I am currently working on a computer vision problem statement for which I use C3D on CPU only mode. It works great, but feature extraction on my dataset of videos (1900 videos) takes 4 to 5 days. I want to now build a real time prototype of my model. Could you suggest minimum GPU configuration for this to be possible?
By real-time, I mean 1 sec of a 240x320 video should be processed within much lesser than 1 sec so that further processing can be done on features to send out real time alerts.
Thanks in advance.
I am currently working on a computer vision problem statement for which I use C3D on CPU only mode. It works great, but feature extraction on my dataset of videos (1900 videos) takes 4 to 5 days. I want to now build a real time prototype of my model. Could you suggest minimum GPU configuration for this to be possible? By real-time, I mean 1 sec of a 240x320 video should be processed within much lesser than 1 sec so that further processing can be done on features to send out real time alerts. Thanks in advance.