style loss becomes nan

[BPAWD]

Hi, I am training StyleRF on my own dataset. The training on the original TensoRF and the feature stages looks good and the rendered novel views of these two stages are good. But when I train the style stage, the style loss becomes nan after about 1K iters. Any solution on it?

[ruanchunqing7]

Hello,

I have not found the implementation code corresponding to table 1, may I ask if you have found it? Thank you very much!

[BPAWD]

Nope, I didn't find it.