open-neuromorphic/snnmetrics

Metrics for spiking neural networks based on torchmetrics

19
/ 100
Experimental

This package helps neuromorphic engineers and researchers quantify the computational efficiency of spiking neural networks (SNNs). It takes the activation data from individual SNN layers and calculates metrics like the number of synaptic operations (SynOps). This allows you to evaluate and compare different SNN architectures based on their operational cost.

No commits in the last 6 months.

Use this if you are developing or analyzing spiking neural networks and need to measure their computational workload in terms of synaptic operations.

Not ideal if you are working with traditional artificial neural networks (ANNs) or require metrics unrelated to the unique characteristics of spiking neurons.

neuromorphic-computing spiking-neural-networks SNN-evaluation computational-efficiency brain-inspired-AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

Last pushed

Mar 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/open-neuromorphic/snnmetrics"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.