NVIDIA Xavier - Deep Learning - TensorRT - Parsing Caffe
Parsing Caffe model for TensorRT
The process for caffe models are fairly similar to Tensorflow models. The key difference is that you don't need to generate a uff model file. Caffe model file (.caffemodel) can be imported directly from tensorrt.
Loading a caffe model is an actual example provided by NVIDIA with TensorRT naned sample_mnist. For more details on this example please refer to the C++ API section.