(manually) update zero gradients after updating the weights #3397
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Outdated suggestions cannot be applied.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.
Fixes #ISSUE_NUMBER : PyTorch Docathon H1 2025 #153952
file location: https://github.com/pytorch/tutorials/blob/main/beginner_source/examples_autograd/polynomial_autograd.py
Description
Previous version:
a.grad, b.grad, c.grad, d.grad = None, None, None, None
Proposed version:
Deletion on that code snippet or at least put a comment on that code snippet. It eventually runs successfully with verified numerical outputs.
Checklist