Re: WebML CG Teleconference – 8 August 2019 - 14:00-15:00 UTC+0

Hi,

Ningxin - thanks for the proposal.

All - the call agenda has been amended:

https://github.com/webmachinelearning/meetings/blob/master/telcons/2019-08-08-agenda.md


Issue #17 will be given priority on this call and we'll discuss the details of PR #22 time permitting. My expectation is participants will review PR #22 ahead the call and submit review comments via GH. Since these two issues are intertwined it is good to try discuss them on the same call. (#22 assumes a graph-builder API per issue #16 resolution.)

Links to the above-mentioned resources in the agenda.

Thanks,

-Anssi


On 6 Aug 2019, at 5.40, Hu, Ningxin <ningxin.hu@intel.com<mailto:ningxin.hu@intel.com>> wrote:

Thanks Anssi.

I'd like to propose one topic (https://github.com/webmachinelearning/meetings/pull/11):

* Graph-building syntax simpler for web developers
* RESOLVED RESOLUTION: Craft a spec PR based on https://github.com/webmachinelearning/webnn/issues/16#issuecomment-504305802 considering feedback on the call
* Review the PR: https://github.com/webmachinelearning/webnn/pull/22


Regards,
-ningxin

-----Original Message-----
From: Kostiainen, Anssi [mailto:anssi.kostiainen@intel.com]
Sent: Monday, August 5, 2019 9:53 PM
To: public-webmachinelearning@w3.org<mailto:public-webmachinelearning@w3.org>
Subject: WebML CG Teleconference – 8 August 2019 - 14:00-15:00 UTC+0

https://github.com/webmachinelearning/meetings/blob/master/telcons/2019-

08-08-agenda.md

WebML CG Teleconference – 8 August 2019 - 14:00-15:00 UTC+0

### 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/2019Apr/0000.html
* Minutes: https://www.w3.org/2019/08/08-webmachinelearning-minutes.html


### Agenda

* Define the set of operations and their specification
* PROPOSED RESOLUTION: The specification will reference the ONNX
operations and if there are any improvements desired for ONNX the work
should be there.
* Discuss and resolve objections raised for the proposed resolution
* Clarify proposed resolution based on feedback where appropriate
(versioning etc.)
* https://github.com/webmachinelearning/webnn/issues/17


Thanks,

-Anssi (WebML CG chair)