hzxie/Pix2Vox

Custom dataset training with ShapeNet-like structure.

sobikim opened this issue · 2 comments

sobikim commented

Hi.
I have some questions for training using custom dataset(ShapeNet-like structure)

  1. If not 24 images per object, would it be a problem for training?
  2. If the image size isn't 137 x 137, would it be a problem for training?
  3. If the object isn't centered in the image, will it be a problem for training?

Thank you!

hzxie commented
  1. No
  2. No
  3. No
sobikim commented

Thank you very much!