Not getting real time performance on face detection

[ghimireadarsh]

I am using open-cv to read the camera feed and passing to facenet-pytorch mtcnn module for face detection. The bottleneck I see is in the mtcnn.detect() which takes 0.08 to 0.1 second per frame which is like 10 to 12.5 FPS. I am getting same speed while GPU and CPU. I am not getting performance improvement while using GPU. Could anyone suggest on how to attain real-time speed?

[Uysim]

I am facing the same problem