Skip to content

Conversation

@kimishpatel
Copy link
Contributor

Summary:
This is to unify how output scale calculation is to be done between
fbgemm and qnnpack (servers vs mobile).

Test Plan:
Quantization tests.

Reviewers:

Subscribers:

Tasks:

Tags:

Copy link
Contributor

@facebook-github-bot facebook-github-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kimishpatel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should this be multiplying by inv_output_scale?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Aaaah. yes. Some changes got dropped by me I think.

@kimishpatel kimishpatel force-pushed the inverse_output_scale branch from 503d620 to 79a90ba Compare July 13, 2020 17:11
Copy link
Contributor

@facebook-github-bot facebook-github-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kimishpatel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Copy link
Contributor

@facebook-github-bot facebook-github-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kimishpatel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@kimishpatel kimishpatel force-pushed the inverse_output_scale branch from 79a90ba to 1d7a6f4 Compare August 3, 2020 14:54
@kimishpatel kimishpatel requested a review from apaszke as a code owner August 3, 2020 14:54
Summary:
This is to unify how output scale calculation is to be done between
fbgemm and qnnpack (servers vs mobile).

Test Plan:
Quantization tests.

Reviewers:

Subscribers:

Tasks:

Tags:
@kimishpatel kimishpatel force-pushed the inverse_output_scale branch from 1d7a6f4 to 5b24352 Compare August 3, 2020 14:57
@dr-ci
Copy link

dr-ci bot commented Aug 3, 2020

💊 CI failures summary and remediations

As of commit 5b24352 (more details on the Dr. CI page):


💚 💚 Looks good so far! There are no failures yet. 💚 💚


This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions on the GitHub issue tracker or post in the (internal) Dr. CI Users group.

See how this bot performed.

This comment has been revised 1 time.

Copy link
Contributor

@facebook-github-bot facebook-github-bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kimishpatel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@kimishpatel merged this pull request in f0fd1cc.

@facebook-github-bot facebook-github-bot deleted the inverse_output_scale branch January 27, 2021 18:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants