Skip to content
/ MWCNN Public

Pytorch implement "Multi-level Wavelet Convolutional Neural Networks"

Notifications You must be signed in to change notification settings

pminhtam/MWCNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

41 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MWCNN

Source https://github.com/lpj-github-io/MWCNNv2

Paper Multi-level Wavelet Convolutional Neural Networks

#Train

python train_eval_syn_DGF.py --noise_dir ../image/Noisy/ --gt_dir ../image/Clean/  \
--image_size 256 --batch_size 8 --save_every 1000 --loss_every 100   \
-nw 8  -ckpt checkpoints --resetart

Test

python test_mat.py  -n /mnt/vinai/SIDD/ValidationNoisyBlocksSrgb.mat  -g /mnt/vinai/SIDD/ValidationGtBlocksSrgb.mat \
  -ckpt checkpoints 

Codalab competition

Make data

unzip  /mnt/vinai/codalab/MAI2021_denoising_valid_cropped_noi.zip -d ~/codalab_val/
python utils/crop_overlap.py
python test_codalab.py -n ../codalab_val/ --save_img ../codalab_re -ckpt checkpoints
python utils/merge_overlap.py

About

Pytorch implement "Multi-level Wavelet Convolutional Neural Networks"

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages