You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm confused about how I build/compile pose_tracker. I am on ubuntu 22.02 and cuda 12.1, and I have been able to install and run through all of the main tutorials, including with rtmpose. However, I haven't compiled mmdeploy yet.
If the user has MMDeploy compiled correctly, you will see the pose_tracker executable under the mmdeploy/build/bin/.
pass 0 to input can inference from a webcam
# go to the mmdeploy folder
cd ${PATH_TO_MMDEPLOY}/build/bin/
# inference for a video
./pose_tracker rtmpose-ort/rtmdet-nano/ rtmpose-ort/rtmpose-m/ your_video.mp4 --device cpu
Is this referring to the 'Build' section in the documentation? I installed tensorrt with pip.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm confused about how I build/compile pose_tracker. I am on ubuntu 22.02 and cuda 12.1, and I have been able to install and run through all of the main tutorials, including with rtmpose. However, I haven't compiled mmdeploy yet.
For example, on https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
Is this referring to the 'Build' section in the documentation? I installed tensorrt with pip.
Beta Was this translation helpful? Give feedback.
All reactions