search

MoyGcc / vid2avatar

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)
https://moygcc.github.io/vid2avatar/
Other
1.2k stars 102 forks source link

batch_size: 2 error #55

Closed shuochen365 closed 9 months ago

shuochen365 commented 9 months ago

Hello! what is the problem and how can i solve it ? Thank you ! when I set batch_size: 2 in the train stage, I get this error: RuntimeError: stack expects each tensor to be equal size, but got [34] at entry 0 and [40] at entry 1

MoyGcc commented 9 months ago

Hi, we currently don't support training with batch_size > 1 (one training image per iteration). There should be some NeRF works/codes that use multiple images for one training iteration and you could modify the code based on these resources.

shuochen365 commented 9 months ago

OK, thank you