Combine-and-Conquer Detection Framework

We release the code of our CC-Det-v2 proposed in our paper.

Requirements

We recommend you to use Anaconda to create a conda environment:

conda create -n ccdet python=3.6

Then, activate the environment:

conda activate ccdet

Requirements:

pip install -r requirements.txt

PyTorch >= 1.9.1 and Torchvision >= 0.10.1

Network

Backbone: ResNet
Neck: Dilated Encoder
Feature Aggregation: PaFPN
Head: DecoupledHead

Experiments

COCO

Download COCO.

cd <FreeYOLOv2_HOME>
cd dataset/scripts/
sh COCO2017.sh

Check COCO

cd <FreeYOLOv2_HOME>
python dataset/coco.py

Main results on COCO:

Model	Size	FPS^2080ti	Param	FLOPs	AP^val	AP^test	weight
CCDet-R18	640	132	21.9 M	29.5 B	37.7	37.7	github
CCDet-R50	640	68	36.3 M	50.1 B	41.8	41.8	github
CCDet-R101	640	45	56.3 M	81.2 B	42.6	42.6	github

Train

Single GPU

sh train.sh

You can change the configurations of train.sh, according to your own situation.

Multi GPUs

sh train_ddp.sh

You can change the configurations of train_ddp.sh, according to your own situation.

Test

python test.py -d coco --cuda -v ccdet_r18 -size 640 --weight path/to/weight --show
                  voc            ccdet_r50
                  ...            ...

Eval

python eval.py -d coco-val --cuda -v ccdet_r18 -size 640 --weight path/to/weight
                  voc                ccdet_r50
                  ...                ...

Demo

I have provide some images in data/demo/images/, so you can run following command to run a demo:

python demo.py --cuda \
               --mode image \
               --path_to_img data/demo/images/ \
               -v ccdet_r18 \
               -size 640 \
               --weight path/to/weight

If you want run a demo of streaming video detection, you need to set --mode to video, and give the path to video --path_to_vid。

python demo.py --cuda \
               --mode video \
               --path_to_img data/demo/videos/video_file \
               -v ccdet_r18 \
               -size 640 \
               --weight path/to/weight

If you want run video detection with your camera, you need to set --mode to camera。

python demo.py --cuda \
               --mode camera \
               -v ccdet_r18 \
               -size 640 \
               --weight path/to/weight

References

If you are using our code, please consider citing our paper.

@article{yang2022novel,
  title={A novel fast combine-and-conquer object detector based on only one-level feature map},
  author={Yang, Jianhua and Wang, Ke and Li, Ruifeng and Qin, Zhonghao and Perner, Petra},
  journal={Computer Vision and Image Understanding},
  volume={224},
  pages={103561},
  year={2022},
  publisher={Elsevier}
}

yjh0410/Combine-and-Conquer-Detection