Membrane Updates Metric #205
Merged
Conversation
This file contains 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
|
Looks good @ben9809, could you also cover with a test in Hoping that the memory requirements don't blow up from saving all info under same hook, it should be fine for now since it's just for SNN, but maybe in the future we could use separate hooks. Could you also add in the docstring of the metric that this metric should only be used with SNNs / also only currently works for SNNTorch? |
|
Sure @jasonlyik!! |
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Outdated suggestions cannot be applied.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.
Description
This pull request introduces a new performance metric, membrane_updates. This metric counts the number of membrane potential updates within spiking neural networks (SNNs). It tracks these updates across different network neurons.
Motivation
The membrane_updates metric aims to capture membrane potential development over multiple steps by counting stateful operations that, together with the synaptic operations, reflect the actual workload in neuromorphic computing models.
Recent research (https://arxiv.org/pdf/2306.15749v4.pdf) has highlighted the importance of considering stateful operations in the analysis of SNNs.