STBP is a way to train SNN with datasets by Backward propagation.

Last update: Dec 09, 2022

Overview

Train SNN with STBP in fp32 and low bit(quantize)

Spiking neural network (SNN), compared with depth neural network (DNN), has faster processing speed, lower energy consumption and more biological interpretability, which is expected to approach Strong AI.

STBP is a way to train SNN with datasets by Backward propagation.Using this Repositories allows you to train SNNS with STBP and quantize SNNS with QAT to deploy to neuromorphological chips like Loihi and Tianjic.

Usage

Download via GitHub:

git clone https://github.com/ZLkanyo009/STBP-train-and-compression.git

example to define SNN_layers like ANN_layers

Convert layer to spatiotemporal layer:

conv = nn.Conv2d(...)
conv_s = tdLayer(conv)

Define LIF activation function just like Relu:

spike = LIFSpike()

In the forward function, replace the activation function of each layer with LIF activation function, and replace the calls such as conv() with conv_ s(), then SNN_layers definition is completed.Finally, we use Frequency Coding to decode SNN's output like out = torch.sum(x, dim=2) / steps

def forward(self, x):
    x = self.conv1_s(x)
    x = self.spike(x)
    x = self.pool1_s(x)
    x = self.spike(x)
    x = x.view(x.shape[0], -1, x.shape[4])
    x = self.fc1_s(x)
    x = self.spike(x)
    out = torch.sum(x, dim=2) / steps
    return out

If BN layer is required:

bn = nn.BatchNorm2d(...)
bn = tdBatchNorm(...)
conv_s = tdLayer(conv, bn)

Training Fp32 Model

# Start training fp32 model with: 
# model_name can be ResNet18, CifarNet, ...
python main.py ResNet18 --dataset CIFAR10

# training with DDP:
python -m torch.distributed.launch main.py ResNet18 --local_rank 0 --dataset CIFAR10 --p DDP

# You can manually config the training with: 
python main.py ResNet18 --resume --lr 0.01

Training Quantize Model

# Start training quantize model with: 
# model_name can be ResNet18, CifarNet, ...
python main.py ResNet18 --dataset CIFAR10 -q

# training with DDP:
python -m torch.distributed.launch main.py ResNet18 --local_rank 0 --dataset CIFAR10 -q --p DDP

# You can manually config the training with: 
python main.py ResNet18 -q --resume --bit 4 --lr 0.01

Accuracy

Model	Acc.(fp32)	Acc.(8 bit quantize)
MNISTNet	97.96%	97.57%
ResNet18	84.40%	84.23%

STBP is a way to train SNN with datasets by Backward propagation.

Related tags

Overview

Train SNN with STBP in fp32 and low bit(quantize)

Usage

Download via GitHub:

example to define SNN_layers like ANN_layers

Training Fp32 Model

Training Quantize Model

Accuracy

About STBP

Owner

Ling Zhang

Source code for "Progressive Transformers for End-to-End Sign Language Production" (ECCV 2020)

VGGVox models for Speaker Identification and Verification trained on the VoxCeleb (1 & 2) datasets

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Unofficial pytorch implementation of the paper "Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution"

Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.

Deeplearning project at The Technological University of Denmark (DTU) about Neural ODEs for finding dynamics in ordinary differential equations and real world time series data

MediaPipeのPythonパッケージのサンプルです。2020/12/11時点でPython実装のある4機能(Hands、Pose、Face Mesh、Holistic)について用意しています。

Meli Data Challenge 2021 - First Place Solution

OneShot Learning-based hotword detection.

learning and feeling SLAM together with hands-on-experiments

This is the official github repository of the Met dataset

Using Self-Supervised Pretext Tasks for Active Learning - Official Pytorch Implementation

A cross-document event and entity coreference resolution system, trained and evaluated on the ECB+ corpus.

An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

TensorFlow port of PyTorch Image Models (timm) - image models with pretrained weights.

Analysis of Antarctica sequencing samples contaminated with SARS-CoV-2

IJCAI2020 & IJCV 2020 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

Prevent `CUDA error: out of memory` in just 1 line of code.

Monify: an Expense tracker Program implemented in a Graphical User Interface that allows users to keep track of their expenses

An alarm clock coded in Python 3 with Tkinter