This project provides the code and results for 'Transmission Line Detection Through Auxiliary Feature Registration with Knowledge Distillation'
Python 3.7+, Pytorch 1.5.0+, Cuda 10.2+, TensorboardX 2.1, opencv-python If anything goes wrong with the environment, please check requirements.txt for details.
数据集： 数据集链接
modify the train_root val_root save_path test_path in config.py according to your own data path.
Train the AFRNet:
python train.py
modify the test_path path in test.py according to your own data path.
Test the AFRNet:
python test.py
Implemented through evaluate.py, specific predictions can be obtained by setting the path inside.
百度网盘链接：Saliency Maps and Weights
百度网盘链接: Pretraining Models
Please drop me an email for any problems or discussion: https://wujiezhou.github.io/ (wujiezhou@163.com) or wysss1998@163.com