About MIMO TensorRT Engine


I have two question about TensorRT Engines of multi input multi output networks.

when i have a network which contains two input encoder and two output decoder (ex.input: camera, lidar, output:detection, semantic segmentation) and convert it TensorRT Engine, and i want to execute it as camera+lidar-detection or camera-only segmentation model separately.

Is there any api for realizing this engine execution?

If i realize this execution and execute as camera-only segmentation, whether does this engine computes lidar-encoder and segmentaion decoder or not?

Sorry for my bad English.

Please check the below link, as they might answer your concerns