namogg

For the regconition network, im getting this error. RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs. Dictionaries and strings are also accepted, but their usage is not...

For my testing, communication time is not that time consuming. Eventhough throughput of Triton is higher than TensorRT when handling multiple request, the latency for each client is too high...

We also have the same concern. Does CVCUDA have any sample working with NvBufSurface in C++/python?

Here is some of my eviroment settings: • DeepStream Version: 7.0 • TensorRT Version: 8.6.1 • NVIDIA GPU Driver Version: 550 • GPU: RTX 4060Ti • Docker image: nvcr.io/nvidia/deepstream:7.0-gc-triton-devel