Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
shelterX
876c0d5239
|
3 months ago | |
|---|---|---|
| dataset | 10 months ago | |
| model | 3 months ago | |
| pytorch-gradual-warmup-lr | 10 months ago | |
| utils | 3 months ago | |
| MPRNet.py | 3 months ago | |
| README.md | 10 months ago | |
| SSIM.py | 10 months ago | |
| common.py | 8 months ago | |
| config.py | 10 months ago | |
| data_RGB.py | 10 months ago | |
| dataset_RGB.py | 10 months ago | |
| evaluate_PSNR_SSIM.m | 10 months ago | |
| local_arch.py | 6 months ago | |
| losses.py | 10 months ago | |
| restormer_arch.py | 6 months ago | |
| test.py | 5 months ago | |
| train.py | 6 months ago | |
| training.yml | 3 months ago | |
README.md
Training
-
Download the Datasets
-
Train the model with default arguments by running
python train.py
Evaluation
-
Download the model and place it in
./pretrained_models/ -
Download test datasets (Test100, Rain100H, Rain100L, Test1200, Test2800) from here and place them in
./Datasets/Synthetic_Rain_Datasets/test/ -
Run
python test.py
To reproduce PSNR/SSIM scores of the paper, run
evaluate_PSNR_SSIM.m
