README.md

Datasets

-Train datasets: GoPro

-Test datasets: GoPro, RealBlur_R, RealBlur_J

-Val dataset: To accelerate the training speed, we selected the first image from the GoPro test set as the validation set.

• The above dataset path is as follows

Deblurring/Datasets
 ├──train
          ├──input
          └──target
 ├──val
          ├──input
          └──gt
 └──test
     ├──GoPro
          ├──input
          └──target
     ├──RealBlur_J
          ├──input
          └──target
     └──RealBlur_R
          ├──input
          └──target

Training

First, modify the path where the project is located in the second line of the /basicsr/train.py file.

1. To train C2F-DFT in the coarse training pipeline, modify the comments on lines 129-134 and 195-237 in the /basicsr/models/image_restoration_model.py file, then run

   cd C2F-DFT-main
   python -m torch.distributed.launch --nproc_per_node=2 --master_port=4321 basicsr/train.py -opt Deblurring/Options/Deblurring_C2F-DFT_Coarse.yml  --launcher pytorch
   

2. To train C2F-DFT in the fine training pipeline, modify the comments on lines 137-145 and 240-286 in the /basicsr/models/image_restoration_model.py file, then run

   cd C2F-DFT-main
   python -m torch.distributed.launch --nproc_per_node=2 --master_port=4321 basicsr/train.py -opt Deblurring/Options/Deblurring_C2F-DFT_Fine.yml  --launcher pytorch
   

Testing

1. Download the pre-trained model and place it in ./pretrained_models/

2. Testing

   Modify the path where the project is located in the second line of the Deblurring/test.py file

   Testing on GoPro dataset, run

   cd Deblurring
   python test.py
   

   Testing on RealBlur dataset, run

   cd Deblurring
   python test_real.py
   

3. Calculating PSNR/SSIM scores

   Calculate GoPro dataset, run

   python calculate_psnr_ssim.py
   

   Calculate RealBlur dataset, run

   python evaluate_realblur.py