huijuan88
commented
5 years ago You can check the test lib file in the code.
It doesn’t include the video loading time. The video loading time also depends on the frame size.
It includes the teasing and post-processing time.
On Nov 10, 2018, at 23:00, canbaoburen notifications@github.com<mailto:notifications@github.com> wrote:
It is mentioned that your activity detection speed can reached at 569 fps. I wonder how you compute the speed? I guess it include the time of post-processing such as NMS, right? Then, does it include the time of frames reading and pre-processing before input to the C3D becuse it is usually time-consuming? Hope to receive your reply soon.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/VisionLearningGroup/R-C3D/issues/43, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AFOa_8u0T40PVKds3c2L9ewxhB2x8gOzks5ut8sJgaJpZM4YYWpb.
Qinying-Liu
It is mentioned that your activity detection speed can reached at 569 fps. I wonder how you compute the speed? I guess it include the time of post-processing such as NMS, right? Then, does it include the time of frames reading and pre-processing before input to the C3D becuse it is usually time-consuming? Hope to receive your reply soon.