-
Notifications
You must be signed in to change notification settings - Fork 25.6k
[quant][pt2] Add prepare QAT test for resnet18 #103020
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/103020
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 5ce5c0f: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D46456243 |
a487f59
to
b5d1ef0
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
b5d1ef0
to
3202067
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
3202067
to
6bef00c
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
6bef00c
to
b7651e4
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
b7651e4
to
b03755b
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
b03755b
to
3410d29
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
3410d29
to
0b5f448
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
This pull request was exported from Phabricator. Differential Revision: D46456243 |
0b5f448
to
05a5efb
Compare
Summary: Pull Request resolved: pytorch#103020 Prepare QAT for resnet18 has matching numerics with FX. Adding this test requires us to refactor the way the test code is structured, however. Test Plan: python test/test_quantization.py TestQuantizePT2EModels.test_qat_resnet18 Reviewed By: kimishpatel, jerryzh168 Differential Revision: D46456243 fbshipit-source-id: 9735f9d32b1bf8940b8bc5014e9eb41dcc232fa6
05a5efb
to
5ce5c0f
Compare
This pull request was exported from Phabricator. Differential Revision: D46456243 |
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Summary:
Prepare QAT for resnet18 has matching numerics with FX.
Adding this test requires us to refactor the way the test code
is structured, however.
Test Plan: python test/test_quantization.py TestQuantizePT2EModels.test_qat_resnet18
Differential Revision: D46456243