Ramazan
Ramazan
> How did you split the FF++ to train&valid, test? Face Clustering which in your paper? I followed the FF++ [official split](https://github.com/ondyari/FaceForensics/tree/master/dataset/splits), the result on C40 is four points lower...
> @fatbao55 Please check this PR, [graphdeco-inria/diff-gaussian-rasterization#10](https://github.com/graphdeco-inria/diff-gaussian-rasterization/pull/10) For my case, adding "-Xcompiler -fno-gnu-unique" option in submodules/diff-gaussian-rasterization/setup.py: line 29 resolves the illegal memory access error in training. > > ``` >...