The best configuration for realtime application

Daniil-Osokin / lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

Apache License 2.0

656 stars 138 forks source link

Closed morgunl2 closed 4 years ago

morgunl2 commented 4 years ago

As far as I understand, we can consider one of these configurations:

OpenVino, CPU. For this configuration I have 3-6 FPS with default input height (256) and about 40 FPS with 128 input height
OpenVino, GPU
PyTorch, CPU
PyTorch, GPU

Could you make an advice, what config is the fastest for you algorithm?

Daniil-Osokin commented 4 years ago

Hey, use PyTorch + GPU with c++ part built.

Daniil-Osokin commented 4 years ago

Hope, it helped.

ghost commented 4 years ago

Hello @Daniil-Osokin. How about the performance in terms of error (MPJPE) ?