---
license: apache-2.0
tags:
  - Super-Resolution
  - computer-vision
  - bsrgan
  - gan
---

### Model Description
[BSRGAN: Designing a Practical Degradation Model for Deep Blind Image Super-Resolution .](https://arxiv.org/abs/2103.14006)

[BSRGAN-Pip: Packaged version of the BSRGAN repository](https://github.com/kadirnar/bsrgan-pip/)

[Paper Repo: Implementation of paper - BSRGAN](https://github.com/cszn/BSRGAN)

### Installation
```
pip install bsrgan
```

### BSRGAN Usage
```python
from bsrgan import BSRGAN

model = BSRGAN(weights='kadirnar/BSRGANx2', device='cuda:0', hf_model=True)
model.save = True

pred = model.predict(img_path='data/image/test.png')
```

### BibTeX Entry and Citation Info
 ```
@inproceedings{zhang2021designing,
    title={Designing a Practical Degradation Model for Deep Blind Image Super-Resolution},
    author={Zhang, Kai and Liang, Jingyun and Van Gool, Luc and Timofte, Radu},
    booktitle={IEEE International Conference on Computer Vision},
    pages={4791--4800},
    year={2021}
}
```