Alan Liao comments

Repositories
Issues
Comments

Results 2 comments of


                                            Alan Liao

Slow training with large patch_size=64, (nerfacto; poster)

Hi @sangminkim-99, I also notice the same strange training ,result from large patch size config.But I'm curious whether the same behavior appears in torch-ngp(I didn't find patch size setting in...

Slow training with large patch_size=64, (nerfacto; poster)

> Hi @lbh666, > > Upon further review, I've realized that I misunderstood the sampling process in torch-ngp. Specifically, in torch-ngp, rays are sampled from a single image, but it's...