Deepstream-test3 DS(5.1) and deepstream with triton


Have some questions:

python program for deepstream-test3:

  1. i am taking the obj_meta.confidence retrieve from object and noticed the values in it are all -0.10000000149011612? Why is it so ?

  2. the object id is all 18446744073709551615 when retrieved, it is being that there is no tracking?

Is there some python sample for deepstream with triton as well?

thank you

1 If “Group Rectangles” mode of clustering is chosen then confidence value is set to -0.1 because the algorithm does not preserve confidence value. Also, for the objects being tracked by the tracker but not detected by the inference component, confidence value is set to -0.1 .
2 in one case, if the objects detected and tracked is only one.
3 you can refer to deepstream-ssd-parser, it used triton inference server.

1 Like

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.