main
rajeevyasarla 6 years ago
parent ddc8f7dd8a
commit faed054baf

@ -26,7 +26,6 @@ We propose a novel multi-stream architecture and training methodology that explo
- 25000 kernels with size ranging from 13 to 29 are generated and saved as ".mat" file
2. Clean face images from Helen and CelebA are aligned and used as input to train UMSN
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.
- input should be clean image. blurry images for training are generated by the code it self.

Loading…
Cancel
Save