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

refactor: uncouple Descriptor and Fitting from Trainer #2549

Conversation

njzjz
Copy link
Member

@njzjz njzjz commented May 21, 2023

No description provided.

njzjz added 3 commits May 21, 2023 05:52
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@codecov
Copy link

codecov bot commented May 21, 2023

Codecov Report

Patch coverage: 83.03% and project coverage change: -2.42 ⚠️

Comparison is base (5f3bbbc) 75.35% compared to head (125b619) 72.93%.

Additional details and impacted files
@@            Coverage Diff             @@
##            devel    #2549      +/-   ##
==========================================
- Coverage   75.35%   72.93%   -2.42%     
==========================================
  Files         227      234       +7     
  Lines       23816    25947    +2131     
  Branches     1666     1852     +186     
==========================================
+ Hits        17947    18925     +978     
- Misses       4793     5845    +1052     
- Partials     1076     1177     +101     
Impacted Files Coverage Δ
deepmd/descriptor/loc_frame.py 95.31% <ø> (ø)
deepmd/descriptor/se_a.py 95.72% <ø> (ø)
deepmd/descriptor/se_a_ebd.py 67.13% <ø> (ø)
deepmd/descriptor/se_a_ef.py 53.55% <ø> (ø)
deepmd/descriptor/se_a_mask.py 85.45% <ø> (ø)
deepmd/descriptor/se_r.py 95.33% <ø> (ø)
deepmd/descriptor/se_t.py 94.87% <ø> (ø)
deepmd/loss/dos.py 9.18% <ø> (ø)
deepmd/loss/ener.py 66.26% <ø> (ø)
deepmd/utils/type_embed.py 100.00% <ø> (ø)
... and 15 more

... and 24 files with indirect coverage changes

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.

@wanghan-iapcm wanghan-iapcm requested a review from iProzd May 22, 2023 14:47
njzjz added 3 commits May 22, 2023 16:58
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
deepmd/train/trainer.py Show resolved Hide resolved
deepmd/model/ener.py Outdated Show resolved Hide resolved
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@wanghan-iapcm wanghan-iapcm merged commit 0d732ad into deepmodeling:devel Jun 2, 2023
wanghan-iapcm pushed a commit that referenced this pull request Jun 12, 2023
Fix a bug introduced in #2549.

Add tests for it.

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
@njzjz njzjz mentioned this pull request Jul 17, 2023
wanghan-iapcm pushed a commit that referenced this pull request Jul 20, 2023
Add an experimental model called pairwise DPRc, which is fragment-based
and integrated with QM/MM. Compression inference and training are
supported.
Unit tests and documentation have been added.

Some features or bugfix to implement this PR have been merged in #2549,
#2600, #2601, #2604, #2631, #2635, #2665, #2666, #2667, and #2679.
This PR makes some changes to `model.build_descrpt` additionally:
- fix errors when the suffix is not empty
- fix errors when `fparam` or `aparam` are given
- support model-customized `input_map`

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
@njzjz njzjz mentioned this pull request Oct 22, 2024
github-merge-queue bot pushed a commit that referenced this pull request Oct 23, 2024
It was forgotten in #2549

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

- **New Features**
- Introduced the DPA-1 model with an attention mechanism for molecular
simulation.
- Added the `se_a_mask` descriptor for DP/MM simulations with dynamic
atom counts.
	- Expanded support for multi-task fine-tuning in PyTorch.

- **Documentation Enhancements**
- Improved clarity and detail in various documents, including model
compression, DPLR model training, and fine-tuning processes.
- Updated references to follow a standardized format, enhancing
navigation and understanding.

- **Bug Fixes**
- Corrected references and parameters across multiple documents to
ensure accuracy in model configurations and training instructions.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants