yolov7

Yolov7 resmi

Implementasi Kertas-YOLOV7: Tag-of-freebies yang dapat dilatih mengatur canggih baru untuk detektor objek real-time

Demo web

• Terintegrasi ke dalam ruang pelukan? menggunakan gradio. Coba demo web

Pertunjukan

Ms Coco

Model	Ukuran tes	Tes AP	Tes AP 50	Tes AP 75	Batch 1 fps	Batch 32 waktu rata -rata
Yolov7	640	51,4%	69,7%	55,9%	161 fps	2,8 ms
Yolov7-x	640	53,1%	71,2%	57,8%	114 fps	4.3 ms
YOLOV7-W6	1280	54,9%	72,6%	60,1%	84 fps	7,6 ms
YOLOV7-E6	1280	56,0%	73,5%	61,2%	56 fps	12,3 ms
YOLOV7-D6	1280	56,6%	74,0%	61,8%	44 fps	15.0 ms
YOLOV7-E6E	1280	56,8%	74,4%	62,1%	36 fps	18.7 ms

Instalasi

Lingkungan Docker (Direkomendasikan)

Memperluas

 # 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

Pengujian

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

Anda akan mendapatkan hasilnya:

 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

Untuk mengukur akurasi, unduh coco-annotasi untuk pycocotools ke ./coco/annotations/instances_val2017.json

Pelatihan

Persiapan data

bash scripts/get_coco.sh

• Unduh gambar dataset MS Coco (kereta api, val, tes) dan label. Jika sebelumnya Anda telah menggunakan versi YOLO yang berbeda, kami sangat menyarankan Anda menghapus file train2017.cache dan val2017.cache , dan label muatan redown

Pelatihan GPU tunggal

 # 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

Beberapa pelatihan GPU

 # 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

Transfer pembelajaran

yolov7_training.pt yolov7x_training.pt yolov7-w6_training.pt yolov7-e6_training.pt yolov7-d6_training.pt yolov7-e6e_training.pt

Finetuning GPU tunggal untuk dataset khusus

 # 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

Parameterisasi ulang

Lihat reparameterisasi.ipynb

Kesimpulan

Di video:

python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4

Pada gambar:

python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg

Ekspor

Pytorch to Coreml (dan inferensi pada macOS/iOS)

Pytorch ke Onnx dengan NMS (dan inferensi)

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 ke Tensorrt dengan NMS (dan inferensi)

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 to tensorrt cara lain

Memperluas

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

Diuji dengan: Python 3.7.13, Pytorch 1.12.0+Cu113

Estimasi pose

code yolov7-w6-pose.pt

Lihat keypoint.ipynb.

Segmentasi instan (dengan NTU)

code yolov7-mask.pt

Lihat instance.ipynb.

Segmentasi instan

code yolov7-seg.pt

YOLOV7 misalnya segmentasi (yolor + yolov5 + yolact)

Model	Ukuran tes	Kotak AP	AP 50 Box	Kotak AP 75	Topeng AP	AP 50 Mask	AP 75 Mask
YOLOV7-SEG	640	51,4%	69,4%	55,8%	41,5%	65,5%	43,7%

Kepala deteksi bebas jangkar

code yolov7-u6.pt

Yolov7 dengan tal head yang dipisahkan (yolor + yolov5 + yolov6)

Model	Ukuran tes	AP VAL	AP 50 VAL	AP 75 Val
YOLOV7-U6	640	52,6%	69,7%	57,3%

Kutipan

 @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}
}

Pengejek

YOLOV7-SEMANTY & YOLOV7-PANOPTIC & YOLOV7-CAPTION

YOLOV7-SEMANTY & YOLOV7-DETEKSI & YOLOV7-DEPTH (dengan NTUT)

YOLOV7-3D-DETEKSI & YOLOV7-LIDAR & YOLOV7-ROAD (dengan NTUT)

Ucapan Terima Kasih

Memperluas

• https://github.com/alexeyab/darknet
• https://github.com/wongkinyiu/yolor
• https://github.com/wongkinyiu/pytorch_yolov4
• https://github.com/wongkinyiu/scaledyolov4
• https://github.com/megvii berbasisetection/yolox
• https://github.com/ultralytics/yolov3
• https://github.com/ultralytics/yolov5
• https://github.com/dingxiaoh/repvgg
• https://github.com/jugghm/orepa_cvpr2022
• https://github.com/texasinstruments/edgeai-yolov5/tree/yolo-pose