Jetson Nano trt_pose_hand performance


I’ve been playing around with my Jetson Nano and I ran the NVIDIA-AI-IOT/trt_pose_hand: Real-time hand pose estimation and gesture classification using TensorRT ( example with my CSI camera

I get around 8.2FPS

I compared this with a custom built mediapipe 0.8 that includes compiled OpenGL ES support and I modified the Hands - mediapipe ( solution to use either the CPU or the GPU and I get around 13-14FPS with the CPU version and around 40FPS with the GPU version.

That certainly surprised me a bit to see the performance difference so big…

Does anyone else have some performance statistics that they can share or any ideas what the reason may be?


I’m running

  • Jetpack 4.6
  • OpenCV 4.5.3 compiled from source with CUDA support
  • mediapipe 0.8 compiled from source with OpenEL GPU support. I modified the hand_gesture solution to use the GPU (different graph, …)


The model complexity in these two examples are quite different.

trt_pos_hand sample use OpenPose resnet18_baseline_att_224x224 model whose size is 85MB.
mediapipe use TF lite model which is just 1.98MB.

It’s expected that smaller model gives a better performance.
But it may have some accuracy drawback in a complicated scenario.