Mise en œuvre du papier - Yolov7: un sac debies formable définit un nouveau stade de la technologie pour les détecteurs d'objets en temps réel
Mme Coco
Modèle | Taille de test | Test AP | Test AP 50 | Test AP 75 | lot 1 ip | lot 32 Temps moyen |
---|---|---|---|---|---|---|
Yolov7 | 640 | 51,4% | 69,7% | 55,9% | 161 ips | 2,8 ms |
Yolov7-x | 640 | 53,1% | 71,2% | 57,8% | 114 ips | 4.3 ms |
Yolov7-w6 | 1280 | 54,9% | 72,6% | 60,1% | 84 ips | 7,6 ms |
Yolov7-e6 | 1280 | 56,0% | 73,5% | 61,2% | 56 ips | 12.3 MS |
Yolov7-d6 | 1280 | 56,6% | 74,0% | 61,8% | 44 ips | 15.0 ms |
Yolov7-e6e | 1280 | 56,8% | 74,4% | 62,1% | 36 ips | 18,7 MS |
Environnement Docker (recommandé)
# create the docker container, you can change the share memory size if you have more.
nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3
# apt install required packages
apt update
apt install -y zip htop screen libgl1-mesa-glx
# pip install required packages
pip install seaborn thop
# go to code folder
cd /yolov7
yolov7.pt
yolov7x.pt
yolov7-w6.pt
yolov7-e6.pt
yolov7-d6.pt
yolov7-e6e.pt
python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val
Vous obtiendrez les résultats:
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.51206
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.69730
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.55521
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.38453
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.63765
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.68772
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868
Pour mesurer la précision, téléchargez coco-annotations pour pycocotools sur le ./coco/annotations/instances_val2017.json
Préparation des données
bash scripts/get_coco.sh
train2017.cache
et val2017.cache
Files et RedOndload LabelsFormation de GPU unique
# train p5 models
python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights ' ' --name yolov7 --hyp data/hyp.scratch.p5.yaml
# train p6 models
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights ' ' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
Formation GPU multiple
# train p5 models
python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights ' ' --name yolov7 --hyp data/hyp.scratch.p5.yaml
# train p6 models
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights ' ' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
yolov7_training.pt
yolov7x_training.pt
yolov7-w6_training.pt
yolov7-e6_training.pt
yolov7-d6_training.pt
yolov7-e6e_training.pt
Fintuning de GPU unique pour l'ensemble de données personnalisé
# finetune p5 models
python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights ' yolov7_training.pt ' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml
# finetune p6 models
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights ' yolov7-w6_training.pt ' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml
Voir réparamètre.ipynb
Sur la vidéo:
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4
Sur l'image:
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg
Pytorch à coreml (et inférence sur macOS / iOS)
Pytorch à onnx avec NMS (et inférence)
python export.py --weights yolov7-tiny.pt --grid --end2end --simplify
--topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
Pytorch à Tensorrt avec NMS (et inférence)
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
git clone https://github.com/Linaom1214/tensorrt-python.git
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
Pytorch pour tendre une autre manière
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
python export.py --weights yolov7-tiny.pt --grid --include-nms
git clone https://github.com/Linaom1214/tensorrt-python.git
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
# Or use trtexec to convert ONNX to TensorRT engine
/usr/src/tensorrt/bin/trtexec --onnx=yolov7-tiny.onnx --saveEngine=yolov7-tiny-nms.trt --fp16
Testé avec: Python 3.7.13, Pytorch 1.12.0 + Cu113
code
yolov7-w6-pose.pt
Voir keypoint.ipynb.
code
yolov7-mask.pt
Voir instance.ipynb.
code
yolov7-seg.pt
Yolov7 par exemple segmentation (yolor + yolov5 + yolact)
Modèle | Taille de test | Box AP | AP 50 BOX | AP 75 Box | Masque AP | Masque AP 50 | Masque AP 75 |
---|---|---|---|---|---|---|---|
Yolov7-seg | 640 | 51,4% | 69,4% | 55,8% | 41,5% | 65,5% | 43,7% |
code
yolov7-u6.pt
Yolov7 avec tal tal découplé (yolor + yolov5 + yolov6)
Modèle | Taille de test | Ap Val | AP 50 Val | AP 75 Val |
---|---|---|---|---|
Yolov7-u6 | 640 | 52,6% | 69,7% | 57,3% |
@inproceedings{wang2023yolov7,
title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2023}
}
@article{wang2023designing,
title={Designing Network Design Strategies Through Gradient Path Analysis},
author={Wang, Chien-Yao and Liao, Hong-Yuan Mark and Yeh, I-Hau},
journal={Journal of Information Science and Engineering},
year={2023}
}
Yolov7-sémantique et yolov7-panoptique & yolov7-caption
Yolov7-sémantique & yolov7-détection & yolov7-depth (avec ntut)
Yolov7-3d-détection & yolov7-lidar & yolov7-road (avec ntut)