L4T Multimedia API Reference28.1 Release |
NVIDIA® TensorRT™ is an accelerated neural network inference engine and run-time library. ConvertCaffeToTrtModel
is a standalone model conversion tool that converts a CAFFE network to a TensorRT compatible model. This tool runs offline on the NVIDIA® Jetson™ platform and provides a cached TensorRT model stream to prevent subsequent repetitive network conversion. Using this converted model, TensorRT-based applications can improve greatly in accuracy and performance.
If the source model changes (i.e., is retrained), the tool performs conversion again to enable TensorRT accelerated inference.
TBD
Enter:
./ConvertCaffeToGieModel -n ../../data/model/GoogleNet-modified.prototxt \ -l ../../data/model/GoogleNet-modified-online_iter_30000.caffemodel \ -m detection -o coverage,bboxes -f fp16 -b 2 \
-h
opion.The CudaEngine
structure is a TensorRT interface that invokes the TensorRT function.
The sample uses the following function:
Function | Description |
---|---|
caffeToTRTModel | Uses TensorRT API to transfer a network model from CAFFE to TensorRT. |