feat: add nframe=3 adsorption softmax training#5746
Draft
anyangml wants to merge 2 commits into
Draft
Conversation
for more information, see https://pre-commit.ci
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds a softmax-weighted averaging behavior intended for an adsorption workflow that uses exactly 3 frames/samples per batch, and adjusts HDF5 opening behavior.
Changes:
- Open HDF5 files with
locking=Falsein the cached H5 loader. - Add softmax-weighted averaging across the batch in PyTorch
PropertyLossand enforcenbz == 3. - Add softmax-weighted averaging across frames in
DeepProperty.evaland enforcenframes == 3(with a debugprint).
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
deepmd/utils/path.py |
Changes HDF5 file open behavior by disabling file locking. |
deepmd/pt/loss/property.py |
Introduces batch-level softmax averaging and hard-codes a batch size of 3 in the property loss. |
deepmd/infer/deep_property.py |
Introduces frame-level softmax averaging and hard-codes nframes == 3 (plus debug output). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
331
to
+334
| # this method has cache to avoid duplicated | ||
| # loading from different DPH5Path | ||
| # However the file will be never closed? | ||
| return h5py.File(path, mode) | ||
| return h5py.File(path, mode, locking=False) |
Comment on lines
+103
to
+122
| # ---- Softmax-weighted averaging over the batch added by YL---- | ||
| # model_pred[var_name]: (nbz, task_dim) | ||
| # 1) get a scalar score per sample (mean over task_dim) | ||
| # (If you want to favor smaller values, use `score_per_sample = -model_pred[var_name].mean(dim=1)`.) | ||
| score_per_sample = model_pred[var_name].mean(dim=1) # (nbz,) | ||
| weights = F.softmax(score_per_sample, dim=0) # (nbz,) | ||
| # 2) weighted average vector (1, task_dim) | ||
| avg_vec = (weights.unsqueeze(1) * model_pred[var_name]).sum(dim=0, keepdim=True) | ||
| # 3) replace all predictions with the averaged vector (broadcast over batch) | ||
| model_pred[var_name] = avg_vec.expand_as(model_pred[var_name]) | ||
| # ---------------------------------------------------- | ||
|
|
||
| nbz = model_pred[var_name].shape[0] | ||
| # =======Raise error when nbz!=3======= | ||
| if nbz != 3: | ||
| raise RuntimeError( | ||
| f"[PropertyLoss] Expected batch size nbz == 3 for softmax-avg, got nbz == {nbz}. " | ||
| "Ensure your DataLoader yields triples (batch_size=3, drop_last=True)." | ||
| ) | ||
|
|
Comment on lines
+144
to
+153
| # --- softmax-weighted averaging over frames (minimal) --- | ||
| print(f"Nframes == {nframes}") | ||
| if nframes != 3: | ||
| raise RuntimeError(f"Expected nframes == 3, got {nframes}") | ||
| scores = property.mean(axis=1) # (3,) | ||
| # If you want to favor *smaller* values (e.g., energies), use: scores = -scores | ||
| w = np.exp(scores - scores.max()) | ||
| w /= w.sum() # (3,) | ||
| avg = (w[:, None] * property).sum(axis=0, keepdims=True) # (1, D) | ||
| property[:] = np.repeat(avg, nframes, axis=0) # (3, D) |
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #5746 +/- ##
==========================================
- Coverage 81.95% 76.02% -5.94%
==========================================
Files 714 1015 +301
Lines 73441 139629 +66188
Branches 3616 5764 +2148
==========================================
+ Hits 60187 106146 +45959
- Misses 12091 31831 +19740
- Partials 1163 1652 +489 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.