|
|
|
@ -31,7 +31,7 @@ We propose a novel multi-stream architecture and training methodology that explo
|
|
|
|
|
|
|
|
|
|
|
|
## To train Segmentation Netweork
|
|
|
|
## To train Segmentation Netweork
|
|
|
|
Train Segmentation Netweork using the following command
|
|
|
|
Train Segmentation Netweork using the following command
|
|
|
|
1. training segmentation network with clean images
|
|
|
|
1. training segmentation network with clean images,
|
|
|
|
python seg_train.py --mode_clean 1 --dataroot ./facades/github/ --valDataroot ./facades/github/
|
|
|
|
python seg_train.py --mode_clean 1 --dataroot ./facades/github/ --valDataroot ./facades/github/
|
|
|
|
2. training segmentation network with blurry images
|
|
|
|
2. training segmentation network with blurry images,
|
|
|
|
python seg_train.py --mode_clean 0 --dataroot ./facades/github/ --valDataroot ./facades/github/
|
|
|
|
python seg_train.py --mode_clean 0 --dataroot ./facades/github/ --valDataroot ./facades/github/
|
|
|
|
|