This is a code modified to work with EN675 by taking the code from https://github.com/WongKinYiu/yolov7.
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
- python3.8
# create the docker container, you can change the share memory size if you have more.
pip install -r requirement.txt
# install torch, cuda
...-
resolution : 512x896 (HxW)
-
dataset : COCO 2017 VAL
-
GPU mAP
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.369
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.548
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.399
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.213
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.410
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.491
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.307
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.524
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.580
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.411
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.628
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.723
- NPU mAP - this test on board
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.291
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.482
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.313
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.139
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.321
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.398
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.239
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.365
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.381
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.196
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.419
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.501
To measure accuracy, download COCO-annotations for Pycocotools to the ./coco/annotations/instances_val2017.json
Data preparation
bash scripts/get_coco.sh- Download MS COCO dataset images (train, val, test) and labels. If you have previously used a different version of YOLO, we strongly recommend that you delete
train2017.cacheandval2017.cachefiles, and redownload labels
Single GPU training
CUDA_VISIBLE_DEVICES=0 python train.py --batch-size 32 --data data/example.yaml --img-size-train 640 640 --img-size-test 640 640 --cfg cfg/yolov7-tiny-silu-en675-rfb.yaml --weights yolov7-tiny.pt --hyp data/hyp.scratch.tiny.yaml
Multiple GPU training
python -m torch.distributed.launch --nproc_per_node 3 train.py --workers 8 --device 0,1,2 --sync-bn --batch-size 120 --data data/example.yaml --img-size-train 640 640 --img-size-test 640 640 --cfg cfg/yolov7-tiny-silu-en675-rfb.yaml --weights yolov7-tiny.pt --hyp data/hyp.scratch.tiny.yaml
On video:
python detect.py --weights {pt file} --conf 0.25 --img-size 640 640 --source {video file path}On image:
python detect.py --weights {pt file} --conf 0.25 --img-size 640 640 --source {imgae file path}
CUDA_VISIBLE_DEVICES=0 python test.py --data data/example.yaml --img 640 640 --batch-size 32 --conf 0.001 --iou 0.65 --weights {pt file} - img-size {height, width}
python export.py --weight {pt file} --img-size 640 640 --simplify --batch-size 1@article{wang2022yolov7,
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},
journal={arXiv preprint arXiv:2207.02696},
year={2022}
}
Expand
- 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-BaseDetection/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