Skip to content
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

How to Enable GPU Computation in Python Wrapper #4905

Closed
riven314 opened this issue Sep 22, 2019 · 1 comment
Closed

How to Enable GPU Computation in Python Wrapper #4905

riven314 opened this issue Sep 22, 2019 · 1 comment

Comments

@riven314
Copy link

riven314 commented Sep 22, 2019


Required Info
Camera Model D435i
Firmware Version 05.11.06.250
Operating System & Version Win 10
Kernel Version (Linux Only)
Platform Notebook (Lenovo Y740)
SDK Version v2.25
Language python
Segment deploy in my own notebook

Issue Description

I mainly use your python wrapper for my own development. I installed sdk 2.0 here (https://www.intelrealsense.com/developers/).
I found that the current SDK viewer and the python wrapper only consume my CPU power, and I want to leverage my GPU computation. How can I enable GPU computation in python wrapper?

@MartyG-RealSense
Copy link
Collaborator

RealSense SDK 2.0 supports CUDA for graphics processing enhancement. If your GPU supports CUDA, you can use CMake to build Librealsense with CUDA enabled by using the build customization flag BUILD_WITH_CUDA which is set to False by default.

https://github.com/IntelRealSense/librealsense/wiki/Build-Configuration#build-customization-flags

image

An alternative to CUDA is GLSL processing blocks, which were added in SDK version 2.22.0.

#3654

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants