yolor Download - yolor Source Code Download

yolor

Python

1.0.0

Herunterladen

Yolor

Implementierung von Papier - Sie lernen nur eine Darstellung: Unified Network für mehrere Aufgaben

Einheitliches Netzwerk

Um die Ergebnisse auf die Tabelle zu bringen, verwenden Sie diese Filiale bitte.

Modell	Testgröße	AP ^-Test	AP ₅₀ ^Test	AP ₇₅ ^Test	Batch1 -Durchsatz	Batch32 Inferenz
Yolor-CSP	640	52,8%	71,2%	57,6%	106 fps	3,2 ms
Yolor-CSP-X	640	54,8%	73,1%	59,7%	87 fps	5,5 ms
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	10,7 ms
Yolor-e6	1280	57,6%	75,2%	63,0%	45 fps	17.1 ms
Yolor-D6	1280	58,2%	75,8%	63,8%	34 fps	21,8 ms

Yolov4-p5	896	51,8%	70,3%	56,6%	41 fps (alt)	- -
Yolov4-p6	1280	54,5%	72,6%	59,8%	30 fps (alt)	- -
Yolov4-p7	1536	55,5%	73,4%	60,8%	16 fps (alt)	- -

Beheben Sie den Speed Engpass auf unserem NFS, dank NCHC-, TWCC- und NARLABS -Support -Teams.

Modell	Testgröße	AP ^val	AP ₅₀ ^Val	AP ₇₅ ^Val	AP _S ^Val	Ap _m ^val	Ap _l ^val	Gewichte
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%	Gewichte
Yolor-csp *	640	50,0%	68,7%	54,3%	34,2%	55,1%	64,3%	Gewichte

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%	Gewichte
Yolor-csp-x *	640	51,5%	69,9%	56,1%	35,8%	56,8%	66,1%	Gewichte

Entwicklung...

Modell	Testgröße	AP ^-Test	AP ₅₀ ^Test	AP ₇₅ ^Test	_APs ^Test	AP _M ^-Test	AP _L ^-Test
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%

Zug von Grund auf 300 Epochen ...

Modell	Info	Testgröße	AP
Yolor-CSP	Evolution	640	48,0%
Yolor-CSP	Strategie	640	50,0%
Yolor-CSP	Strategie + Simota	640	51,1%

Yolor-CSP-X	Strategie	640	51,5%
Yolor-CSP-X	Strategie + Simota	640	53,0%

Installation

Docker -Umgebung (empfohlen)

Expandieren

 # 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

Colab -Umgebung

Expandieren

 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 ..

Bereiten Sie den Coco -Datensatz vor

Expandieren

 cd /yolor
bash scripts/get_coco.sh

Bereiten Sie vorbereitetes Gewicht vor

Expandieren

 cd /yolor
bash scripts/get_pretrain.sh

Testen

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

Sie erhalten die Ergebnisse:

 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

Ausbildung

Single GPU -Training:

 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

Mehrfacher GPU -Training:

 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

Schulungsplan in der Zeitung:

 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

Schlussfolgerung

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

Sie erhalten die Ergebnisse:

Pferde

Zitat

 @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}
}