- From: Kostiainen, Anssi <anssi.kostiainen@intel.com>
- Date: Thu, 13 Oct 2022 08:59:12 +0000
- To: "public-webmachinelearning-wg@w3.org" <public-webmachinelearning-wg@w3.org>
- Message-ID: <237A18AF-92F7-4627-83D2-14BBC1C32A32@intel.com>
Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md
WebML WG Teleconference – 20 October 2022 - 14:00-15:00 UTC
San Francisco (U.S.A. - California) Thu, 20 October 2022 07:00 UTC-7 hours
Boston (U.S.A. - Massachusetts) Thu, 20 October 2022 10:00 UTC-4 hours
London (United Kingdom - England) Thu, 20 October 2022 15:00 UTC+1 hours
Berlin (Germany) Thu, 20 October 2022 16:00 UTC+2 hours
Helsinki (Finland) Thu, 20 October 2022 17:00 UTC+3 hours
Shanghai (China) Thu, 20 October 2022 22:00 UTC+8 hours
Tokyo (Japan) Thu, 20 October 2022 23:00 UTC+9 hours
Corresponding UTC (GMT) Thu, 20 October 2022 14:00 UTC
Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20221020T14
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-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/2022/10/20-webmachinelearning-minutes.html
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md#%E2%84%B9%EF%B8%8F-webml-wg-charter-2023-2025-under-development>ℹ️ WebML WG Charter 2023-2025 under development
Web Machine Learning Working Group Charter for 2023-2025 is now under development. Please review the draft PR and open issues, provide your comments and open new issues as appropriate to help shape the WG's technical scope.
* Announcement https://lists.w3.org/Archives/Public/public-webmachinelearning-wg/2022Oct/0002.html
* Charter PR w3c/machine-learning-charter#19<https://github.com/w3c/machine-learning-charter/pull/19>
* Open issues https://github.com/w3c/machine-learning-charter/issues
* Features deferred to WebNN v2
* Dedicated ML hardware accelerators: NPU, VPU, xPU
* Set of ops supported must be more comprehensive
* Level of abstraction for neural net operations
* WebRTC coordination
* WebGPU interoperability
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-candidate-recommendation-open-issues>ℹ️ WebNN API Candidate Recommendation open issues
Review and discuss the current CR issues, work out a plan to address the issues prior to the expected CR publication.
* Current CR issues https://github.com/webmachinelearning/webnn/labels/cr
* Web platform tests
* Continue discuss w-p-t updates informed by Operator Tolerance Conformance Considerations<https://lists.w3.org/Archives/Public/www-archive/2022Oct/att-0000/DirectML_Operator_Tolerance_Conformance.pdf> presentation
* webnn-baseline implementation plan update https://github.com/webmachinelearning/webnn-baseline/issues
* ➡️ Status: Recommended tolerances reviewed, w-p-t & webnn-baseline reference impl updates in progress
* Add method steps and normative algorithms to operations
* issue: webmachinelearning/webnn#210<https://github.com/webmachinelearning/webnn/issues/210>
* issue: webmachinelearning/webnn#211<https://github.com/webmachinelearning/webnn/issues/211>
* ➡️ Status: Spec changes in progress, review any proposals submitted
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-webgpu-interop>ℹ️ WebNN-WebGPU interop
Review WebGPU interop mechanism and its normative WebGPU dependencies to assess whether WebGPU interop is a feasible CR target or a v2 feature.
WebNN API interface to record the ML workload onto a WebGPU-compatible GPUCommandBuffer:
* MLCommandEncoder https://www.w3.org/TR/webnn/#mlcommandencoder
Normative WebGPU API dependencies:
* GPUBuffer https://gpuweb.github.io/gpuweb/#buffer-interface
* GPUCommandBuffer https://gpuweb.github.io/gpuweb/#command-buffers
* GPUCommandBufferDescriptor https://gpuweb.github.io/gpuweb/#dictdef-gpucommandbufferdescriptor
* GPUDevice https://gpuweb.github.io/gpuweb/#gpu-device
* GPUQueue https://gpuweb.github.io/gpuweb/#gpuqueue
* GPUTexture https://gpuweb.github.io/gpuweb/#gputexture
See also:
* 22 Sep 2022 discussion https://www.w3.org/2022/09/22-webmachinelearning-minutes.html#t06
* related issue: webmachinelearning/webnn#264<https://github.com/webmachinelearning/webnn/issues/264>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md#%E2%84%B9%EF%B8%8F-prs-in-review>ℹ️ PRs in review
* Use unsigned long for size related options of conv2d, convTranspose2d and pooling operations
* issue: webmachinelearning/webnn#269<https://github.com/webmachinelearning/webnn/issues/269>
* PR: webmachinelearning/webnn#294<https://github.com/webmachinelearning/webnn/pull/294>
* Change newShape of reshape to a sequence of nullable unsigned long
* issue: webmachinelearning/webnn#289<https://github.com/webmachinelearning/webnn/issues/289>
* PR: webmachinelearning/webnn#291<https://github.com/webmachinelearning/webnn/pull/291>
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-10-20-wg-agenda.md#%E2%84%B9%EF%B8%8F-proposed-new-features>ℹ️ Proposed new features
* Unsqueeze operator is missing
* issue: webmachinelearning/webnn#296<https://github.com/webmachinelearning/webnn/issues/296>
* Need for type casting?
* issue: webmachinelearning/webnn#284<https://github.com/webmachinelearning/webnn/issues/284>
* Softmax should only support input of floating-point types
* issue: webmachinelearning/webnn#283<https://github.com/webmachinelearning/webnn/issues/283>
Revisit proposed new features discussed earlier:
* Should MLBufferView + MLOperandDescriptor be strongly typed
* proposed CR issue: webmachinelearning/webnn#275<https://github.com/webmachinelearning/webnn/issues/275>
* Support coordinate transformation modes for Resample2d
* proposed CR issue: webmachinelearning/webnn#270<https://github.com/webmachinelearning/webnn/issues/270>
* l2Pool2d algorithm clarifications
* issue: webmachinelearning/webnn#278<https://github.com/webmachinelearning/webnn/issues/278>
Received on Thursday, 13 October 2022 08:59:31 UTC