Resnet10 object detector: which architecture / how to interpret outputs

Hi, I am trying to run the Resnet10 object detector included with Deepstream 4.0 SDK with the Python TensorRT API to be able to work on a custom tracker prototype. I can’t find any information what type of object detector this model is (SSD, YOLO, Faster RCNN ?), and therefore I haven’t been able to interpret its output vector.

Can you please share more detailed information on the included model and how to use it outside of the nvinfer plugin? It’d be also interesting what dataset this net has been trained on.


Edit: Found how to parse the output in nvdsinfer_custombboxparser.cpp. Still, what kind of object detection architecture is this model?


ssd, frcnn are caffe models
We will public uff model for frcnn, ssd in github using deepstream 4.0 deploy.
Other info: