Closed psw13583112 closed 3 years ago
Hi, thank you for the interest! I think the problem might be 2D pose normalization. The 2D pose here has absolute value > 1 (head, feet), which is not usual in training data. Can you try scale down the 2D pose by 0.5?
@Garfield-kh Thanks a lot for your prompt reply, I tried to reduce it by 0.5 times, the effect is indeed much better, but the results obtained by predicting the same picture every time are not the same.
Did you fix the random seed and also model.eval() for the dropout layer?
@Garfield-kh Thank you, I will pay attention to these details
Can this model run a single picture? When I ran a picture, there was some misalignment. The model used was MLP trained by PoseAug, and I found that the result was not very satisfactory.