Openvx/Visionworks graph input from GPU memory Buffer

[armand.zampierizn4wa]

Ok moved here:

Openvx/Visionworks graph input from GPU memory Buffer

Description Hello, I am facing a problem with Siamrpn++ inferencing with tensorrt. This problem is present for many similar network architecture and is, from what i learned, due to the non-support of the cross-correlation between two dynamic input by tensorrt (tensorrt seems to require a static kernel for this kind of operations). To solve this issue the solutions found yet are to crop the network architecture before the cross-correlation operation and to do those either manually or using ot…

Thought tensorrt issue mentionned is not jetson specific (observed on a windows plateform too), and same for visionworks buffer issue (thought visionworks is mainly oriented toward jetson)