynamic-shape-inference>Dynamic shape inference

Discuss proposal:

https://github.com/webmachinelearning/webnn/issues/124


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#webnn-conv2d-layout-parameter-tensorflow-incompatibility>WebNN conv2d layout parameter TensorFlow incompatibility

Discuss issue, solicit proposals:

https://github.com/webmachinelearning/webnn/issues/125


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#super-resolution-models>Super-resolution models

Discuss proposal:

https://github.com/webmachinelearning/webnn/issues/127


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#int8-quantized-models>int8 quantized models

Discuss proposal:

https://github.com/webmachinelearning/webnn/issues/128


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#conformance-testing-of-webnn-api>Conformance testing of WebNN API

Discuss conformance testing of operations, integration of web-platform-tests with NNAPI CTS

Review PR for generated NNAPI CTS:

https://github.com/webmachinelearning/webnn-polyfill/pull/29


Review PR for SqueezeNet model test:

https://github.com/webmachinelearning/webnn-polyfill/pull/32


Web-platform-tests framework for writing test cases:

https://web-platform-tests.org/writing-tests/testharness.html


https://web-platform-tests.org/writing-tests/idlharness.html


Background discussed at workshop:

https://github.com/w3c/machine-learning-workshop/issues/80


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#nsnet2-sample>NSNet2 sample

Discuss the sample of NSNet2 which is one of the first-wave models and used in explainer key scenarios

Review PR of NSNet2 PR:

https://github.com/webmachinelearning/webnn-samples/pull/22


Update the NSNet sample code of explainer to NSNet2:

https://github.com/webmachinelearning/webnn/blob/master/explainer.md#key-scenarios


Potential memory leaking issue of webnn-polyfill using tf.js WebGL backend:

https://github.com/webmachinelearning/webnn-samples/pull/22#issuecomment-730217119


<https://github.com/webmachinelearning/meetings/blob/master/telcons/2021-01-07-agenda.md#proposals-for-future-work>Proposals for future work

Discuss new proposals submitted for consideration for future work:

  *   Data processing: https://github.com/webmachinelearning/proposals/issues/1


  *   Operation-specific APIs: https://github.com/webmachinelearning/proposals/issues/2