amnesiac555

About suface_normal Prediction

5

Hello, JiaxiongQ! when i read your code, i found that after you predict the surface normal vector, you perform some transformation operations on it. the code is: outputN = torch.zeros_like(normals2)...

test.py for val_selection_cropped

1

hello when i try to reproduce the infrence result, i use the KITTI val_selection_cropped data, but the pred make me confused, when i print the pred.max(), i find all are...

During the training process, the loss has been rising

8

 i use the mobilenet and fpn_inception, training data is Gopro, config is as follows: anyone has trained successfully？  

thanks for you sharing, i have read the bicycleGAN paper, but i am confused that whether lager Batchsize will have a bad influence or not . Because you implementation also...