fix: SpikingNeuron.zeros() now clears hidden states in-place - #424
Open
xyaz1313 wants to merge 1 commit into
Open
fix: SpikingNeuron.zeros() now clears hidden states in-place#424xyaz1313 wants to merge 1 commit into
xyaz1313 wants to merge 1 commit into
Conversation
The previous implementation used `state = torch.zeros_like(state)` which only rebinds the local variable without modifying the caller's tensor. Changed to `state.zero_()` for in-place modification, consistent with the `detach()` method directly above it. Fixes jeshraghian#423
4 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bug Fix: SpikingNeuron.zeros() now clears hidden states in-place
Root Cause
The
SpikingNeuron.zeros()static method usedstate = torch.zeros_like(state)which creates a new tensor and rebinds the local variable. The caller's original tensor remains unchanged, making the method effectively a no-op.Fix
Changed to
state.zero_()which modifies the tensor in-place, consistent with thedetach()method directly above it which already usesstate.detach_().Testing
Added
tests/test_snntorch/test_zeros.pywith two test cases:test_zeros_clears_hidden_state— verifies hidden state is cleared after running a Leaky neurontest_zeros_multiple_args— verifies multiple tensors are zeroed correctlyFixes #423