Closed lucasjinreal closed 1 year ago
@Walter0807 the output of onnx is same with pytorch when feeding same input. As I should feed the keypoints and process in c++, so I doubt is this preprocess keypoints part not fully aligned with python. however it's hard to compare the values in c++ but if onnx is right, then wrong part must be some preprocessing step.
@Walter0807 I realize the problem, it seems original python have 2 ways for normalize, using input w h or directly normalize to -1, 1, what's the differences between them?
OH, I also found a serrious problem, the normalization you did in python, was on whole sequence, while in realtime, it can not...... how to resolve this?
I have resolved all problems, now C++ runs OK.
I'm not sure, what is wrong with your result? You can also print the variables (e.g. network input) in C++ and python.