Weird results on MipNeRF360 dataset for merf with your given parameters

[thucz]

I run the following code: python main.py data/bonsai/ --workspace trial_merf_360_bonsai --enable_cam_center --eval_cnt 1 --save_cnt 1 --downscale 4 #--fast_baking

And I finally get a weird result like this:

Do you know why this happened and how to fix it?

[CultureAddiction]

I had same result at bonsai subdataset, but got better result at bicycle subdataset. Was wondering about re-doing training would occur that weired result. cuz when i train same dataset again, it gets much faster. I'll let you know if i get something