Matthew Tancik

It's possible that the pose optimization is unstable when working with such long focal lengths. Maybe try disabling it to see if it helps, `--pipeline.datamanager.camera-optimizer.mode off`

Can you try increasing the "near" plane, `--pipeline.model.near-plane` it defaults to 0.05, you might need larger, you can also try increasing the far plane, `--pipeline.model.far-plane`. Other parameters to try, `--optimizers.proposal-networks.optimizer.lr...

It needs the data files for creating some metadata used to generate the model. This isn't ideal, at some point we hope to store that data in the model file...

I'm not a Windows user, but I have heard that people have had trouble with VS 2022 and TinyCudaNN. I think folks have had better luck with VS 2019.

> Not sure if expected, but I got a warning about UNet, and to run `scripts\trace_stablediff.py` -- eventually got that to work and then saw `Loading traced UNet.` -- but...

I get the following warning when running other models like nerfacto (not observed in main) ``` ns-train nerfacto --data data/nerfstudio/egg /home/tancik/miniconda3/envs/nerfstudio/lib/python3.8/site-packages/tyro/_fields.py:794: UserWarning: Mutable type is used as a default value...

It is not normal for the GPU to not work. I'm actually surprised that it is working at all given that TinyCudaNN requires a GPU. Can you post the full...

Can you first check that you, are not running `tyro==0.3.34`, this was throwing the same error #987 Next, does the transforms.json file exist in that directory?

Add `nerfstudio-data` to the end of your command. The mipnerf model defaults to using the blender dataparser.

When using `instant-ngp` for the first time, it will compile CUDA drivers that will take a few minutes. Try waiting a bit to see if that solves it. If not,...