Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

English | 简体中文

paper

Datasets:
- PASCAL VOC 2007+12
- WiderPerson
- SODA10M (for autonomous vehicles)
- DOTA1.0
(We only provide the train/val/test.txt file we used so that you can reproduce our results. The images & labels can be found on the official websites of these datasets.)

An example of comparison on remote sensing images

scaled-yolov4

slim neck scaled-yolov4

Training the custom datasets

1. For GSConv-yolov5

(Updated July 14th)

git clone https://github.com/AlanLi1997/slim-neck-by-gsconv.git
cd slim-neck-by-gsconv/gsconv-yolov5
pip install requirements.txt
python train.py --cfg models/sm-yolov5s.yaml

2. For GSConv-scaled_yolov4

(Updated Aug 17th)

git clone https://github.com/AlanLi1997/slim-neck-by-gsconv.git
cd slim-neck-by-gsconv
pip install requirements.txt
cd gsconv-scaled-yolov4
python train.py --cfg models/sm-yolov4-p5.yaml

Pretrained Checkpoints

MS COCO

Model	size ^(pixels)	mAP^val 0.5:0.95	mAP^val 0.5	FPS ^{T4 b1}	FPS ^{T4 b32}	params ^(M)	FLOPs ^{@640 (G)}
yolov5n(ultralytics)	640	28.0	45.7	--	--	1.9	4.5
GSyolov5n	640	28.4(+0.4)	47.0(+1.3)	147	207	1.8	4.0
Model	size ^(pixels)	mAP^val 0.5:0.95	mAP^val 0.5	FPS ^{A40 b1}	FPS ^{A40 b32}	params ^(M)	FLOPs ^{@640 (G)}
yolov5s	640	35.7	54.3	109	297	7.2	16.4
GSyolov5s	640	36.0(+0.3)	54.2	95	312(+15)	7.0	14.5

Testing the slim-neck detectors

1. For GSConv-yolov5

cd gsconv-yolov5
python val.py --data yourdata.yaml --weights sm-yolov5s.pt --task test

2. For GSConv-scaled-yolov4

cd gsconv-scaled-yolov4
python val.py --data yourdata.yaml --weights sm-yolov4-p5.pt --task test

References

Citation

@article{li2022slim,
title={Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles},
author={Li, Hulin and Li, Jun and Wei, Hanbing and Liu, Zheng and Zhan, Zhenfei and Ren, Qiliang},
journal={arXiv preprint arXiv:2206.02424},
year={2022}
}

littlewhite152 / slim-neck-by-gsconv Goto Github PK

slim-neck-by-gsconv's Introduction

Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

Datasets:
- PASCAL VOC 2007+12
- WiderPerson
- SODA10M (for autonomous vehicles)
- DOTA1.0
(We only provide the train/val/test.txt file we used so that you can reproduce our results. The images & labels can be found on the official websites of these datasets.)

An example of comparison on remote sensing images

Training the custom datasets

1. For GSConv-yolov5

2. For GSConv-scaled_yolov4

Pretrained Checkpoints

Testing the slim-neck detectors

1. For GSConv-yolov5

2. For GSConv-scaled-yolov4

References

Citation

slim-neck-by-gsconv's People

Contributors

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

littlewhite152 / slim-neck-by-gsconv Goto Github PK

slim-neck-by-gsconv's Introduction

Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

Datasets: - PASCAL VOC 2007+12 - WiderPerson - SODA10M (for autonomous vehicles) - DOTA1.0 (We only provide the train/val/test.txt file we used so that you can reproduce our results. The images & labels can be found on the official websites of these datasets.)

An example of comparison on remote sensing images

Training the custom datasets

1. For GSConv-yolov5

2. For GSConv-scaled_yolov4

Pretrained Checkpoints

Testing the slim-neck detectors

1. For GSConv-yolov5

2. For GSConv-scaled-yolov4

References

Citation

slim-neck-by-gsconv's People

Contributors

Recommend Projects

Recommend Topics

Recommend Org

Datasets:
- PASCAL VOC 2007+12
- WiderPerson
- SODA10M (for autonomous vehicles)
- DOTA1.0
(We only provide the train/val/test.txt file we used so that you can reproduce our results. The images & labels can be found on the official websites of these datasets.)