During the past few months I have been working towards making high performance deep learning inferences much more accessible in ROS on the nVidia Jetson TX2. The result is jetson_tensorrt: a collection of optimized TensoRT based nodes and nodelets specifically tailored to the Jetson platform. To start out with, classification and object detection are supported for nVidia DIGITS ImageNet and DetectNets.
Here is some example output in rviz from a single class pedestrian detector using an Intel RealSense D435:
DetectNet Object Detection
Support is planned for SegNets as well.
Check it out on Github!