output1_1.mp4
output2_1.mp4
conda create -n YOLO python=3.9
conda activate YOLO
pip install thop
pip install tqdm
pip install PyYAML
pip install opencv-python
conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch-lts
- Configure your dataset path in
main.pyfor training - Run
bash main.sh $ --trainfor training,$is number of GPUs
- Configure your dataset path in
main.pyfor testing - Run
python main.py --Validatefor validation
- Run
python main.py --inferencefor inference
| Model | mAPval 50-95 |
mAPval 50 |
params (M) |
FLOPs @640 (B) |
|---|---|---|---|---|
| YOLOv11n | 39.5 | 54.8 | 2.6 | 6.5 |
| YOLOv11s | 47.0 | 63.5 | 9.4 | 21.5 |
| YOLOv11m | 51.5 | 68.1 | 20.1 | 68.0 |
| YOLOv11l | 53.4 | 69.7 | 25.3 | 86.9 |
| YOLOv11x | 54.9 | 71.3 | 56.9 | 194.9 |
├── COCO
├── images
├── train2017
├── 1111.jpg
├── 2222.jpg
├── val2017
├── 1111.jpg
├── 2222.jpg
├── labels
├── train2017
├── 1111.txt
├── 2222.txt
├── val2017
├── 1111.txt
├── 2222.txt
⭐ Star the Repo!
If you find this project helpful, give us a star ⭐