Skip to content

[quant] quantized path for ConstantPadNd #43304

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
z-a-f wants to merge 11 commits into from
Closed

[quant] quantized path for ConstantPadNd #43304

z-a-f wants to merge 11 commits into from

Conversation

@z-a-f
Copy link

@z-a-f z-a-f commented Aug 19, 2020 •
edited
Loading

Stack from ghstack:

Differential Revision: D23231946

@z-a-f z-a-f mentioned this pull request Aug 19, 2020
Closed
@z-a-f z-a-f requested review from jerryzh168 and supriyar August 19, 2020 23:45
@dr-ci
Copy link

dr-ci bot commented Aug 19, 2020 •
edited
Loading

💊 CI failures summary and remediations

As of commit 4d5c29b (more details on the Dr. CI page):

  • 1/1 failures possibly* introduced in this PR
    • 1/1 non-CircleCI failure(s)

ci.pytorch.org: 1 failed

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 27 times.

z-a-f pushed a commit that referenced this pull request Aug 20, 2020
[quant] quantized path for ConstantPadNd
e44013e 
ghstack-source-id: 7c152e7
Pull Request resolved: #43304
jerryzh168
jerryzh168 reviewed Aug 21, 2020
View reviewed changes
aten/src/ATen/native/ConstantPadNd.cpp
const auto memory_format = self.suggest_memory_format();
output = at::_empty_affine_quantized(
new_shape, self.options().memory_format(memory_format),
self.q_scale(), self.q_zero_point(), c10::nullopt);
Copy link
Contributor

@jerryzh168 jerryzh168 Aug 21, 2020

Choose a reason for hiding this comment

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

is the last argument memory format? why do we have that?

Copy link
Author

@z-a-f z-a-f Aug 24, 2020

Choose a reason for hiding this comment

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

This is required because if not explicitly specified as nullopt there will be two conflicting memory_format arguments -- one from the options and one as an argument.

z-a-f pushed a commit that referenced this pull request Aug 24, 2020
[quant] quantized path for ConstantPadNd
3aaef78 
ghstack-source-id: 8c8364d
Pull Request resolved: #43304
z-a-f pushed a commit that referenced this pull request Aug 27, 2020
[quant] quantized path for ConstantPadNd
b7451d0 
ghstack-source-id: a5d7573
Pull Request resolved: #43304
z-a-f pushed a commit that referenced this pull request Aug 28, 2020
[quant] quantized path for ConstantPadNd
6d67eb2 
ghstack-source-id: 4109170
Pull Request resolved: #43304
@codecov
Copy link

codecov bot commented Aug 28, 2020 •
edited
Loading

Codecov Report

Merging #43304 into gh/z-a-f/54/base will not change coverage.
The diff coverage is n/a.

Impacted file tree graph

@@                Coverage Diff                @@
##           gh/z-a-f/54/base   #43304   +/-   ##
=================================================
  Coverage             69.24%   69.24%           
=================================================
  Files                   381      381           
  Lines                 47573    47573           
=================================================
  Hits                  32943    32943           
  Misses                14630    14630

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update f48d10b...4d5c29b. Read the comment docs.

z-a-f pushed a commit that referenced this pull request Aug 31, 2020
[quant] quantized path for ConstantPadNd
02b4417 
ghstack-source-id: ca8c32e
Pull Request resolved: #43304
z-a-f pushed a commit that referenced this pull request Sep 9, 2020
[quant] quantized path for ConstantPadNd
28052ee 
ghstack-source-id: 7a8571e
Pull Request resolved: #43304
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Sep 9, 2020

@z-a-f merged this pull request in 3674264.

@facebook-github-bot facebook-github-bot deleted the gh/z-a-f/54/head branch September 13, 2020 14:17
@nile649
Copy link

nile649 commented Oct 23, 2020 •
edited
Loading

Little help needed, can u tell me how to write my own quantized layer? I simply want to re-create quantized reflection padding?
@z-a-f you seem to have contributed many functions in the quantization module so any help I can get?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@jerryzh168 jerryzh168 jerryzh168 approved these changes

@supriyar supriyar Awaiting requested review from supriyar

Assignees

No one assigned

Labels

Merged

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@z-a-f @facebook-github-bot @nile649 @jerryzh168 @mruberry