Skip to content
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.

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

[quant][graphmode][fx] Add support for functional conv1d and conv3d #51155

Closed
wants to merge 2 commits into from

Conversation

jerryzh168
Copy link
Contributor

@jerryzh168 jerryzh168 commented Jan 26, 2021

Stack from ghstack:

Summary:
This PR added support for quantizing functional conv1d, conv3d, conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D26089965

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Jan 26, 2021

💊 CI failures summary and remediations

As of commit 83c0bee (more details on the Dr. CI page):


  • 2/7 failures possibly* introduced in this PR
    • 2/2 non-CircleCI failure(s)
  • 5/7 broken upstream at merge base 1ee5d11 on Jan 26 from 12:49pm to 7:04pm

🚧 5 fixed upstream failures:

These were probably caused by upstream breakages that were already fixed.

Please rebase on the viable/strict branch (expand for instructions)

If your commit is older than viable/strict, run these commands:

git fetch https://github.com/pytorch/pytorch viable/strict
git rebase FETCH_HEAD

Check out the recency history of this "viable master" tracking branch.


Extra GitHub checks: 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 to the (internal) Dr. CI Users group.

…nd conv3d"

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D26089965](https://our.internmc.facebook.com/intern/diff/D26089965)

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Jan 27, 2021
Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 836346b4ea5f0f5a558f3febe88fa333b82b48a6
Pull Request resolved: #51155
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in dd1a97b.

@mruberry
Copy link
Collaborator

Unlanding. This broke several builds, as its Github CI indicates. Sample failure:

test_run_mypy [mypy.ini] - TestTypeHints
test_type_hints.py

Traceback (most recent call last):
  File "test_type_hints.py", line 171, in test_run_mypy
    self.fail(f"mypy failed: {stdout} {stderr}")
AssertionError: mypy failed: torch/quantization/fx/utils.py:206: error: Incompatible return value type (got "Optional[Any]", expected "Callable[..., Any]")  [return-value]
Found 1 error in 1 file (checked 1211 source files)

@mruberry mruberry reopened this Jan 27, 2021
jerryzh168 added a commit that referenced this pull request Jan 28, 2021
…51155)

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewed By: vkuzo

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Jan 28, 2021
…51155)

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewed By: vkuzo

ghstack-source-id: a2c4439b244f64533474d65a689435db5fe26f91
Pull Request resolved: #51254
@jerryzh168
Copy link
Contributor Author

will reland in #51254

@jerryzh168 jerryzh168 closed this Jan 28, 2021
jerryzh168 added a commit that referenced this pull request Jan 28, 2021
…conv1d and conv3d (#51155)"

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewed By: vkuzo

Differential Revision: [D26116172](https://our.internmc.facebook.com/intern/diff/D26116172)

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Jan 28, 2021
…51155)

Summary:
This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Reviewed By: vkuzo

ghstack-source-id: 8537b36cbdb26dbc503294c4f5148d3bef73152c
Pull Request resolved: #51254
facebook-github-bot pushed a commit that referenced this pull request Jan 28, 2021
…51155) (#51254)

Summary:
Pull Request resolved: #51254

This PR added support for quantizing functional conv1d, conv3d,  conv1d_relu and conv3d_relu

Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_functional_conv

Imported from OSS

Reviewed By: vkuzo

Differential Revision: D26116172

fbshipit-source-id: 56e7d799c11963fe59ee3a1b6eb23f52007b91dc
@facebook-github-bot facebook-github-bot deleted the gh/jerryzh168/534/head branch January 31, 2021 15:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants