Why does fps onscreen of video very different from fps printed when using -show_stats or -real_input_fps with face detection models? Openvino on FPGA vs CPU: face-detection-adas-001 vs face-detection-retail-0004

Hi,

QUESTION: Showing FPS on screen (by omitting no_show flag) doesn’t always give same number as –real_input_fps (retail-0004) and –show_stats (adas-0001). Can vary by 50-100 fps. Is there a reason for this? What does each FPS value (from the flags, higher vs. printed on the video while inference is running, lower) indicate?

There will be variation due to the CPU will be performing the post processing to show the image in your display which will cause it to have a lower fps compare to not showing the image. The FPS will varies depending on how many detection has been detected and whether if other task need to be performed on the CPU.