DeepLabCut-core icon indicating copy to clipboard operation
DeepLabCut-core copied to clipboard
verified publisher icon DeepLabCut

Hope to remove the Intel-openmp dependency

Open disadone opened this issue 4 years ago • 3 comments

I try to install deeplabcut-core to download pretrained model on my jetson nano. However, I found DLC need Intel-openmp. ARM frame CPU becomes more and more popular (like Apple M1). Maybe you can consider my suggestion :; Also I wonder how you test your models on Jetson Xavier. If I trained a model on an x86, it can be implemented on an arm directly with tensorRT support? Thanks!

disadone avatar Feb 13 '21 14:02 disadone

This is probably a question that belongs to the forum/gitter, but since someone brought it up here, I'm also curious about the same thing. I'm on macOS with M1 chip, and was wondering if you plan to support it anytime in the future.

Alyetama avatar Feb 16 '21 05:02 Alyetama

Hi @disadone then you should use deeplabcut-live; as this is designed to work on embedded systems like Jetson: https://github.com/DeepLabCut/DeepLabCut-live

MMathisLab avatar Feb 23 '21 10:02 MMathisLab

@Alyetama I have not tried the M1 yet, but we will test it soon and see what's needed, thanks!

MMathisLab avatar Feb 23 '21 10:02 MMathisLab