mediapipe icon indicating copy to clipboard operation
mediapipe copied to clipboard

Published 20 hours ago • verified publisher icon google-ai-edge

Gesture recognition on the Android platform is using too much CPU

Open yinyongliang94 opened this issue 7 months ago • 4 comments

Have I written custom code (as opposed to using a stock example script provided in MediaPipe)

None

OS Platform and Distribution

Android 13

MediaPipe Tasks SDK version

0.10.21

Task name (e.g. Image classification, Gesture recognition etc.)

Gesture Recognition

Programming Language and version (e.g. C++, Python, Java)

kotlin

Describe the actual behavior

On the rk3588 platform, when running the gesture_recognizer android-sample, whether the gesture recognition model runs on the CPU or GPU, the application's CPU usage ends up around 200%. Is this normal? If not, how can it be reduced?

Describe the expected behaviour

reduce the CPU usage to below 100%

Standalone code/steps you may have used to try to get what you need

https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/gesture_recognize，No modifications have been mader ,

Other info / Complete Logs

yinyongliang94 avatar Mar 27 '25 03:03 yinyongliang94