fix float precision problem of se_atten in line 217 (#3961) #3978
Conversation
…ap input, check rang os switch function
for more information, see https://pre-commit.ci
WalkthroughWalkthroughThe recent changes to the Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant wrap.py
participant se_atten.py
User->>wrap.py: Call wrap_head with ener_fact
wrap.py->>wrap.py: Calculate atom_ener_shift
wrap.py->>wrap.py: Process atom_ener_shift elements
User->>wrap.py: Call wrap_lut
wrap.py->>wrap.py: Reshape arrays
wrap.py->>wrap.py: Perform matrix multiplication
User->>se_atten.py: Assign two_embd_value
se_atten.py->>se_atten.py: Apply GLOBAL_NP_FLOAT_PRECISION
Recent review detailsConfiguration used: CodeRabbit UI Files selected for processing (1)
Files skipped from review as they are similar to previous changes (1)
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? TipsChatThere are 3 ways to chat with CodeRabbit:
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)
Additionally, you can add CodeRabbit Configuration File (
|
for more information, see https://pre-commit.ci
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## devel #3978 +/- ##
==========================================
+ Coverage 82.82% 82.83% +0.01%
==========================================
Files 520 522 +2
Lines 50869 50884 +15
Branches 3020 3015 -5
==========================================
+ Hits 42134 42152 +18
+ Misses 7798 7796 -2
+ Partials 937 936 -1 ☔ View full report in Codecov by Sentry. |
|
Could you rebase the branch - there are too many unrelated commits |
for more information, see https://pre-commit.ci
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Outside diff range, codebase verification and nitpick comments (2)
deepmd/tf/nvnmd/entrypoints/wrap.py (2)
166-166: Add a docstring for the new parameter.The new parameter
ener_factis added, but its purpose is not documented.ener_fact factor for atom_ener + ener_fact factor for adjusting atom_ener precision
229-229: Remove debug print statement.The debug print statement should be removed or replaced with proper logging.
- print(atom_ener_shift) + log.debug(f"atom_ener_shift: {atom_ener_shift}")
… (deepmodeling#3978) fix float precision problem of se_atten in line 217. fix the bug: the different energy between qnn and lammps <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Improved energy calculation methods for more accurate results in the `wrap` module. - Introduced new parameters for enhanced configurability in energy-related computations. - **Improvements** - Enhanced handling and processing of energy shift arrays for better performance and accuracy. - Updated array manipulation and calculation methods for various wrapping functionalities. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: LiuGroupHNU <liujie123@HNU> Co-authored-by: MoPinghui <mopinghui1020@gmail.com> Co-authored-by: Han Wang <92130845+wanghan-iapcm@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pinghui Mo <pinghui_mo@outlook.com>
fix float precision problem of se_atten in line 217.
fix the bug: the different energy between qnn and lammps
Summary by CodeRabbit
New Features
wrapmodule.Improvements