compute output stat for atomic model #3642
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
|
|
||
| def setUp(self): | ||
| TestCaseSingleFrameWithNlist.setUp(self) | ||
| nf, nloc, nnei = self.nlist.shape |
Check notice
Code scanning / CodeQL
Unused local variable Note test
|
|
||
| def setUp(self): | ||
| TestCaseSingleFrameWithNlist.setUp(self) | ||
| nf, nloc, nnei = self.nlist.shape |
Check notice
Code scanning / CodeQL
Unused local variable Note test
|
|
||
| def setUp(self): | ||
| TestCaseSingleFrameWithNlist.setUp(self) | ||
| nf, nloc, nnei = self.nlist.shape |
Check notice
Code scanning / CodeQL
Unused local variable Note test
| atom_exclude_types: List[int] = [], | ||
| pair_exclude_types: List[Tuple[int, int]] = [], | ||
| ): | ||
| super().__init__() | ||
| self.type_map = type_map |
Check warning
Code scanning / CodeQL
Overwriting attribute in super-class or sub-class Warning
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## devel #3642 +/- ##
==========================================
+ Coverage 81.72% 81.80% +0.07%
==========================================
Files 503 503
Lines 46007 46445 +438
Branches 2891 2952 +61
==========================================
+ Hits 37601 37993 +392
- Misses 7528 7559 +31
- Partials 878 893 +15 ☔ View full report in Codecov by Sentry. |
Co-authored-by: Duo <[email protected]> Signed-off-by: Han Wang <[email protected]>
for more information, see https://pre-commit.ci
github-merge-queue
bot
removed this pull request from the merge queue due to failed status checks
| atom_exclude_types: List[int] = [], | ||
| pair_exclude_types: List[Tuple[int, int]] = [], | ||
| rcond: Optional[float] = None, | ||
| preset_out_bias: Optional[Dict[str, torch.Tensor]] = None, |
There was a problem hiding this comment.
line 74 is different from line 60
There was a problem hiding this comment.
This PR:
compute_or_load_output_statfor the base atomic model. the method computes both bias and std.compute_or_load_output_statmethod for computing output stat.apply_out_stat, the derived class may override the method to define how the statistics is applied to an atomic model's output. @anyangml may need.out_statsupport statistics of output tensor of any shape.@iProzd please check if i took it correctly in ce7ec1f
To be done: