Fix utils.reset() ignoring neurons in nested containers#414
Open
IonThief wants to merge 2 commits intojeshraghian:masterfrom
Open
Fix utils.reset() ignoring neurons in nested containers#414IonThief wants to merge 2 commits intojeshraghian:masterfrom
IonThief wants to merge 2 commits intojeshraghian:masterfrom
Conversation
…_modules.values() looks only at direct children of the net, i replaced it with net.modules() to look recursively for neurons
… confirm its functionality
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description:
Currently,
utils.reset(net)usesnet._modules.values()to check for neurons.This only looks at the first layer of the network.
If neurons are inside containers like
nn.Sequentialornn.ModuleList, the function fails to detect them, and their hidden states are not reset.Fix
I updated
_layer_checkto usenet.modules()instead ofnet._modules.values().This recursively searches the entire network, ensuring that all neurons are detected and reset correctly, no matter how deep they are nested.
Verification
I added unit tests that check reset() on different architectures with spiking Leaky neurons
Checklist
Flake8andBlack