search

dvl-tum / defocus-net

Official PyTorch implementation of "Focus on Defocus" paper.
MIT License
75 stars 5 forks source link

What is MODEL1 and MODEL2 #2

Open fuy34 opened 3 years ago

fuy34 commented 3 years ago

Thank you for sharing the code.

I am trying to run the training process. But based on the default setting, it seems we are supposed to load a model from step1, and the training model is 2.

May I ask what they are? And where can I get the access to the MODEL1?

https://github.com/dvl-tum/defocus-net/blob/418601f5f8f9cb37477e5d71923b68bcaf744edd/source/run_training.py#L11

https://github.com/dvl-tum/defocus-net/blob/418601f5f8f9cb37477e5d71923b68bcaf744edd/source/train.py#L199

zch24879 commented 3 years ago

hello，I meet the same problem。Do you know how to use it now？

ClaraRus commented 3 years ago

Hi, Have you figure it out? My intuition would be to first train MODEL 1 with TRAINING_MODE=1 and then proceed with step 2 and train with TRAINING_MODE=2 while also loading the previously trained MODEL 1. So is MODEL 1 supposed to be the DEFOCUS NET and MODEL 2 the DEPTH NET ? Any thoughts?