EDVR has been merged into BasicSR. This GitHub repo is a mirror of BasicSR. Recommend to use BasicSR, and open issues, pull requests, etc in BasicSR.
Note that this version is not compatible with previous versions. If you want to use previous ones, please refer to the old_version
branch.
๐ BasicSR
GitHub | Gitee็ ไบ
English | ็ฎไฝไธญๆ
BasicSR is an open source image and video super-resolution toolbox based on PyTorch (will extend to more restoration tasks in the future).
(ESRGAN, EDVR, DNI, SFTGAN)
- Python >= 3.7 (Recommend to use Anaconda or Miniconda)
- PyTorch >= 1.3
- NVIDIA GPU + CUDA
Please run the following commands in the BasicSR root path to install BasicSR:
Make sure that your GCC version: gcc >= 5.
pip install -r requirements.txt
python setup.py develop
Note that BasicSR is only tested in Ubuntu, and may be not suitable for Windows. You may try Windows WSL with CUDA supports :-) (It is now only available for insider build with Fast ring).
Please see project boards.
- Please refer to DatasetPreparation.md for more details.
- The descriptions of currently supported datasets (
torch.utils.data.Dataset
classes) are in Datasets.md.
- Training and testing commands: Please see TrainTest.md for the basic usage.
- Options/Configs: Please refer to Config.md.
- Logging: Please refer to Logging.md.
- The descriptions of currently supported models are in Models.md.
- Pre-trained models and log examples are available in ModelZoo.md.
- We also provide training curves in wandb:
Please see DesignConvention.md for the designs and conventions of the BasicSR codebase.
The figure below shows the overall framework. More descriptions for each component:
Datasets.mdโ|โModels.mdโ|โConfig.mdโ|โLogging.md
This project is released under the Apache 2.0 license. More details are in LICENSE.
If you have any question, please email [email protected]
.