yolor 다운로드 - yolor 소스 코드 다운로드

yolor

파이썬

1.0.0

다운로드

노른자

종이 구현 - 하나의 표현 만 배웁니다 : 여러 작업을위한 통합 네트워크

통합 네트워크

테이블에서 결과를 얻으려면이 분기를 사용하십시오.

모델	테스트 크기	AP ^테스트	AP ₅₀ ^테스트	AP ₇₅ ^테스트	Batch1 처리량	Batch32 추론
Yolor-CSP	640	52.8%	71.2%	57.6%	106 fps	3.2ms
Yolor-CSP-X	640	54.8%	73.1%	59.7%	87 fps	5.5ms
Yolor-P6	1280	55.7%	73.3%	61.0%	76 fps	8.3 MS
Yolor-W6	1280	56.9%	74.4%	62.2%	66 fps	10.7ms
Yolor-e6	1280	57.6%	75.2%	63.0%	45 fps	17.1ms
Yolor-D6	1280	58.2%	75.8%	63.8%	34 fps	21.8ms

yolov4-p5	896	51.8%	70.3%	56.6%	41 FPS (오래)	-
yolov4-p6	1280	54.5%	72.6%	59.8%	30 fps (old)	-
yolov4-p7	1536	55.5%	73.4%	60.8%	16 FPS (구)	-

NCHC, TWCC 및 NARLABS 지원 팀 덕분에 NFS의 속도 병목 현상을 수정하십시오.

모델	테스트 크기	ap ^val	AP ₅₀ ^발	AP ₇₅ ^발	ap _s ^val	ap _m ^val	ap _l ^val	무게
Yolov4-CSP	640	49.1%	67.7%	53.8%	32.1%	54.4%	63.2%	-
Yolor-CSP	640	49.2%	67.6%	53.7%	32.9%	54.4%	63.0%	무게
Yolor-CSP *	640	50.0%	68.7%	54.3%	34.2%	55.1%	64.3%	무게

Yolov4-CSP-X	640	50.9%	69.3%	55.4%	35.3%	55.8%	64.8%	-
Yolor-CSP-X	640	51.1%	69.6%	55.7%	35.7%	56.0%	65.2%	무게
Yolor-CSP-X *	640	51.5%	69.9%	56.1%	35.8%	56.8%	66.1%	무게

개발 ...

모델	테스트 크기	AP ^테스트	AP ₅₀ ^테스트	AP ₇₅ ^테스트	AP _S ^테스트	AP _M ^테스트	AP _L ^테스트
Yolor-CSP	640	51.1%	69.6%	55.7%	31.7%	55.3%	64.7%
Yolor-CSP-X	640	53.0%	71.4%	57.9%	33.7%	57.1%	66.8%

300 개의 에포크를 위해 처음부터 훈련 ...

모델	정보	테스트 크기	ap
Yolor-CSP	진화	640	48.0%
Yolor-CSP	전략	640	50.0%
Yolor-CSP	전략 + 시모타	640	51.1%

Yolor-CSP-X	전략	640	51.5%
Yolor-CSP-X	전략 + 시모타	640	53.0%

설치

도커 환경 (권장)

확장하다

 # create the docker container, you can change the share memory size if you have more.
nvidia-docker run --name yolor -it -v your_coco_path/:/coco/ -v your_code_path/:/yolor --shm-size=64g nvcr.io/nvidia/pytorch:20.11-py3

# apt install required packages
apt update
apt install -y zip htop screen libgl1-mesa-glx

# pip install required packages
pip install seaborn thop

# install mish-cuda if you want to use mish activation
# https://github.com/thomasbrandon/mish-cuda
# https://github.com/JunnYu/mish-cuda
cd /
git clone https://github.com/JunnYu/mish-cuda
cd mish-cuda
python setup.py build install

# install pytorch_wavelets if you want to use dwt down-sampling module
# https://github.com/fbcotter/pytorch_wavelets
cd /
git clone https://github.com/fbcotter/pytorch_wavelets
cd pytorch_wavelets
pip install .

# go to code folder
cd /yolor

콜랩 환경

확장하다

 git clone https://github.com/WongKinYiu/yolor
cd yolor

# pip install required packages
pip install -qr requirements.txt

# install mish-cuda if you want to use mish activation
# https://github.com/thomasbrandon/mish-cuda
# https://github.com/JunnYu/mish-cuda
git clone https://github.com/JunnYu/mish-cuda
cd mish-cuda
python setup.py build install
cd ..

# install pytorch_wavelets if you want to use dwt down-sampling module
# https://github.com/fbcotter/pytorch_wavelets
git clone https://github.com/fbcotter/pytorch_wavelets
cd pytorch_wavelets
pip install .
cd ..

코코 데이터 세트를 준비하십시오

확장하다

 cd /yolor
bash scripts/get_coco.sh

사전에 사전 무게를 준비하십시오

확장하다

 cd /yolor
bash scripts/get_pretrain.sh

테스트

yolor_p6.pt

 python test.py --data data/coco.yaml --img 1280 --batch 32 --conf 0.001 --iou 0.65 --device 0 --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --name yolor_p6_val

결과를 얻을 수 있습니다.

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.52510
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.70718
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.57520
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.37058
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.56878
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66102
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.39181
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.65229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.71441
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.57755
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.75337
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.84013

훈련

단일 GPU 교육 :

 python train.py --batch-size 8 --img 1280 1280 --data coco.yaml --cfg cfg/yolor_p6.cfg --weights '' --device 0 --name yolor_p6 --hyp hyp.scratch.1280.yaml --epochs 300

다중 GPU 교육 :

 python -m torch.distributed.launch --nproc_per_node 2 --master_port 9527 train.py --batch-size 16 --img 1280 1280 --data coco.yaml --cfg cfg/yolor_p6.cfg --weights '' --device 0,1 --sync-bn --name yolor_p6 --hyp hyp.scratch.1280.yaml --epochs 300

논문의 훈련 일정 :

 python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train.py --batch-size 64 --img 1280 1280 --data data/coco.yaml --cfg cfg/yolor_p6.cfg --weights '' --device 0,1,2,3,4,5,6,7 --sync-bn --name yolor_p6 --hyp hyp.scratch.1280.yaml --epochs 300
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 tune.py --batch-size 64 --img 1280 1280 --data data/coco.yaml --cfg cfg/yolor_p6.cfg --weights 'runs/train/yolor_p6/weights/last_298.pt' --device 0,1,2,3,4,5,6,7 --sync-bn --name yolor_p6-tune --hyp hyp.finetune.1280.yaml --epochs 450
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train.py --batch-size 64 --img 1280 1280 --data data/coco.yaml --cfg cfg/yolor_p6.cfg --weights 'runs/train/yolor_p6-tune/weights/epoch_424.pt' --device 0,1,2,3,4,5,6,7 --sync-bn --name yolor_p6-fine --hyp hyp.finetune.1280.yaml --epochs 450

추론

yolor_p6.pt

 python detect.py --source inference/images/horses.jpg --cfg cfg/yolor_p6.cfg --weights yolor_p6.pt --conf 0.25 --img-size 1280 --device 0

결과를 얻을 수 있습니다.

소환

 @article{wang2023you,
  title={You Only Learn One Representation: Unified Network for Multiple Tasks},
  author={Wang, Chien-Yao and Yeh, I-Hau and Liao, Hong-Yuan Mark},
  journal={Journal of Information Science and Engineering},
  year={2023}
}