refact: the DPA2 descriptor #3758

iProzd · 2024-05-07T17:28:39Z

Refact the DPA2 descriptor in PyTorch with clearer interface
Support residual
Remove bn
Add numpy implement

Summary by CodeRabbit

New Features
- Added a new descriptor class DescrptDPA2 implementing DPA-2 functionality for computing descriptors and representations based on input coordinates and atom types.
- Expanded supported backends for DPA-2 descriptor to include DP in addition to PyTorch.
Documentation
- Updated the supported backends information in the documentation for the DPA-2 descriptor to reflect the addition of DP backend support.
- Added a reference to the model implementation and a training example link in the DPA-2 descriptor documentation.
Tests
- Introduced test cases for the DescrptDPA2 class in different frameworks like TensorFlow, PyTorch, and DeepMD to cover various parameters and configurations.
- Validated the functionality of the DescrptDPA2 descriptor class for deep learning models in the test case class TestDescrptDPA2.

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

coderabbitai · 2024-05-07T17:29:19Z

Warning

Rate Limit Exceeded

@iProzd has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 4 minutes and 1 seconds before requesting another review.

How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.
Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.
Please see our FAQ for further information.

Commits

Files that changed from the base of the PR and between f17f40f and e223336.

Walkthrough

The recent updates focus on enhancing the deepmd module by refining documentation, optimizing imports, and enriching class functionalities. These changes aim to improve clarity, functionality, and compatibility within the module, including method descriptions, class replacements, and support for new modes and functionalities.

Changes

Files	Summary of Changes
`deepmd/pt/model/descriptor/dpa2.py`	- Introduces `DescrptDPA2` class for DPA-2 descriptor functionality. - Adds properties `dim_out` and `dim_emb`. - Updates imports and includes new modules and classes.
`deepmd/pt/model/descriptor/repformers.py`	- Replaces `SimpleLinear` with `MLPLayer`. - Updates `se_repformer` class parameters and `forward` method implementation.
`deepmd/utils/argcheck.py`	- Adds `env_protection` argument with optional default value and updates related functions' documentation.
`doc/model/dpa2.md`	- Expands supported backends for DPA-2 descriptor to include DP in addition to PyTorch. - Updates model references and training examples.
`source/tests/common/dpmodel/test_descriptor_dpa2.py`, `source/tests/consistent/descriptor/test_dpa2.py`	- Introduces test classes and methods to validate `DescrptDPA2` functionality across different frameworks. - Adds setups for testing various scenarios and defining tolerances.

This summary condenses the changes across different files for a more concise overview.

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>.
- Generate unit testing code for this file.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai generate unit testing code for this file.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai generate interesting stats about this repository and render them as a table.
- @coderabbitai show all the console.log statements in this repository.
- @coderabbitai read src/utils.ts and generate unit testing code.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger a review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (`.coderabbit.yaml`)

You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
Please see the configuration documentation for more information.
If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

for more information, see https://pre-commit.ci

github-advanced-security

CodeQL found more than 20 potential problems in the proposed changes. Check the Files changed tab for more details.

deepmd/pt/model/descriptor/repformer_layer_old_impl.py

deepmd/pt/model/descriptor/repformers.py

deepmd/dpmodel/descriptor/repformers.py

deepmd/tf/descriptor/se_atten.py

coderabbitai

Actionable comments posted: 11

Out of diff range and nitpick comments (1)

deepmd/pt/model/descriptor/repformer_layer.py (1)

271-290: Review the initialization parameters of Atten2Map.

Consider adding default values for parameters such as has_gate and smooth in the Atten2Map class to enhance usability and avoid potential errors if these parameters are not provided.

deepmd/pt/model/descriptor/dpa2.py

deepmd/dpmodel/descriptor/dpa1.py

deepmd/dpmodel/descriptor/repformers.py

deepmd/pt/model/descriptor/repformer_layer.py

coderabbitai

Actionable comments posted: 5

Out of diff range and nitpick comments (2)

deepmd/pt/model/descriptor/repformer_layer.py (2)

32-67: Consider adding type hints for _scale and _mode in the get_residual function to improve code readability and maintainability.

494-494: Plan to refactor grrg for reuse across descriptors.

The method grrg could be reused in different descriptors. Plan a refactoring in a future PR to improve code reuse and maintainability.

deepmd/pt/model/descriptor/repformer_layer.py

coderabbitai

Actionable comments posted: 7

doc/model/dpa2.md

deepmd/dpmodel/descriptor/dpa2.py

deepmd/pt/model/descriptor/dpa2.py

coderabbitai

Actionable comments posted: 0

Out of diff range and nitpick comments (1)

deepmd/pt/model/descriptor/repformer_layer.py (1)

32-67: Consider adding type hints for all parameters in the get_residual function to enhance code readability and maintainability.

iProzd and others added 17 commits April 25, 2024 21:56

feat: Support stripped_type_embedding in PT/DP

7d82945

Update train-se-atten.md

a230198

Update graph.py

5157781

Update deepmd/utils/argcheck.py

f780d58

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Update deepmd/pt/model/descriptor/se_atten.py

3b3d25e

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Update deepmd/tf/descriptor/se_a.py

cf841f2

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Update deepmd/tf/descriptor/se_a.py

a9e24d9

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Update deepmd/tf/descriptor/se_atten.py

764cab7

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Update deepmd/tf/descriptor/se_atten.py

0b9cea1

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

Merge branch 'devel' into add_strip_dpa1

30a594a

Update docs

1e86b75

resolve conversations

f3056ee

rf dpa2 with identity implement

4e231e4

Update test_dpa2.py

b7af498

Add residual support

61d9794

rm bn support

0e4fe1c

Add numpy impl for DPA2

7a1095c

github-actions bot added Python Docs Examples labels May 7, 2024

iProzd and others added 2 commits May 8, 2024 01:36

Merge branch 'devel' into rf_dpa2_consist

0924505

Signed-off-by: Duo <50307526+iProzd@users.noreply.github.com>

[pre-commit.ci] auto fixes from pre-commit.com hooks

b19a0e1

for more information, see https://pre-commit.ci

github-advanced-security bot found potential problems May 7, 2024

View reviewed changes

update argcheck

c952798