YOLOV is a high performance video object detector. Please refer to our paper on Arxiv for more details.
This repo is an implementation of PyTorch version YOLOV based on YOLOX.
| Model | size | mAP@50val |
Speed 2080Ti(batch size=1) (ms) |
weights |
|---|---|---|---|---|
| YOLOX-s | 576 | 69.5 | 9.4 | |
| YOLOX-l | 576 | 76.1 | 14.8 | |
| YOLOX-x | 576 | 77.8 | 20.4 | |
| YOLOV-s | 576 | 77.3 | 11.3 | |
| YOLOV-l | 576 | 83.6 | 16.4 | |
| YOLOV-x | 576 | 85.5 | 22.7 | |
| YOLOV-x + post | 576 | 87.5 | - | - |
Finish Swin-Transformer based experiments.
Installation
Install YOLOV from source.
git clone [email protected]:YuHengsss/YOLOV.git
cd YOLOVCreate conda env.
conda create -n yolov python=3.7
conda activate yolov
pip install -r requirements.txt
pip3 install -v -e .Demo
Step1. Download a pretrained weights.
Step2. Run yolov demos. For example:
python tools/vid_demo.py -f [path to your yolov exp files] -c [path to your yolov weights] --path /path/to/your/video --conf 0.25 --nms 0.5 --tsize 576 --save_result For online mode, exampled with yolov_l, you can run:
python tools/yolov_demo_online.py -f ./exp/yolov/yolov_l_online.py -c [path to your weights] --path /path/to/your/video --conf 0.25 --nms 0.5 --tsize 576 --save_result For yolox models, please use python tools/demo.py for inferencing.
Reproduce our results on VID
Step1. Download datasets and weights:
Download ILSVRC2015 DET and ILSVRC2015 VID dataset from IMAGENET and organise them as follows:
path to your datasets/ILSVRC2015/
path to your datasets/ILSVRC/Download our COCO-style annotations for training and video sequences. Then, put them in these two directories:
YOLOV/annotations/vid_train_coco.json
YOLOV/yolox/data/dataset/train_seq.npyChange the data_dir in exp files to [path to your datasets] and Download our weights.
Step2. Generate predictions and convert them to IMDB style for evaluation.
python tools/val_to_imdb.py -f exps/yolov/yolov_x.py -c path to your weights/yolov_x.pth --fp16 --output_dir ./yolov_x.pklEvaluation process:
python tools/REPPM.py --repp_cfg ./tools/yolo_repp_cfg.json --predictions_file ./yolov_x.pkl --evaluate --annotations_filename ./annotations/annotations_val_ILSVRC.txt --path_dataset [path to your dataset] --store_imdb --store_coco (--post)(--post) indicates involving post-processing method. Then you will get:
{'mAP_total': 0.8758871720817065, 'mAP_slow': 0.9059275666099181, 'mAP_medium': 0.8691557352372217, 'mAP_fast': 0.7459511040452989}Training example
python tools/vid_train.py -f exps/yolov/yolov_s.py -c weights/yoloxs_vid.pth --fp16Roughly testing
python tools/vid_eval.py -f exps/yolov/yolov_s.py -c weights/yolov_s.pth --tnum 500 --fp16tnum indicates testing sequence number.
Details
Training base detector
The train_coco.json is a COCO format annotation file. When trainig the base detector on your own dataset, try to convert the annotation to COCO format.
Training YOLOV
The train_seq.npy and val_seq.npy files are numpy arrays of lists. They can be loaded using the following command:
numpy.load('./yolox/data/datasets/train_seq.npy',allow_pickle=True)Each list contains the paths to all images in a video. The specific annotations(xml annotation in VID dataset) are loaded via these image paths, refer to https://github.com/YuHengsss/YOLOV/blob/f5a57ddea2f3660875d6d75fc5fa2ddbb95028a7/yolox/data/datasets/vid.py#L125 for more details.
Expand
If YOLOV is helpful for your research, please cite the following paper:
@article{shi2022yolov,
title={YOLOV: Making Still Image Object Detectors Great at Video Object Detection},
author={Shi, Yuheng and Wang, Naiyan and Guo, Xiaojie},
journal={arXiv preprint arXiv:2208.09686},
year={2022}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent