Yukai Yang (Alexis)

1. Ideally yes, the different stages can be pipelined in parallel. This might cause some delay with live stream but the overall FPS should improve. However, python has GIL so...

1) Currently, KLT runs in parallel with detection. What do you want to replace KLT with? 2) Yes, refer to one-stage network like FairMOT. However, FairMOT is not optimized (slow)....

Also, I think three stages can potentially be multithreaded, i.e., detection, feature extraction, and association. But even without Python's GIL, because of the frame skip mechanism, these are not run...

I need to know your target hardware. Keeping KLT is required if you don’t want to run the detector every frame for FPS. “Reusing the feature vector” is the same...

For Jetson, it's recommended to keep KLT because the detector and feature extractor are too expensive to run at every frame. Unless you can get JDE or FairMOT converted to...

Marking this as a feature request for one stage model. You should look at FairMOT instead of JDE because it is more accurate. Let me know if you make any...

DLA34 is probably slow. Converting their YOLOv5s backbone to TRT is better. You might need YOLOv5 TRT plugins.

Related: #184

@PonyMaY Thanks. I cannot access your link. Can you share your ONNX model and your TensorRT conversion script if possible? Did you use any plugins?

@akashAD98 FastMOT supports scaled YOLO models. Please open a new issue if you have further questions