You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In paper “4.2 We considered the pose as a k x 2-dimensional property of the center point , and parametrize each keypoint bu an offset to the center point . **we directly regress to the joint offsets(in pixels) with an L1 loss ** ”
Why use pixels not a rate , that way vary unusual
问下姿态估计部分的归回,为什么要用像素来回归,这样好像就会缺少一些尺度不变性吧
请问一下,在关节点检测问题中,预测的offset_map是nHW(n是关节点的个数)的,但一个关键点只会产生一个offset值,那么在构建offset_map的target的时候,是整张map都是这一个值吗?还是怎样构成的呢?
The text was updated successfully, but these errors were encountered: