New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loading multiple pipelines and trainers #161
Comments
@orperel as a continuation of the above response I have tried the following. First, to give you a brief description of what I am trying to achieve so that we are in the same page. My goal is to load and train multiple sdf pipelines. Then I am using the default
The above gives me the following error:
So apparently I am doing something wrong. I am not sure whether the |
@orperel I am trying to use a similar approach as in
My
Attached I have the full demo source code, just in case it makes of any help. Just put it inside the app folder similarly to the nerf and nglod folders and then just run the |
ok, specifying the
but now I am getting the following:
so I am not sure if using |
Ok small win, the above error is resolved by passing the pipeline to the cuda device since by default the device was set to the cpu.
@orperel I am not sure now how to connect the |
The above
which my guess is due to the different size of vertices/faces of my actual mesh files. Thus, now I am stuck on two main issues:
I've attached also the updated |
You can add multiple objects to the scene graph like this:
Each object has its own
ObjectTransform
so you can control their orientation, dimensions and location around the scene.Some more explanation about the scene graph and
NeuralRadianceFieldPackedRenderer
is available in the docs:https://kaolin-wisp.readthedocs.io/en/latest/pages/renderer.html#the-scenegraph
Keep in mind that the app runs in an infinite loop, add_to_scene_graph is an async request. The object actually gets added to the scene graph when the next frame is drawn.
If you have further questions please open a separate issue, it makes it easier for me to track :)
Originally posted by @orperel in #35 (comment)
The text was updated successfully, but these errors were encountered: