Non-constant inference time with pycaffe

I have a python script that reads images from a USB camera and feeds them to a Caffe neural network. I tried to log the inference and acquisition time at each iteration and I noticed that there are some strange peaks that I don’t know how to explain. I tried to set the number of cores using taskset (all cores, two A72, one A72) but the issue remains. I am attaching the plot for the 2 cores case (I can only upload one image).

I think the issue is on the USB side? We have increased the new user max image number. You can post the other images as well.

For the image acquisition, it could be. As for the inference, I don’t understand how the USB could be related…

I am attaching the other images.
One core:

All cores:

By “All cores”, do you include the A53 cores? Can you just let the A53 cores offline and test with only two A72 cores?