Skip to content

Install through PyPI #36

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.

Sign up for GitHub

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

Jump to bottom
Closed
anandijain opened this issue Feb 9, 2020 · 2 comments
Closed

Install through PyPI #36

anandijain opened this issue Feb 9, 2020 · 2 comments
Assignees
@bottler @nikhilaravi
Labels
enhancement New feature or request

Comments

@anandijain
Copy link

I am wondering why the package is not on PyPI. I am thinking it is because of some of the dependencies, but I'm not sure.

Installing through PyPI without conda makes it much easier for anyone to get started.
This is useful for many users.
@nikhilaravi
Copy link
Contributor

@anandijain this is on our roadmap! We hope to release a PyPi package soon.

@nikhilaravi nikhilaravi added the enhancement New feature or request label Feb 10, 2020
@bottler
Copy link
Contributor

bottler commented Mar 31, 2020

pytorch3d is now available on pypi for Mac and Linux. These are CPU-only builds - they don't use cuda.

@bottler bottler closed this as completed Mar 31, 2020
@rohitdavas rohitdavas mentioned this issue Jul 4, 2020
Closed
facebook-github-bot pushed a commit that referenced this issue Jun 26, 2022
@d4l3k @facebook-github-bot
shader: add SoftDepthShader and HardDepthShader for rendering depth m…
7e0146e 
…aps (#36)

Summary:
X-link: fairinternal/pytorch3d#36

This adds two shaders for rendering depth maps for meshes. This is useful for structure from motion applications that learn depths based off of camera pair disparities.

There's two shaders, one hard which just returns the distances and then a second that does a cumsum on the probabilities of the points with a weighted sum. Areas that don't have any z faces are set to the zfar distance.

Output from this renderer is `[N, H, W]` since it's just depth no need for channels.

I haven't tested this in an ML model yet just in a notebook.

hard:
![hardzshader](https://user-images.githubusercontent.com/909104/170190363-ef662c97-0bd2-488c-8675-0557a3c7dd06.png)

soft:
![softzshader](https://user-images.githubusercontent.com/909104/170190365-65b08cd7-0c49-4119-803e-d33c1d8c676e.png)

Pull Request resolved: #1208

Reviewed By: bottler

Differential Revision: D36682194

Pulled By: d4l3k

fbshipit-source-id: 5d4e10c6fb0fff5427be4ddd3bd76305a7ccc1e2
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@bottler bottler

@nikhilaravi nikhilaravi

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@bottler @nikhilaravi @anandijain