Skip to content

[quant] conv2d per channel quantization support #25134

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
wants to merge 8 commits into from
Closed

[quant] conv2d per channel quantization support #25134

wants to merge 8 commits into from

Conversation

dskhudia
Copy link
Contributor

@dskhudia dskhudia commented Aug 23, 2019 •
edited
Loading

Stack from ghstack:

copy of #24936

it was reverted #25131

Per channel quantization support in qconv2d + tests

Differential Revision: D16999104

@pytorchbot pytorchbot added module: operators oncall: quantization Quantization support in PyTorch labels Aug 23, 2019
@dskhudia dskhudia requested a review from jianyuh August 23, 2019 23:43
@jianyuh
Copy link
Member

jianyuh commented Aug 23, 2019

This is re-applying the PR (#24936). Previously there is an issue of OSS landing tools: In the stack of dependent diffs, somehow #2 and #3 landed before #1. This caused #24936 lands before #24934. Previously to avoid the build error propagation, #25131 is applied.

@dskhudia
Update on "[quant] per channel quantization support"
f42e470 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 23, 2019
@dskhudia
[quant] per channel quantization support
b40c817 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88914362

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia dskhudia changed the title [quant] per channel quantization support [quant] conv2d per channel quantization support Aug 23, 2019
@dskhudia
Update on "[quant] conv2d per channel quantization support"
55ae41d 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 24, 2019
@dskhudia
[quant] per channel quantization support
821d779 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88920488

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia
Update on "[quant] conv2d per channel quantization support"
0d6d8b9 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 24, 2019
@dskhudia
[quant] per channel quantization support
4ad1efb 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88929180

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia
Update on "[quant] conv2d per channel quantization support"
54abe5e 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 24, 2019
@dskhudia
[quant] per channel quantization support
013702e 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88930137

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia
Update on "[quant] conv2d per channel quantization support"
b1ce522 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 25, 2019
@dskhudia
[quant] per channel quantization support
f5b8a50 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88977353

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia
Update on "[quant] conv2d per channel quantization support"
7fa323b 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 25, 2019
@dskhudia
[quant] per channel quantization support
129cb2c 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88979399

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia
Update on "[quant] conv2d per channel quantization support"
0bf38a7 
copy of #24936 

it was reverted #25131 


Per channel quantization support in qconv2d + tests

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
dskhudia added a commit that referenced this pull request Aug 26, 2019
@dskhudia
[quant] per channel quantization support
ff3c701 
Pull Request resolved: #25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/


Per channel quantization support in qconv2d + tests
ghstack-source-id: 88992610

Differential Revision: [D16999104](https://our.internmc.facebook.com/intern/diff/D16999104/)
@dskhudia dskhudia mentioned this pull request Aug 26, 2019
Closed
@zou3519 zou3519 deleted the gh/dskhudia/4/head branch August 26, 2019 17:43
zdevito pushed a commit to zdevito/ATen that referenced this pull request Aug 26, 2019
@dskhudia @facebook-github-bot
per channel quantization support (#25134)
7301e55 
Summary:
Pull Request resolved: pytorch/pytorch#25134

copy of https://our.intern.facebook.com/intern/diff/D16909378/

it was reverted in https://our.intern.facebook.com/intern/diff/D16997422/

Per channel quantization support in qconv2d + tests
ghstack-source-id: 88992610

Test Plan:
buck test mode/dev caffe2/test:quantized -- --print-passing-details
```
Finished test run: https://our.intern.facebook.com/intern/testinfra/testrun/4222124656103386
Summary (total time 64.42s):
  PASS: 33
  FAIL: 0
  SKIP: 3
    caffe2/test:quantized - test_qlinear (test_quantized.TestDynamicQuantizedLinear)
    caffe2/test:quantized - test_qnnpack_relu (test_quantized.TestQNNPackOps)
    caffe2/test:quantized - test_qnnpack_linear (test_quantized.TestQNNPackOps)
  FATAL: 0
  TIMEOUT: 0
  OMIT: 0
```

Differential Revision: D16999104

fbshipit-source-id: 008447ffbc0144f0fc76f3cf143a2f69b65922fd
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in d806257.

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

@jianyuh jianyuh jianyuh approved these changes

Assignees
No one assigned
Labels
Merged oncall: quantization Quantization support in PyTorch
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@dskhudia @jianyuh @facebook-github-bot @pytorchbot @mruberry