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

Using Jetson Xavier NX, Jetson Nano #127

Open
raspberryHummus opened this issue Feb 26, 2020 · 2 comments
Open

Using Jetson Xavier NX, Jetson Nano #127

raspberryHummus opened this issue Feb 26, 2020 · 2 comments

Comments

@raspberryHummus
Copy link

Hello,

I am curious if the new Jetson Xavier NX will be supported in the newer version of OPT?

Do you have any experience with the Jetson Nano for pose tracking?
Will the setup guide for the TX2 work for the Jetson Nano or Xavier or is it individual for each Jetson platform?

Thanks!

@arjunsengupta98
Copy link

The hardware requirements specify that an x86 machine is needed. So I don't think it'll work on Jetson. I wanted it to run it on Jetson as well, ran into errors while compiling, then noticed the hardware requirement.

@MikoyChinese
Copy link
Contributor

Hi,
It is no problem. Firstly, you need to ensure your Jetson Device can run the camera and publish color and depth data.

And then you need to find a algorithm which can run in your Jetson, maybe you can try tensorRT to speed up your network. Here some pose estimation example tf-pose-estimation. If you just want to detect an object, you can try the newest network such like centerNet.

Finally, change code you need.

  1. publish color and depth
  2. Transform all coordinate to world coordinate.
  3. Run your detect function to get result.
  4. Publish the result and analyze it.

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

3 participants