search

linghu8812 / tensorrt_inference

702 stars 206 forks source link

Do I need to destroy stream after every run? #49

Closed xxxpsyduck closed 3 years ago

xxxpsyduck commented 3 years ago

I trying to do inference with video input. After running inference on a frame, do I need to destroy the stream and recreate a new one for new frame?

linghu8812 commented 3 years ago

no need

linghu8812 commented 2 years ago

Here is an TensorRT inference on video example which includes detection and tracking: https://github.com/linghu8812/tensorrt_tracker