stable-dreamfusion
stable-dreamfusion copied to clipboard
solve 'NaN or Inf found in input tensor' with disable --fp16
try disable "--cuda_ray‘’, I solve this issue with it. I guess that it happened with enable "--cuda_ray‘’ and '--fp16' together,cause CUDA raymarching calculate tensor error, but pytorch is OK.
Originally posted by @lang-dye in https://github.com/ashawkey/stable-dreamfusion/issues/331#issuecomment-1649552604
just disable '--fp16'