Repeatable results

[briantcantwell]

Hello!

I'm noticing that if I run nerfacto on the same dataset over and over again, I get pretty significant differences with each run. Should that be expected?

[tancik]

Some variance is expected to some extent due to the random nature of the optimization. "Sigificant" differences is a bit surprising and should be looked into a bit more. I wonder if a random seed isn't being set somewhere...

[briantcantwell]

Right, I didn't expect it to match exactly, but the differences are more extreme than I would have thought. Thanks for looking into it!