you can download it and take a look. I am using the 2022.3.3lts version. I did an asynchronous read operation. When I run it on 4070tigpu, the frame rate can reach around 300. When I use the integrated graphics, the speed is only in the tens. What I hope is that the number of running frames of my project will not be affected by model parsing.
I did the following three tests. They are included in the update method of the PoseEstimator script. You can use your laptop to test and run it based on the tests I made. I don’t know if my code is wrong. If so, Please help me write the correct code
