YOLO Object Detection Plugin for DeepStream 2.0

Hi all, we have released a new sample plugin for DeepStream 2.0 performing YOLO (You Only Look Once) object detection, accelerated with TensorRT. Supported models include YOLO v2 & v3.

Find the sources here: https://github.com/vat-nvidia/deepstream-plugins

Hi, I wonder if I have to write a plugin when using a custom model.
If not, which models are supported in default GIE(nvinfer)?
Especially, is SSD or Faster-RCNN supported?