Closed feitiandemiaomi closed 6 years ago
Hi, we tried it on a Titan-X GPU. We did not try any lighter network since we rather went for accuracy, and the speed was quite fast compared to the state of the art (at that time).
Thank you for your timely reply , I will have a try .
@scaelles Hi, Thank your great repo, I read your paper saying the model can process a frame in 102ms, What is your machine? and have you try the lighter network to improve efficiency ?