code for generating data set ES-ImageNet with corresponding training code

Last update: Dec 25, 2022

Overview

es-imagenet-master

code for generating data set ES-ImageNet with corresponding training code

dataset generator

some codes of ODG algorithm
The variables to be modified include datapath (data storage path after transformation, which needs to be created before transformation) and root_Path (root directory of training set before transformation)

file name	function
traconvert.py	converting training set of ISLVRC 2012 into event stream using ODG
trainlabel_dir.txt	It stores the corresponding relationship between the class name and label of the original Imagenet file
trainlabel.txt	It is generated during transformation and stores the label of training set
valconvert.py	Transformation code for test set.
valorigin.txt	Original test label, need and valconvert.py Put it in the same folder
vallabel.txt	It is generated during transformation and stores the label of training set.

dataset usage

codes are in ./datasets
some traing examples are provided for ES-imagenet in ./example An example code for easily using this dataset based on Pytorch

from __future__ import print_function
import sys
sys.path.append("..")
from datasets.es_imagenet_new import ESImagenet_Dataset
import torch.nn as nn
import torch

data_path = None #TODO:modify 
train_dataset = ESImagenet_Dataset(mode='train',data_set_path=data_path)
test_dataset = ESImagenet_Dataset(mode='test',data_set_path=data_path)

train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
test_sampler  = torch.utils.data.distributed.DistributedSampler(test_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=False, num_workers=1,pin_memory=True,drop_last=True,sampler=train_sampler)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=1,pin_memory=True)

for batch_idx, (inputs, targets) in enumerate(train_loader)
  pass
  # input = [batchsize,time,channel,width,height]
  
for batch_idx, (inputs, targets) in enumerate(test_loader):
  pass
  # input = [batchsize,time,channel,width,height]

training example and benchmarks

Requirements

Python >= 3.5
Pytorch >= 1.7
CUDA >=10.0
TenosrBoradX(optional)

Train the baseline models

$ cd example

$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 example_ES_res18.py #LIAF/LIF-ResNet-18
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 example_ES_res34.py #LIAF/LIF-ResNet-34
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 compare_ES_3DCNN34.py #3DCNN-ResNet-34
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 compare_ES_3DCNN18.py #3DCNN-ResNet-18
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 compare_ES_2DCNN34.py #2DCNN-ResNet-34 
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 compare_ES_2DCNN18.py #2DCNN-ResNet-18
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 compare_CONVLSTM.py #ConvLSTM (no used in paper)
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 example_ES_res50.py #LIAF/LIF-ResNet-50 (no used in paper)

** note:** To select LIF mode, change the config files under /LIAFnet : self.actFun= torch.nn.LeakyReLU(0.2, inplace=False) #nexttest:selu to self.actFun= LIAF.LIFactFun.apply

baseline / Benchmark

Network	layer	Type Test Acc/%	# of Para	FP32+/GFLOPs	FP32x/GFLOPs
ResNet18	2D-CNN	41.030	11.68M	1.575	1.770
ResNet18	3D-CNN	38.050	28.56M	12.082	12.493
ResNet18	LIF	39.894	11.69M	12.668	0.269
ResNet18	LIAF	42.544	11.69M	12.668	14.159
ResNet34	2D-CNN	42.736	21.79M	3.211	3.611
ResNet34	3D-CNN	39.410	48.22M	20.671	21.411
ResNet34	LIF	43.424	21.80M	25.783	0.288
ResNet18+imagenet-pretrain (a)	LIF	43.74	11.69M	12.668	0.269
ResNet34	LIAF	47.466	21.80M	25.783	28.901
ResNet18+self-pretrain	LIAF	50.54	11.69M	12.668	14.159
ResNet18+imagenet-pretrain (b)	LIAF	52.25	11.69M	12.668	14.159
ResNet34+imagenet-pretrain (c)	LIAF	51.83	21.80M	25.783	28.901

Note: model (a), (b) and (c) are stored in ./pretrained_model

Download

The datasets ES-ImageNet (100GB) for this study can be download in the Tsinghua Cloud or Openl
The converted event-frame version (40GB) can be found in Tsinghua Cloud

Citation

If you use this for research, please cite. Here is an example BibTeX entry:

@misc{lin2021esimagenet,
    title={ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks},
    author={Yihan Lin and Wei Ding and Shaohua Qiang and Lei Deng and Guoqi Li},
    year={2021},
    eprint={2110.12211},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

You might also like...

