Pytorch Implementation of Spiking Neural Networks Calibration, ICML 2021

Last update: Dec 27, 2022

Related tags

Overview

SNN_Calibration

Pytorch Implementation of Spiking Neural Networks Calibration, ICML 2021

Feature Comparison of SNN calibration:

Features	SNN Direct Training	ANN-SNN Conversion	SNN Calibration
Accuract (T<100)	High	Low	High
Scalability to ImageNet	Tiny	Large	Large
Training Speed	Slow	Fast	Fast
# Required Data	Full-set (1.2M For ImageNet)	~1000	~1000
Inference Speed	Fast	Slow	Fast

Requirements

Pytorch 1.8

For ImageNet experiments, please be sure that you can initialize distributed environments

For CIFAR experiments, one GPU would suffice.

Pre-training ANN on CIFAR10&100

Train an ANN model with main_train.py

python CIFAR/main_train.py --dataset CIFAR10 --arch VGG16 --dpath PATH/TO/DATA --usebn

Pre-trained results:

Dataset	Model	Random Seed	Accuracy
CIFAR10	VGG16	1000	95.76
CIFAR10	ResNet-20	1000	95.68
CIFAR100	VGG16	1000	77.98
CIFAR100	ResNet-20	1000	76.52

SNN Calibration on CIFAR10&100

Calibrate an SNN with main_calibration.py.

python CIFAR/main_calibration.py --dataset CIFAR10 --arch VGG16 --T 16 --usebn --calib advanced --dpath PATH/TO/DATA

--T is the time step, --calib is the calibration method, please use none, light, advanced for experiments.

The calibration will run for 5 times, and return the mean accuracy as well as the standard deviation.

Example results:

Architecture	Datset	T	Random Seed	Calibration	Mean Acc	Std.
VGG16	CIFAR10	16	1000	None	64.52	4.12
VGG16	CIFAR10	16	1000	Light	93.30	0.08
VGG16	CIFAR10	16	1000	Advanced	93.65	0.25
ResNet-20	CIFAR10	16	1000	None	67.88	3.63
ResNet-20	CIFAR10	16	1000	Light	93.89	0.20
ResNet-20	CIFAR10	16	1000	Advanced	94.33	0.12
VGG16	CIFAR100	16	1000	None	2.69	0.76
VGG16	CIFAR100	16	1000	Light	65.26	0.99
VGG16	CIFAR100	16	1000	Advanced	70.91	0.65
ResNet-20	CIFAR100	16	1000	None	39.27	2.85
ResNet-20	CIFAR100	16	1000	Light	73.89	0.15
ResNet-20	CIFAR100	16	1000	Advanced	74.48	0.16

Pre-training ANN on ImageNet

To be updaed

Pytorch Implementation of Spiking Neural Networks Calibration, ICML 2021

Related tags

Overview

SNN_Calibration

Requirements

Pre-training ANN on CIFAR10&100

SNN Calibration on CIFAR10&100

Pre-training ANN on ImageNet

Owner

Yuhang Li

A customisable game where you have to quickly click on black tiles in order of appearance while avoiding clicking on white squares.

Official repository for the NeurIPS 2021 paper Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided curriculum Learning Approach

This is 2nd term discrete maths project done by UCU students that uses backtracking to solve various problems.

ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

A PyTorch implementation of "Graph Classification Using Structural Attention" (KDD 2018).

Interactive web apps created using geemap and streamlit

[ICLR'21] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

Bi-level feature alignment for versatile image translation and manipulation (Under submission of TPAMI)

The official repository for Deep Image Matting with Flexible Guidance Input

Chainer Implementation of Semantic Segmentation using Adversarial Networks

In the AI for TSP competition we try to solve optimization problems using machine learning.

Official PyTorch implementation of the paper: DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

Unsupervised Image-to-Image Translation

Codes for the ICCV'21 paper "FREE: Feature Refinement for Generalized Zero-Shot Learning"

JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation

CRF-RNN for Semantic Image Segmentation - PyTorch version

Streamlit tool to explore coco datasets

Learnable Boundary Guided Adversarial Training (ICCV2021)

PyTorch implementation of the paper Dynamic Token Normalization Improves Vision Transfromers.