Gina Wu
Gina Wu
Hi thanks for submitting the issue! I believe that error does not mean the dataset no longer exists (if you copy paste the google drive link it seems to still...
Seems like the dozer dataset definitely exists ([here](https://github.com/nerfstudio-project/nerfstudio/blob/3ac1b6bec7396e975c43cdcd3bfe89743f6073d6/nerfstudio/scripts/downloads/download_data.py#L119)). Have you used colab before? Seems like a colab error and I'm wondering if it's a new problem.
Can you explain what you mean by this? If you mean cropped point clouds and meshes, this should already be supported in ns-export.
Hey! Thanks for letting me know the errors! Unfortunately I'm still working on debugging the training portion in this pr draft... But your error seems to point to a tinycudann...
Thank you!!! Going to test this soon and see if anything is needed, but it looks like everything is good!
Hi! What dataset are you training on? `means3d: torch.Size([0, 3])` means there are 0 points hence the invalid shape error in projection step. I cannot recreate this error on my...
Hi thanks for submitting the issue! Can you attach a screenshot of your error message and how to reproduce it please?
You can include `--vis viewer+wandb` in your command to access both the viewer (to view your nerf during training) and wandb (for evaluation metrics)!
I think `add_notification` being in the gui api seems reasonable, but the `clear_notification` part kind of breaks the harmony of the rest of the api. There is probably a cleaner...
Should be good to go now!