The value of `self.cascade` becomes 0 when `bound <= 0.5`, causing errors
ShenhanQian opened this issue · comments
A remedy could be modifying
Line 73 in b6e0804
to
self.cascade = max(1 + math.ceil(math.log2(bound)), 1)
A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.
ShenhanQian opened this issue · comments
A remedy could be modifying
Line 73 in b6e0804
self.cascade = max(1 + math.ceil(math.log2(bound)), 1)