Inference time?

hey @nvidias

I have trained an object detection model using mmdet hrnet. after converting the mmdet .pth file to .trt file on NX device I am getting inference time for one image is like 0.3 seconds. Before conversion to trt it was like 2 seconds for single image. Using trt model can we speed up the inference time less than to 0.3 seconds ? Any idea ?



I’m not who you’re looking for.
I think you should use “Hi” or “Hi Teams”.
In fact, when you asked the question, you didn’t specify anyone。


1 Like


When converting a model into TensorRT, you can choose different precision for inference.

By default, TensorRT will use fp32 precision if not specified.
You can try fp16 or even int8 precision to see if any acceleration.


This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.