About training a genelized model

[frspring]

In the readme I found the line
set batch_size to 1 when you are trining a genelized model, you can enlarge it when fine-tuning.
and since the batch_size is already 1 in the outer loop which loads the image, hould I set the ray size to 1 as well?

And why it's necessary to set batch size to 1?

[apchenstu]

I remember our plan-sweep warping don't support batch size>1, but it's not difficult to extend it to support large batch size, you can take a look at that function "build_volume_costvar_img"

[frspring]

Well I'm working on it. Thanks!