Yolo for real time

Will the yolo predictions work the same for real time videos or will you have to define real time object diffently? I intend to run the model using real time.

Thanks in advance for helping.

YOLO as described in the original presentations and research papers runs on the order of 40 frames per second. What does real time mean to you?

Found this while rereading the V1 paper to respond to a different thread…

Our base network runs at 45 frames per second with no batch processing on a Titan X GPU and a fast version runs at more than 150 fps. This means we can process streaming video in real-time with less than 25 milliseconds of latency.

That was in 2015.