YOLO nano is from this paper.
Since I'm too busy at the end of the semester, I will continue working on this project after my exams.
- Finish a draft version of implementation
- Add README
- Add checkpoint support
- Add COCO dataset support (Code still needs cleaning. I'm working on it.)
- Add multi scale and horizontal flip transforms
- Reconstruct the code of visualizer
- Add val and test
- Add VOC support
- Test accuracy
git clone https://github.com/liux0614/yolo_nano
pip3 install -r requirements.txt
root/ results/ datasets/ coco/ images/ train/ val/ annotation/ instances_train2017.json instances_val2017.json
To use COCO dataset loader, pycocotools should be installed via the following command.
pip install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"
To train on COCO dataset:
python3 main.py --dataset_path datasets/coco/images --annotation_path datasets/coco/annotation/instances_train2017.json
--dataset coco --lr 0.0001 --conf_thres 0.8 --nms_thres 0.5