GitHub | Gitee码云
English | 简体中文

BasicSR is an open source image and video super-resolution toolbox based on PyTorch (may 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:

python setup.py develop
pip install -r requirements.txt

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 Datasets.md for more details.

Please see TrainTest.md for the basic usage, i.e., training and testing.

Results and pre-trained models are available in ModelZoo.md.

Please see DesignConvention.md for the designs and convetions of the BasicSR codebase.

This project is released under the Apache 2.0 license. More details are in LICENSE.

If you have any question, please email [email protected].

_{^{BasicSR-private}}