MIAYOLO: Multiexpert and Intraclass Aggregation-Assisted Suburban Building Detection in Unmanned Aerial Vehicle Imagery

⭐ This code has been completely released ⭐

Requirements

pip install -r requirements.txt

Train

1. Prepare training data

• Download data for our experiment from baiduyun (code: zd59). And the path of dataset is like that

MIAYOLO
├── dataset
│   ├── UCB
│   │   ├── train
│   │   │   ├── images
│   │   │   ├── labels
│   │   ├── val
│   │   │   ├── images
│   │   │   ├── labels

2. Begin to train

python train.py --cfg models/MIAYOLO.yaml

Test

1. Pretrained Checkpoints

You can use our pretrained checkpoints for test process. Download pre-trained model and put it in here (code: jqan).

2. Begin to test

python detect.py --weights weights/MIAYOLO.pt 

Acknowledgements

This code is built on YOLOv5 (PyTorch). We thank the authors for sharing the codes.