![]() |
Multimedia API ReferenceNovember 16, 2016 | 24.2.1 Release |
TensorRT is an accelerated neural network inference engine and run-time library. ConvertCaffeToGieModel
is a standalone model conversion tool that converts a CAFFE network to a TensorRT compatible model. This tool aims to run 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.
Before running the sample, you must have the following:
The CudaEngine
structure is a TensorRT interface that invokes the TensorRT function.
The sample uses the following function:
Function | Description |
---|---|
caffeToGIEModel | Uses TensorRT API to transfer a network model from CAFFE to TensorRT. |
To run the sample, execute:
ConvertCaffeToGieModel -n <network_name> -l <model_name> -m <mode_name> -o <outBlob_name> [<outBlob_name>] -f <fp16 or fp32> -b <batch_size> -s <store_cache_name>
The following example shows a sample execution: