Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
filterbank
8d3af73854
|
4 months ago | |
|---|---|---|
| codes | 4 months ago | |
| data | 4 months ago | |
| datasets | 4 months ago | |
| results | 4 months ago | |
| tb_logger | 4 months ago | |
| README.md | 4 months ago | |
README.md
Contributors
author:Fengping Dou
The code was written primarily by Fengping Dou alone.
We have updated the code, the main model is unchanged, as before.
Dependencies
- Python >= 3.6 (Recommend to use Anaconda)
- PyTorch >= 1.5.0
- NVIDIA GPU + CUDA
- Python packages:
pip install numpy opencv-python lmdb - [option] Python packages:
pip install tensorboardX, for visualizing curves.
Codes
- Our codes version based on BasicSR.
How to test a single branch
cd codes
- Run testing for ClassSR.
cd codes
python test_ClassSR.py -opt options/test/test_ClassSR_CARN.yml
- The output results will be sorted in
./results.
How to train a single branch
cd codes/data_scripts
python data_augmentation.py
python generate_mod_LR_bic.py
python extract_subimages_train.py
python divide_subimages_train.py
5. Run training for a single branch (default branch1, the simplest branch).
cd codes
python train.py -opt options/train/train_CARN.yml
6. The experiments will be sorted in `./experiments`.
## How to train ClassSR
- Generate training data (the all data(1.59M) in paper).
cd codes/data_scripts
python data_augmentation.py
python generate_mod_LR_bic.py
python extract_subimages_train.py
- Run training for ClassSR.
cd codes
python train_ClassSR.py -opt options/train/train_ClassSR_CARN.yml
- The experiments will be sorted in
./experiments.
Contact
Email: lxu@nao.cas.cn
This is the codec of the proposed multiple branch super-resolution. The dataset can be accessed via http://www.deepsolar.space/news_view.php?id=70
Python MATLAB
Contributors (1)