UMSN Files

README.md

@@ -1,2 +1,20 @@
 # 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 images. blurry images for trained are generated by the code it self.
+
+