fanwuyang
/
UMSN-Face-Deblurring
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
4 Commits
1 Branch
0 Tags
388 MiB
 
 
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'a4bea87d97'
${ noResults }
Go to file
rajeevyasarla a4bea87d97
UMSN Files 		6 years ago
datasets UMSN Files 6 years ago
facades/github UMSN Files 6 years ago
models UMSN Files 6 years ago
myutils UMSN Files 6 years ago
pretrained_models UMSN Files 6 years ago
transforms UMSN Files 6 years ago
README.md UMSN Files 6 years ago
kernel.mat UMSN Files 6 years ago
misc.py UMSN Files 6 years ago
test_face_deblur.py UMSN Files 6 years ago
train_face_deblur.py UMSN Files 6 years ago

README.md

UMSN-Face-Deblurring

Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

Rajeev Yasarla, Federico Perazzi, Vishal M. Patel

Prerequisites:

  1. Linux
  2. Python 2 or 3
  3. CPU or NVIDIA GPU + CUDA CuDNN (CUDA 8.0)

To test UMRL:

python2.7 test_face_deblur.py --dataroot ./facades/github/ --valDataroot <path_to_test_data> --netG ./pretrained_models/Deblur_epoch_Best.pth

To train UMRL:

python2.7 train_face_deblur.py --dataroot <path_to_train_data> --valDataroot ./facades/github/ --exp ./face_deblur --batchSize 10

  • input should be clean image. blurry images for trained are generated by the code it self.