Skip to main content

A deep learning framework for SNNs built on PyTorch.

Project description

SpikingJelly

GitHub last commit Documentation Status PyPI PyPI - Python Version repo size

English | 中文

demo

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

The documentation of SpikingJelly is written in both English and Chinese: https://spikingjelly.readthedocs.io.

Installation

Note that SpikingJelly is based on PyTorch. Please make sure that you have installed PyTorch before you install SpikingJelly.

Version notes

The odd version number is the developing version, which is updated with GitHub/OpenI repository. The even version number is the stable version and available at PyPI.

The default doc is for the latest developing version. If you are using the stable version, do not forget to switch to the doc in the corresponding version.

From the version 0.0.0.0.14, modules including clock_driven and event_driven are renamed. Please refer to the tutorial Migrate From Old Versions.

If you use an old version of SpikingJelly, you may meet some fatal bugs. Refer to Bugs History with Releases for more details.

Docs for different versions:

Install the last stable version from PyPI:

pip install spikingjelly

Install the latest developing version 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://openi.pcl.ac.cn/OpenI/spikingjelly.git
cd spikingjelly
python setup.py install

Build SNN In An Unprecedented Simple Way

SpikingJelly is user-friendly. Building SNN with SpikingJelly is as simple as building ANN in PyTorch:

nn.Sequential(
        layer.Flatten(),
        layer.Linear(28 * 28, 10, bias=False),
        neuron.LIFNode(tau=tau, surrogate_function=surrogate.ATan())
        )

This simple network with a Poisson encoder can achieve 92% accuracy on MNIST test dataset. Read refer to the tutorial for more details. You can also run this code in Python terminal for training on classifying MNIST:

python -m spikingjelly.activation_based.examples.lif_fc_mnist -tau 2.0 -T 100 -device cuda:0 -b 64 -epochs 100 -data-dir <PATH to MNIST> -amp -opt adam -lr 1e-3 -j 8

Fast And Handy ANN-SNN Conversion

SpikingJelly implements a relatively general ANN-SNN Conversion interface. Users can realize the conversion through PyTorch. What's more, users can customize the conversion mode.

class ANN(nn.Module):
    def __init__(self):
        super().__init__()
        self.network = nn.Sequential(
            nn.Conv2d(1, 32, 3, 1),
            nn.BatchNorm2d(32, eps=1e-3),
            nn.ReLU(),
            nn.AvgPool2d(2, 2),

            nn.Conv2d(32, 32, 3, 1),
            nn.BatchNorm2d(32, eps=1e-3),
            nn.ReLU(),
            nn.AvgPool2d(2, 2),

            nn.Conv2d(32, 32, 3, 1),
            nn.BatchNorm2d(32, eps=1e-3),
            nn.ReLU(),
            nn.AvgPool2d(2, 2),

            nn.Flatten(),
            nn.Linear(32, 10)
        )

    def forward(self,x):
        x = self.network(x)
        return x

This simple network with analog encoding can achieve 98.44% accuracy after converiosn on MNIST test dataset. Read the tutorial for more details. You can also run this code in Python terminal for training on classifying MNIST using converted model:

>>> import spikingjelly.activation_based.ann2snn.examples.cnn_mnist as cnn_mnist
>>> cnn_mnist.main()

CUDA-Enhanced Neuron

SpikingJelly provides two backends for multi-step neurons. You can use the user-friendly torch backend for easily codding and debugging, and use cupy backend for faster training speed.

The followed figure compares execution time of two backends of Multi-Step LIF neurons (float32):

exe_time_fb

float16 is also provided by the cupy backend and can be used in automatic mixed precision training.

To use the cupy backend, please install CuPy. Note that the cupy backend only supports GPU, while the torch backend supports both CPU and GPU.

Device Supports

  • Nvidia GPU
  • CPU

As simple as using PyTorch.

>>> net = nn.Sequential(layer.Flatten(), layer.Linear(28 * 28, 10, bias=False), neuron.LIFNode(tau=tau))
>>> net = net.to(device) # Can be CPU or CUDA devices

Neuromorphic Datasets Supports

SpikingJelly includes the following neuromorphic datasets:

Dataset Source
ASL-DVS Graph-based Object Classification for Neuromorphic Vision Sensing
CIFAR10-DVS CIFAR10-DVS: An Event-Stream Dataset for Object Classification
DVS128 Gesture A Low Power, Fully Event-Based Gesture Recognition System
ES-ImageNet ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
HARDVS HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
N-Caltech101 Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades
N-MNIST Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades
Nav Gesture Event-Based Gesture Recognition With Dynamic Background Suppression Using Smartphone Computational Capabilities
Spiking Heidelberg Digits (SHD) The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks

