search

EdwardSmith1884 / 3D-IWGAN

A repository for the paper "Improved Adversarial Systems for 3D Object Generation and Reconstruction".
MIT License
195 stars 56 forks source link

about Voxsize #3

Closed brotherNanNan closed 6 years ago

brotherNanNan commented 7 years ago

Hi, If i use 64 64 64 size volume as input and set output_size=64, wheather "discriminator" in the models.py should be adjusted or not ? thanks！

EdwardSmith1884 commented 6 years ago

Hi, sorry for the long time to reply, I simply did not see it until now. From what I remember you do not need to change anything for it to run and produce good results. It is possible that creating a larger network would benefit the training as my architecture was optimised for a lower resolution. I'm sure this is old new, so let me know if you have any more questions, I'm sorry again this took so long.

brotherNanNan commented 6 years ago

@EdwardSmith1884 thanks for your reply~