As mentioned in the above link, I found that executing yolov5s half-precision is slower than full-precision on jetson agx orin. The same code is indeed faster than full-precision on jetson xavier nx. It is normal. May I ask? What are the reasons?
Which frameworks do you use?
Could you run it with TensorRT?
The code is executed under the pytorch framework. I just tested tensort’s FP32 and FP16 and found that it is normal. fp16 is faster than fp32. What may be the cause of the problem?
Have you maximized the device’s performance?
$ sudo nvpmodel -m 0
$ sudo jetson_clocks
More, do you have the ONNX model?
Could you check to get the benchmark data with trtexec?
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.