WebML CG Teleconference – 26 January 2022 - 05:00-06:00 UTC+0

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md


WebML CG Teleconference – 26 January 2022 - 05:00-06:00 UTC+0
See the timezone table ...
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#logistics>Logistics

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

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

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2022/01/26-webmachinelearning-minutes.html


________________________________
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#-model-loader-api>🔄 Model Loader API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-benchmark-discussion>ℹ️ Benchmark discussion

  *   Continued from 12 Jan meeting: open questions, proposed next steps

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-hardware-acceleration>ℹ️ Hardware acceleration

  *   What will the interface look like when hardware acceleration is supported?
     *   What if the data of a tensor is on GPU/TPU?
     *   Shall we let users know which ML accelerator is available on the platform? (Performance v.s. Privacy)

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-versioning>ℹ️ Versioning

  *   How to version the API? (supported ops and formats)

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-streaming-inputs>ℹ️ Streaming inputs

  *   Dedicated interface for streaming inputs (e.g. buffered inputs for video, audio)?

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-model-format>ℹ️ Model format

  *   Prototype vs standard format requirements
  *   "The Model Loader API needs a standard format supported across browsers and devices for broad interoperability." condition for standards adoption into WebML WG

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-01-26-cg-agenda.md#%E2%84%B9%EF%B8%8F-references>ℹ️ References

  *   WebML CG Teleconference – 12 Jan 2022 minutes<https://www.w3.org/2022/01/12-webmachinelearning-minutes.html>
  *   Updated explainer<https://github.com/webmachinelearning/model-loader/blob/main/explainer.md> and early spec draft<https://webmachinelearning.github.io/model-loader/>
  *   Chromium prototype<https://chromium-review.googlesource.com/c/chromium/src/+/3341136>

Received on Wednesday, 19 January 2022 09:25:03 UTC