[Bug Fix] Restrict the running_var parameter of BatchNorm to be greater than 0. #301
Conversation
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
|
Thanks for your contribution! |
lixinqi
approved these changes
Oct 13, 2025
Dayuxiaoshui
pushed a commit
to Dayuxiaoshui/GraphNet
that referenced
this pull request
Oct 25, 2025
- Remove temporary workaround code from PR PaddlePaddle#301 - Add min_val constraint handling in replay_tensor function - Update convert_meta_classes_to_tensors to read min_val from weight_meta - Batch update 801 weight_meta.py files to add min_val=0 for all running_var parameters - Fix resolves nan issue in max_diff and mean_diff for 150 samples with batch_norm Verification: max_diff and mean_diff changed from nan to 0.0, all allclose checks pass
Dayuxiaoshui
added a commit
to Dayuxiaoshui/GraphNet
that referenced
this pull request
Oct 25, 2025
- Remove temporary workaround code from PR PaddlePaddle#301 - Add min_val constraint handling in replay_tensor function - Update convert_meta_classes_to_tensors to read min_val from weight_meta - Batch update 801 weight_meta.py files to add min_val=0 for all running_var parameters - Fix resolves nan issue in max_diff and mean_diff for 150 samples with batch_norm Verification: max_diff and mean_diff changed from nan to 0.0, all allclose checks pass
Dayuxiaoshui
added a commit
to Dayuxiaoshui/GraphNet
that referenced
this pull request
Oct 27, 2025
- Remove temporary workaround code from PR PaddlePaddle#301 - Add min_val constraint handling in replay_tensor function - Update convert_meta_classes_to_tensors to read min_val from weight_meta - Batch update 801 weight_meta.py files to add min_val=0 for all running_var parameters - Fix resolves nan issue in max_diff and mean_diff for 150 samples with batch_norm Verification: max_diff and mean_diff changed from nan to 0.0, all allclose checks pass
Xreki
pushed a commit
that referenced
this pull request
Oct 29, 2025
…an (#315) - Remove temporary workaround code from PR #301 - Add min_val constraint handling in replay_tensor function - Update convert_meta_classes_to_tensors to read min_val from weight_meta - Batch update 801 weight_meta.py files to add min_val=0 for all running_var parameters - Fix resolves nan issue in max_diff and mean_diff for 150 samples with batch_norm Verification: max_diff and mean_diff changed from nan to 0.0, all allclose checks pass
JewelRoam
pushed a commit
to JewelRoam/GraphNet
that referenced
this pull request
Oct 29, 2025
…er than 0. (PaddlePaddle#301) * Restrict the running_var parameter of BatchNorm to be greater than 0. * Add TODO.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
PR Category
Bug Fix
Description