UMSN

README.md

@@ -29,4 +29,9 @@ We propose a novel multi-stream architecture and training methodology that explo
 3. python 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 training are generated by the code it self.
 
-
+## To train Segmentation Netweork
+Train Segmentation Netweork using the following command
+1. training segmentation network with clean images
+python seg_train.py --mode_clean 1 --dataroot ./facades/github/ --valDataroot ./facades/github/
+2. training segmentation network with blurry images
+python seg_train.py --mode_clean 0 --dataroot ./facades/github/ --valDataroot ./facades/github/