Hey I have been working with deep learning model for image segmentation using Tensoorrt on Jetson Xavier Nx.
I am using jetpack 4.6.
My question is can I deserialize and load multiple tensorrt engines to memory for inferencing ? I would also want to switch between these engine as per the input ?
YES, you can.
But please make sure you have created a separated CUDA context for each model.
Below is an example for your reference:
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.