Hi,jialee
有幸阅读到simple pose这篇论文，关于论文当中产生GT高斯热图的解释我没有理解为何要涉及到R(stride步长)以及对位置的换算。论文当中是这样描述的：
By the way, we map the pixel p at the location p(x; y) in
the j-th ground truth heatmap to its original floating point
location p~(~ x; y~) = p~(x · R + R=2 − 0:5; y · R + R=2 − 0:5)
in the input image, in which R is the output stride, before
generating the precise ground truth Gaussian peaks.
在heatmapper.py中有看到相关注释，比如：
x,y coordinates of centers of bigger grid, stride / 2 -0.5是为了在计算响应图时，使用grid的中心
basically we should use center of grid, but in this place classic implementation uses left-top point.
期待您的回复，谢谢~
Sunstin
commented
4 years ago
Hi,jialee 有幸阅读到simple pose这篇论文，关于论文当中产生GT高斯热图的解释我没有理解为何要涉及到R(stride步长)以及对位置的换算。论文当中是这样描述的： By the way, we map the pixel p at the location p(x; y) in the j-th ground truth heatmap to its original floating point location p~(~ x; y~) = p~(x · R + R=2 − 0:5; y · R + R=2 − 0:5) in the input image, in which R is the output stride, before generating the precise ground truth Gaussian peaks.
在heatmapper.py中有看到相关注释，比如： x,y coordinates of centers of bigger grid, stride / 2 -0.5是为了在计算响应图时，使用grid的中心 basically we should use center of grid, but in this place classic implementation uses left-top point. 期待您的回复，谢谢~