When I optimize the same model with tensorRT_optimization tool on Nvidia Drive AGX platform twice in a row , I get two binary files of different sizes. Also, it is mentioned here https://github.com/NVIDIA/framework-determinism that TensorRT behaves non-deterministically. Drive OS comes with TensorRT 5.1.2. Is it fixed in newer versions? Can the model be optimized deterministically using TensorRT C++ API? When will solution be available on Nvidia Drive?
TensorRT Version: 5.1.2
CUDA Version: 10.2