YOLOV for video object detection.

Introduction

YOLOV is a high perfomance 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.

Main result

Model	size	mAP@50val	Speed 2080Ti(batch size=1) (ms)	weights
YOLOX-s	576	69.5	9.4	google
YOLOX-l	576	76.1	14.8	google
YOLOX-x	576	77.8	20.4	google
YOLOV-s	576	77.3	11.3	google
YOLOV-l	576	83.6	16.4	google
YOLOV-x	576	85.5	22.7	google
YOLOV-x + post	576	87.5	-	-

TODO

Add YOLOv7 bases

Quick Start

Installation

Install YOLOV from source.

git clone git@github.com:YuHengsss/YOLOV.git
cd YOLOV

Create conda env.

conda create -n yolov python=3.7

conda activate yolov

pip install -r requirements.txt

pip install yolox==0.3

pip3 install -v -e .

Demo

Step1. Download a pretrained weights.

Step2. Run demos. For example:

python tools/vid_demo.py -f [path to your exp files] -c [path to your weights] --path /path/to/your/video --conf 0.25 --nms 0.5 --tsize 576 --save_result 

For online mode, 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 

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.npy

Change 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.pickle

Evaluation process:

python tools/REPPM.py --repp_cfg ./tools/yolo_repp_cfg.json --predictions_file ./yolov_x.pckl --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 --fp16

Roughly testing

python tools/vid_eval.py -f exps/yolov/yolov_s.py -c weights/yolov_s.pth --tnum 500 --fp16

tnum indicates testing sequence number.

Acknowledgements

Expand

• https://github.com/Megvii-BaseDetection/YOLOX
• https://github.com/AlbertoSabater/Robust-and-efficient-post-processing-for-video-object-detection

Cite YOLOV

If YOLOV is helpful for your research, please cite the following paper: