schen
schen
Hello, author, may I ask 'top_ down_ img_ demo_ with_ mmdet. 'pose' in 'py'_ Why is the key point image visualized by 'plot' and the image obtained by 'API' in...
你好,请问我下载了代码重新训练了一下,但几轮下来DEV wer依旧是100%.我把batchsize调成1,lr调成0.000010.可以给点意见吗,谢谢.
@ycmin95 Thanks for your reply.
> I believe that those are the Y axis positions of the middlePIP_left keypoint through the whole video (take a look at [this](https://google.github.io/mediapipe/images/mobile/hand_landmarks.png) to see the codification of hands' keypoints)....
How to change from （x，y， score） to 
Thank you，that‘s great explanation.
Sorry，I mean this [https://github.com/IDEA-Research/OSX/issues/108](https://github.com/IDEA-Research/OSX/issues/108)
Ok，thank you！
Ok，thank you，i will try matching 02-16 to 15 actions you provide.
I compare annotation of osx' Human36M and your H3WD，and find that they have different frames. Your video frame annotations are not continuous, e.g. there is no S1/Images/Directions.60457274/frame_0001.jpg.