Error in running visualization validation

[GalAvineri]

I've done the following steps:

1. Built the directory tree as you instructed
2. ran python torch2pytorch_data.py annd python torch2pytorch_pretrained_weight.py with their instructed parameters
   But when i run 'python visual.py --flip --rotate 0.25 0.5 0.75 --img_glob "data/test/img/pano_aaccxxpwmsdgvj.png" --line_glob "data/test/line/pano_aaccxxpwmsdgvj.png" --output_dir assert/'
   I get the following error

Traceback (most recent call last):
File ".../LayoutNet/visual.py", line 55, in
encoder.load_state_dict(torch.load('%s_encoder.pth' % args.path_prefix))
File ".../lib/python3.5/site-packages/torch/serialization.py", line 356, in load
f = open(f, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'ckpt/pre_encoder.pth'

[sunset1995]

Sorry for the late reply.
What is the arguments you given to the torch2pytorch_pretrained_weight.py?
The script should convert to pretrained model to the path you given to the --encoder...

[GalAvineri]

I was able to solve this eventually.
The script says it is looking for 'ckpt/pre_encoder.pth' but I had 'ckpt/pre_full_encoder.pth' instead.
So I changed the prefix parameter and than it worked.

Due to the fact that following your instructions result in a 'pre_full_encoder.pth' file instead of a 'pre_encoder' file, I would suggest to edit your default behaviour of your code.
i.e edit the visual and visual_from_scratch files by changing the default value of the path-prefix parameter from 'ckpt/pre' to 'ckpt/pre_full