Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GPU • DeepStream Version 6.2 • JetPack Version (valid for Jetson only) • TensorRT Version • NVIDIA GPU Driver Version (valid for GPU only) • Issue Type( questions, new requirements, bugs) • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
hello
If I look at deepstream-app-test2, through the pipeline example of pgie->tracker->sgie, classify has been implemented well.
What I want is a pipeline like pgie->sgie->tracker. Is there any problem with changing the order?
If possible, I want to use the tracker’s interval more, but when inferDone=No, can I get all the meta information about pgie-sgie?
hello. We are working on a project related to face-recognition.
pgie
detect face and landmark
Face-align using opencv through cuda-unified-bufmap
sgie
face recognition
tracker
[important] Currently only bbox is tracking
because of the information about the entire frame, does the tracker have to come before sgie?
As I said before, the pipeline I want is pgie->sgie->tracker
A few limitations that I think
It is good to receive an aligned image for sgie, but align will fall between Pgie and sgie. (precisely pgie_pad_probe_src)
If the tracker is included, since tracking is not possible track the landmark info, when it is pgie-tracker-sgie, I think the performance will decrease in sgie rather.