Code for the paper "A Study of Face Obfuscation in ImageNet"

A Study of Face Obfuscation in ImageNet Code for the paper: A Study of Face Obfuscation in ImageNet Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng,

35 Oct 4, 2022

Code for Active Learning at The ImageNet Scale.

Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training with torch's DDP.

47 Dec 12, 2022

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2

156 Nov 28, 2022

A PyTorch re-implementation of the paper 'Exploring Simple Siamese Representation Learning'. Reproduced the 67.8% Top1 Acc on ImageNet.

Exploring simple siamese representation learning This is a PyTorch re-implementation of the SimSiam paper on ImageNet dataset. The results match that

72 Nov 9, 2022

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Res2Net The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture" Our paper is accepted by IEEE Transactions o

928 Dec 29, 2022

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

Comments

Cannot find validation dataset

Hello,

Thanks for the open-sourced code. However, I had trouble finding the validation set. I directly download the frame set in your cloud server. However, I direct uncompress the file and I didn't find the validation dataset. Also, your dataset_generator/vallabel.txt is empty. How can I find the validation index file and the dataset?

Thanks.

opened by yhhhli 4

Releases(1.1.0)

1.1.0(Oct 25, 2022)

Source code(tar.gz)
Source code(zip)
1.0.0(Mar 2, 2021)

Generating codes, dataset utils and baseline models with training codes
Source code(tar.gz)
Source code(zip)

code for generating data set ES-ImageNet with corresponding training code

Related tags

Overview

es-imagenet-master

dataset generator

dataset usage

training example and benchmarks

Requirements

Train the baseline models

baseline / Benchmark

Download

Citation

You might also like...

Code for the paper "A Study of Face Obfuscation in ImageNet"

Code for Active Learning at The ImageNet Scale.

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

A PyTorch re-implementation of the paper 'Exploring Simple Siamese Representation Learning'. Reproduced the 67.8% Top1 Acc on ImageNet.

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

transfer attack; adversarial examples; black-box attack; unrestricted Adversarial Attacks on ImageNet; CVPR2021 天池黑盒竞赛

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

Comments

Cannot find validation dataset

Releases(1.1.0)

1.1.0(Oct 25, 2022)

1.0.0(Mar 2, 2021)

Owner

Ordinarabbit

Log4j JNDI inj. vuln scanner

Open standard for machine learning interoperability

Pytorch implementation of ICASSP 2022 paper Attention Probe: Vision Transformer Distillation in the Wild

EXplainable Artificial Intelligence (XAI)

Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression.

Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

Library to enable Bayesian active learning in your research or labeling work.

A framework for joint super-resolution and image synthesis, without requiring real training data

PyTorch implementation of hand mesh reconstruction described in CMR and MobRecon.

AI pipelines for Nvidia Jetson Platform

Dense matching library based on PyTorch

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.

Eye-Blink-Counter - Python based Computer Vision project which counts how many time a person blinks

An easy-to-use app to visualise attentions of various VQA models.

Eth brownie struct encoding example

We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.

Simple converter for deploying Stable-Baselines3 model to TFLite and/or Coral

Reimplementation of the paper "Attention, Learn to Solve Routing Problems!" in jax/flax.

Hardware accelerated, batchable and differentiable optimizers in JAX.

Apply a perspective transformation to a raster image inside Inkscape (no need to use an external software such as GIMP or Krita).