Users can use both the origin events data and frames data integrated by SpikingJelly:

import torch
from torch.utils.data import DataLoader
from spikingjelly.datasets import pad_sequence_collate, padded_sequence_mask
from spikingjelly.datasets.dvs128_gesture import DVS128Gesture
root_dir = 'D:/datasets/DVS128Gesture'
event_set = DVS128Gesture(root_dir, train=True, data_type='event')
event, label = event_set[0]
for k in event.keys():
    print(k, event[k])

# t [80048267 80048277 80048278 ... 85092406 85092538 85092700]
# x [49 55 55 ... 60 85 45]
# y [82 92 92 ... 96 86 90]
# p [1 0 0 ... 1 0 0]
# label 0

fixed_frames_number_set = DVS128Gesture(root_dir, train=True, data_type='frame', frames_number=20, split_by='number')
rand_index = torch.randint(low=0, high=fixed_frames_number_set.__len__(), size=[2])
for i in rand_index:
    frame, label = fixed_frames_number_set[i]
    print(f'frame[{i}].shape=[T, C, H, W]={frame.shape}')

# frame[308].shape=[T, C, H, W]=(20, 2, 128, 128)
# frame[453].shape=[T, C, H, W]=(20, 2, 128, 128)

fixed_duration_frame_set = DVS128Gesture(root_dir, data_type='frame', duration=1000000, train=True)
for i in range(5):
    x, y = fixed_duration_frame_set[i]
    print(f'x[{i}].shape=[T, C, H, W]={x.shape}')

# x[0].shape=[T, C, H, W]=(6, 2, 128, 128)
# x[1].shape=[T, C, H, W]=(6, 2, 128, 128)
# x[2].shape=[T, C, H, W]=(5, 2, 128, 128)
# x[3].shape=[T, C, H, W]=(5, 2, 128, 128)
# x[4].shape=[T, C, H, W]=(7, 2, 128, 128)

train_data_loader = DataLoader(fixed_duration_frame_set, collate_fn=pad_sequence_collate, batch_size=5)
for x, y, x_len in train_data_loader:
    print(f'x.shape=[N, T, C, H, W]={tuple(x.shape)}')
    print(f'x_len={x_len}')
    mask = padded_sequence_mask(x_len)  # mask.shape = [T, N]
    print(f'mask=\n{mask.t().int()}')
    break

# x.shape=[N, T, C, H, W]=(5, 7, 2, 128, 128)
# x_len=tensor([6, 6, 5, 5, 7])
# mask=
# tensor([[1, 1, 1, 1, 1, 1, 0],
#         [1, 1, 1, 1, 1, 1, 0],
#         [1, 1, 1, 1, 1, 0, 0],
#         [1, 1, 1, 1, 1, 0, 0],
#         [1, 1, 1, 1, 1, 1, 1]], dtype=torch.int32)

More datasets will be included in the future.

If some datasets' download link are not available for some users, the users can download from the OpenI mirror:

https://openi.pcl.ac.cn/OpenI/spikingjelly/datasets?type=0

All datasets saved in the OpenI mirror are allowable by their licence or authors' agreement.

Tutorials

SpikingJelly provides elaborate tutorials. Here are some of tutorials:

Figure Tutorial
basic_concept Basic Conception
neuron Neuron
lif_fc_mnist Single Fully Connected Layer SNN to Classify MNIST
conv_fashion_mnist Convolutional SNN to Classify FMNIST
ann2snn ANN2SNN
neuromorphic_datasets Neuromorphic Datasets Processing
classify_dvsg Classify DVS Gesture
recurrent_connection_and_stateful_synapse Recurrent Connection and Stateful Synapse
stdp_learning STDP Learning

Other tutorials that are not listed here are also available at the document https://spikingjelly.readthedocs.io.

Publications and Citation

Publications using SpikingJelly are recorded in Publications. If you use SpikingJelly in your paper, you can also add it to this table by pull request.

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 Timothée Masquelier and Tian, Yonghong and other contributors},
	year = {2020},
	howpublished = {\url{https://github.com/fangwei123456/spikingjelly}},
	note = {Accessed: YYYY-MM-DD},
}

Note: To specify the version of framework you are using, the default value YYYY-MM-DD in the note field should be replaced with the date of the last change of the framework you are using, i.e. the date of the latest commit.

Contribution

You can read the issues and get the problems to be solved and latest development plans. We welcome all users to join the discussion of development plans, solve issues, and send pull requests.

Not all API documents are written in both English and Chinese. We welcome users to complete translation (from English to Chinese, or from Chinese to English).

About

Multimedia Learning Group, Institute of Digital Media (NELVT), Peking University and Peng Cheng Laboratory are the main developers of SpikingJelly.

PKUPCL

The list of developers can be found here.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

spikingjelly-0.0.0.0.14.tar.gz (225.6 kB view hashes)

Uploaded Source

Built Distribution

spikingjelly-0.0.0.0.14-py3-none-any.whl (437.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page