欢迎来到惊蜇(SpikingJelly)的文档¶
SpikingJelly 是一个基于 PyTorch ,使用脉冲神经网络(Spiking Neural Network, SNN)进行深度学习的框架。
安装¶
注意,SpikingJelly是基于PyTorch的,需要确保环境中已经安装了PyTorch,才能安装spikingjelly。
从 PyPI 安装:
pip install spikingjelly
PyPI的安装包不包含CUDA扩展。如果想使用CUDA扩展,请 从源代码安装:
通过 GitHub:
git clone https://github.com/fangwei123456/spikingjelly.git
cd spikingjelly
python setup.py install
通过 OpenI :
git clone https://git.openi.org.cn/OpenI/spikingjelly.git
cd spikingjelly
python setup.py install
引用¶
如果您在自己的工作中用到了惊蜇(SpikingJelly),您可以按照下列格式进行引用:
@misc{SpikingJelly,
title = {SpikingJelly},
author = {Fang, Wei and Chen, Yanqi and Ding, Jianhao and Chen, Ding and Yu, Zhaofei and Zhou, Huihui and Tian, Yonghong and other contributors},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/fangwei123456/spikingjelly}},
}
Welcome to SpikingJelly’s documentation¶
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
Installation¶
Note that SpikingJelly is based on PyTorch. Please make sure that you have installed PyTorch before you install SpikingJelly.
Install from PyPI:
pip install spikingjelly
Note that the CUDA extensions are not included in the PyPI package. If you want to use the CUDA extensions, please install from the source codes:
From GitHub:
git clone https://github.com/fangwei123456/spikingjelly.git
cd spikingjelly
python setup.py install
From OpenI:
git clone https://git.openi.org.cn/OpenI/spikingjelly.git
cd spikingjelly
python setup.py install
- Clock driven: Neurons
- Clock driven: Encoder
- Clock driven: Use single-layer fully connected SNN to identify MNIST
- Clock driven: Use convolutional SNN to identify Fashion-MNIST
- spikingjelly.clock_driven.ann2snn
- Reinforcement Learning: Deep Q Learning
- Reinforcement Learning: Advantage Actor Critic (A2C)
- Reinforcement Learning: Proximal Policy Optimization (PPO)
- Classifying Names with a Character-level Spiking LSTM
- Propagation Pattern
- Accelerate with CUDA-Enhanced Neuron and Layer-by-Layer Propagation
- Neuromorphic Datasets Processing
Indices and tables¶
Citation¶
If you use SpikingJelly in your work, please cite it as follows:
@misc{SpikingJelly,
title = {SpikingJelly},
author = {Fang, Wei and Chen, Yanqi and Ding, Jianhao and Chen, Ding and Yu, Zhaofei and Zhou, Huihui and Tian, Yonghong and other contributors},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/fangwei123456/spikingjelly}},
}
About¶
Multimedia Learning Group, Institute of Digital Media (NELVT), Peking University and Peng Cheng Laboratory are the main developers of SpikingJelly.
The list of developers can be found at contributors.