TinyDet: Accurately Detecting Small Objects within
1 GFLOPs
- Python 3.5 or higher
- PyTorch 1.2 or higher
- CUDA 9.2 or higher
- GCC(G++) 4.9 or higher
a. Create a conda virtual environment and activate it (Optional but recommended).
conda create --name tinydet python=3.7
conda activate tinydetb. Install pytorch and torchvision.
conda install pytorch=1.2.0 torchvision=0.4.0 -c pytorchc. Install mmdet (other dependencies wil be installed automatically).
pip install -r requirements.txt
python setup.py build developd. Install PSRoI align.
cd mmdet_extra/ps_roi_align_ori
python setup.py build_ext --inplace
cd ../..e. Prepare dataset and checkpoint file.
Download coco dataset and checkpoint file
Folder structure:
TinyDet
├── mmdet
├── mmdet_extra
├── tools
├── scripts
├── configs
├── data
│ ├── coco
│ │ ├── annotations
│ │ ├── train2017
│ │ ├── val2017
│ │ ├── test2017
├── pth_file
│ ├── mobilenetv3_bc.pt
│ ├── mobilenetv3_d.pt
│ ├── tinydet_L.pth
│ ├── tinydet_M.pth
│ ├── tinydet_S.pth
python -m torch.distributed.launch --nproc_per_node=1 ./tools/test.py \
./configs/tinydet_M.py \
./pth_file/tinydet_M.pth \
--launcher pytorch
If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝 :
@article{chen2023tinydet,
title={TinyDet: accurately detecting small objects within 1 GFLOPs},
author={Chen, Shaoyu and Cheng, Tianheng and Fang, Jiemin and Zhang, Qian and Li, Yuan and Liu, Wenyu and Wang, Xinggang},
journal={Science China Information Sciences},
volume={66},
number={1},
pages={1--2},
year={2023},
publisher={Springer}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent