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.

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

Add universal/consistent tests for loss modules #4105

Closed
njzjz opened this issue Sep 5, 2024 · 1 comment · Fixed by #4354 or #4531
Closed

Add universal/consistent tests for loss modules #4105

njzjz opened this issue Sep 5, 2024 · 1 comment · Fixed by #4354 or #4531
Assignees
@iProzd
Labels
enhancement
Milestone
v3.1.0

Comments

@njzjz
Copy link
Member

njzjz commented Sep 5, 2024 •
edited
Loading 

+ Hits        42870    43087     +217     
- Misses       7822     7934     +112     
- Partials      946      948       +2

I see that 1/3 of the new codes have not been tested.

Where can I see these datas about missing UT? I will add UT based on these datas.

You can click the link sent by @codecov or click the codecov checks.

It looks like the loss module is not tested. @iProzd Do we have a universal test fixture for loss functions?

Not yet, maybe we need a discussion to design a universal test for loss modules.

Originally posted by @iProzd in #3867 (comment)
@njzjz njzjz mentioned this issue Sep 5, 2024
Merged
@njzjz njzjz changed the title Add universal test for loss modules Add universal/consistent tests for loss modules Sep 5, 2024
@iProzd iProzd self-assigned this Sep 26, 2024
@iProzd iProzd moved this to mustfix in DeePMD-kit V3.0.0 RC Sep 26, 2024
@njzjz njzjz added this to the v3.0.0 milestone Sep 26, 2024
@njzjz njzjz linked a pull request Nov 13, 2024 that will close this issue
feat(pt): add universal test for loss #4354
Merged
@coderabbitai coderabbitai bot mentioned this issue Nov 14, 2024
Merged
@njzjz
Copy link
Member Author

njzjz commented Nov 15, 2024

Now we have the universal tests but not the consistent tests.

@njzjz njzjz modified the milestones: v3.0.0, v3.1.0 Nov 15, 2024
@njzjz njzjz mentioned this issue Dec 13, 2024
Merged
njzjz added a commit to njzjz/deepmd-kit that referenced this issue Jan 5, 2025
@njzjz
feat: dpmodel energy loss & consistent tests
d94010c 
Fix deepmodeling#4105. Fix deepmodeling#4429.

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@njzjz njzjz mentioned this issue Jan 5, 2025
Merged
@njzjz njzjz linked a pull request Jan 5, 2025 that will close this issue
feat: dpmodel energy loss & consistent tests #4531
Merged
github-merge-queue bot pushed a commit that referenced this issue Jan 7, 2025
@njzjz
feat: dpmodel energy loss & consistent tests (#4531)
dbdb9b9 
Fix #4105. Fix #4429.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

## Release Notes

- **New Features**
- Introduced a new energy loss calculation framework with support for
multiple machine learning backends.
- Added serialization and deserialization capabilities for loss modules.
- Added a new class `EnergyLoss` for computing energy-related loss
metrics.
  
- **Documentation**
  - Added SPDX license identifiers to multiple files.
  - Included docstrings for new classes and methods.

- **Tests**
- Implemented comprehensive test suite for energy loss functions across
different platforms (TensorFlow, PyTorch, Paddle, JAX).
- Introduced a new test class `TestEner` for evaluating energy loss
functions.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@njzjz njzjz closed this as completed Jan 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@iProzd iProzd

Labels
enhancement
Projects
Multiple backend support for DeePMD-kit
Archived in project
DeePMD-kit V3.0.0 RC
Status: mustfix
Milestone
v3.1.0
2 participants
@njzjz @iProzd