spikingjelly

A PyTorch-based framework for developing and training Spiking Neural Networks (SNNs).

Python2.0K313Updated 4h ago

Quick Overview

What is this?

SpikingJelly provides a user-friendly Python environment for researchers and developers working with SNNs. It supports advanced features like ANN2SNN conversion, event-based datasets, and acceleration backends such as CuPy and Triton, enabling efficient large-scale SNN model development.

What problem does it solve?

A PyTorch-based framework for developing and training Spiking Neural Networks (SNNs).

Who should use it?

Machine learning engineers and researchers focused on Spiking Neural Networks and event-driven AI.

Setup difficulty:Medium

Pros

Beginner-friendly API
ANN2SNN conversion
CuPy and Triton acceleration backends

Cons

Requires PyTorch installation
Steeper learning curve for SNN concepts compared to traditional ANNs

Scores

Trust Score

65

Star reputation (15%)66

Star velocity 7d (15%)0

Commit recency (15%)100

Fork ratio (10%)51

Issue ratio (10%)12

Contributor signal (10%)63

README quality (5%)100

License (5%)100

Homepage/demo (5%)100

Docs URL (5%)0

Topic count (5%)100

Maintenance

67

Commit frequency95

Issue management50

Documentation85

Popularity

51

Stars40

Forks30

Growth trend10

Star History

Not enough data yet. Star history will appear after a few days of tracking.

Snapshot Versions

Version	Commit	Size	Downloads	Date
latestLatest	HEAD	40.3 MB	0	14h ago

Alternatives

tensorflow

91

An Open Source Machine Learning Framework for Everyone

Featured

C++195.8K47775.2K3h ago

stable-diffusion-webui

AUTOMATIC1111

69

Stable Diffusion web UI

Python163.8K44930.4K3mo ago

transformers

huggingface

90

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Featured

Python161.8K63033.6K3h ago