by Hanlin Wu, Libao Zhang, and Jie Ma, details are in paper.
This repository is build for the proposed SG-FBGAN, which contains full training and testing code.
git clone https://github.com/BNUAI/SG-FBGAN.git
- tensorflow==1.14.0
- tensorlayer==1.11.0
- numpy
- easydict
- opencv-python
- tqdm
- wget
pip install -r requirements.txt
- Download the pre-trained SG-FBGAN models.
- BI degradation
- DN degradation
- Unzip the the downloaded file, and put the pre-trained model on path :
experiments/exp_name
- Do testing:
Note: The GeoEye-1 dataset will be downloaded automatically. If the download fails, please download it manually from here, and then put the downloaded file on path :
python predict.py --opt exp_name
data/sr_geo.npz
.
python train.py --opt config/va_fbgan_x3_BI.json
-
change the
datapath
andsavepath
indata_loader/make_npz.py
, and then make the.npz
file:python data_loader/make_npz.py
-
change the
data_path
inconfig/your_own_config_file.json
. -
Do training:
python train.py --opt config/your_own_config_file.json
H. Wu, L. Zhang and J. Ma, "Remote Sensing Image Super-Resolution via Saliency-Guided Feedback GANs," in IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2020.3042515.
- Hanlin Wu ([email protected])