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.
21 lines
814 B
21 lines
814 B
# UMSN-Face-Deblurring
|
|
Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks
|
|
|
|
[Rajeev Yasarla](https://sites.google.com/view/rajeevyasarla/home), [Federico Perazzi](https://research.adobe.com/person/federico-perazzi/), [Vishal M. Patel](https://engineering.jhu.edu/ece/faculty/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.
|
|
|
|
|