- TestSet(Left) and Transfer Leraning on Iter 95000 (Right)
![](https://private-user-images.githubusercontent.com/55197580/284763849-5d835d9a-e21f-4f6c-a9dc-d57986c44aa4.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.MaRSw1ITXtLcPdZGip6qUuF2RpWnsYUhAgjP0nwsVMk)
![](https://private-user-images.githubusercontent.com/55197580/284763943-23fa410a-2ddf-4af1-9ab9-464a38e0ed78.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.z6S8txyiA6zV0S3TsMgZKkUcFGayhjOpngLS__rr_KI)
![](https://private-user-images.githubusercontent.com/55197580/284764012-3f13fc7f-cdb9-49f6-b207-7e905335cb98.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.NnBrCyqG_KrcyIZe9yYulA77VcdZHsvVndY4ybsxePk)
![](https://private-user-images.githubusercontent.com/55197580/284764049-457cbe0b-2934-4c8c-a2b1-bc5319b9b830.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.k3ko-pgnhiVg_pUBN3Z6McMnZGA7yMJFLB9jSCDUukE)
![](https://private-user-images.githubusercontent.com/55197580/284764103-7fb7b526-5212-4e9b-8598-0575b90cdb9a.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.9MdVg0DnSR_gjeVLI-Qy0ghVUv3OA1qkFZFuAhkZSTU)
![](https://private-user-images.githubusercontent.com/55197580/284764137-8e7846fa-a837-4f32-8429-fdea145643a0.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.QmvwGJchOs_Vhd53oKa_ft5_pGxyvxchPDV-mP22YFU)
![](https://private-user-images.githubusercontent.com/55197580/284764182-742c705a-d0c4-489b-9565-c0968bcbfd75.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.F6ISX32KyjiutaRbIz9oJFQw_0VJPxIPDLDXlmRp0mE)
https://github.com/DYDevelop/SwinIR.git
pip install -r requirement.txt
You should modify the json file from options first, for example,
setting "gpu_ids": [0,1,2,3] if 4 GPUs are used,
setting "dataroot_H": "trainsets/trainH" if path of the high quality dataset is trainsets/trainH
.
- Training with
DataParallel
- SwinIR
python main_train_psnr.py --opt options/swinir/train_swinir_denoising_color.json
- Inference on
DataParallel
- SwinIR
python main_test_swinir.py --task color_dn --noise 0 --model_path denoising/swinir_denoising_color_15/models/100000_G.pth --folder_gt testsets/custom_dataset
@inproceedings{liang2021swinir,
title={SwinIR: Image Restoration Using Swin Transformer},
author={Liang, Jingyun and Cao, Jiezhang and Sun, Guolei and Zhang, Kai and Van Gool, Luc and Timofte, Radu},
booktitle={IEEE International Conference on Computer Vision Workshops},
pages={1833--1844},
year={2021}
}
Our Swin Image Reconstruction implementation is heavily based on Kai Zhang's KAIR.