Hi, I hava a YOLO model with ONNX format, and I want to transform it to TensorRT model, so my question is TensorRT recommend to use dynamic batch or specified batch ?
I will do inference with maxbatch size = 2, whether it is necessary to use dynamic batch ? which is faster?
My application connnect 2 cameras to detect object, so it always use a batch size of 2, but when one of the camera disconnect or other reasons to cause frame cannot be obtained, it will use batch size of 1.