Wir verwenden Cookies

Wir nutzen Cookies auf unserer Website. Einige von ihnen sind essenziell, während andere uns helfen, diese Website und Ihre Erfahrung zu verbessern.

Essenziell
 
Analyse & Performance
 
Diplom- arbeit

Deep learning using GPU for video concept detection

Content

Deep learning methods have received considerable attention recently for image classification and object detection tasks. The high computational effort of these approaches can be managed by using frameworks relying on the computational power of graphics processors (GPU). The aim of this work is to evaluate GPU based deep learning frameworks (such as CuDNN) for tasks like concept detection in video.