The Official PyTorch implementation of SC-EADNet on TGRS 2022 paper SC-EADNet: A Self-Supervised Contrastive Efficient Asymmetric Dilated Network for Hyperspectral Image Classification.
conda install pytorch torchvision cudatoolkit=10.0 -c pytorch
pip install tqdm pandas scipy numpy
Indian Pines, Salinas, PaviaU, Houston 2013 datasets are used in this repo, the dataset should be downloaded into dataset/HSIdata directory.
cd dataset
python makeTrainingSet.pypython main.py --batch_size 128 --epochs 100
python linear.py --model_path /path/to/pretrained/checkpoint/
@ARTICLE{9627700,
author={Zhu, Mingzhen and Fan, Jiayuan and Yang, Qihang and Chen, Tao},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={SC-EADNet: A Self-Supervised Contrastive Efficient Asymmetric Dilated Network for Hyperspectral Image Classification},
year={2022},
volume={60},
number={},
pages={1-17},
doi={10.1109/TGRS.2021.3131152}}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent