[Question] Run viewer on private ip than local host
coolkite opened this issue · comments
Hi,
i am having an issue with viewing my rendering of the prompt using the viewer script when I run it on my server. Since I cannot access the localhost link through my server's console, I forward it using ngrok and view it on my local machine (macbook pro). However, the checkpoint doesn't render. As such, I am wondering if there is a way to run the viewer on a private ip than localhost.
I am able to look at the gifs used for eval in the wandb folder so I know the model trained properly but there seems to be some issue with the viewing.
If using the splat viewer is a better option, how and what do I upload to view it in the browser?
Hi coolkite,
Thank you for your interest. In my practical usage, I will use SSH for port tunneling.
ssh -L <YOUR_LOCAL_PORT>:<YOUR_SERVER_IP>:<YOUR_SERVER_PORT> <YOUR_USER>@<YOUR_SERVER>
where the <YOUR_SERVER_PORT>
is 8080
by default.
If you wish to use the splat viewer, first convert the .pt
checkpoint to .ply
file by using the scripts:
python utils/export.py <your_ckpt> --type ply
where the <your_ckpt>
can be the path to the .pt
checkpoint file or, more conveniently, can be the id for the run (the display name of the run in wandb, e.g. 0|213630|2023-10-11|a_high_quality_photo_of_a_corgi
).
After running this command, you can find the exported .ply
file in the exports/ply
directory.
Then, open the online splat viewer and drag the .ply
file into the browser window.
I am really sorry for the inconvenience caused by the design and the incomplete documentation. Feel free to ask any questions about the viewer and our method.
Best regards,
heheyas
Hi heheyas,
Thank you. This worked like a charm! I did encounter an error with the export script but I was able to do a quick fix that I'll open a new issue for.