Comments (5)
Yeah, we should make this clearer. It's currently the host address the server is listening to, which is not necessarily a valid IP address: https://stackoverflow.com/questions/20778771/what-is-the-difference-between-0-0-0-0-127-0-0-1-and-localhost
from nerfstudio.
But will this be solved shortly? Because I want to implement my own models, but also pull from source the latest features and merge them with Git, without having to sort everything manually.
from nerfstudio.
Try going to http://localhost:7007/ for the viewer, this seems to work on Windows
from nerfstudio.
But will this be solved shortly? Because I want to implement my own models, but also pull from source the latest features and merge them with Git, without having to sort everything manually.
This is actually working as designed; 0.0.0.0
is the host address that the webserver is bound to. It's just a bad design because this isn't an IP address that you can necessarily connect to... we should print something clearer, but the fix wouldn't impact your ability to connect to the viewer.
The server should still be accessible by connecting to whatever machine you're running on. If you're running locally http://localhost:7007
should work (as pointed out by @cvachha), if you're running on a remote server (assuming no firewalls) and you know IP address you can also connect to http://that_ip:7007
, for SSH a common practice is also just to forward the port: https://docs.nerf.studio/quickstart/viewer_quickstart.html#training-on-a-remote-machine
As an experimental thing, you can also pass in --viewer.make-share-url True
and you should get a publically accessible https URL at https://[some random string].share.viser.studio
.
from nerfstudio.
Just having to click on the link in the console definitely makes things smoother.
from nerfstudio.
Related Issues (20)
- wandb tries to initialize before logs directory is created
- Doubt about nerfstudio's convention for equirectangular coordinates
- ModuleNotFoundError: No module named 'nerfstudio.viewer.viewer_elements' HOT 2
- CUDA error: an illegal memory access was encountered HOT 6
- ns-train splatfacto for nerfstudio-data with mask_path report RuntimeError HOT 2
- How do I get only the parts of the mesh I want?
- Splatfacto during test . NotImplementedError: Saving images is not implemented yet HOT 1
- Is it originally just the surface and empty on the inside?
- There is way to remove baxkground in mesh? HOT 15
- Splat .ply export not supported by multiple viewers HOT 2
- "Vanilla-NeRF" Poor convergance
- `ns-render dataset` bug for gaussian splatting HOT 3
- poor result on custom images HOT 2
- Automatically generating renderings from eval poses HOT 3
- Unable to render to mp4 with `RuntimeError: stack expects a non-empty TensorList` HOT 5
- How to see which images are used for the evaluation?
- How do I determine the appropriate bbox?
- how to get real size mesh?? HOT 5
- Error when running zipnerf method in nerfstudio HOT 9
- mesh is too small HOT 11
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nerfstudio.