Anand Bhattad

Did anyone successfully get segmented results?

@ZweeLe How many iterations did you train your network for? Also, did you make any changes to hyperparameters?

@chen1005 To achieve this do I need to retrain my network with above changes in train.py? Or my previous trained weights would be adequate to get these results? Also, can...

@chen1005 Thanks for your reply. I have pretrained weights till 200k epochs which I had trained by randomly initializing pyramid networks. People in other issues of this repo have also...

@chen1005 Oh, I had used someone else pretrained weights and trained it from there. I am not sure if they are broken as well. If they are, I will start...

@nywang16 I meant the training data that you uploaded on gdrive. There are few missing .dat files. https://drive.google.com/file/d/1Z8gt4HdPujBNFABYrthhau9VZW10WWYe/view?usp=sharing

Thanks a lot, Nilesh! That was fast :) Best, Anand

Hi Nilesh, I am trying to get a template mesh for another object. Simply running mesh deform doesn't seem to generate templates like the ones you shared. I realized reading...

Hi @maxorange I do get broken results with surface models. How do you generate solid voxels? Is binvox doing that for you? Please let me know if my understanding is...

Hi! Do you have pretrained models for StyleGAN2 on LSUN bedrooms?