YuxianMeng/Matrix-Capsules-pytorch

Isn't here a bug?

Opened this issue · 1 comments

pose = pose.view(b,16,self.B,width_in,width_in).permute(0,2,3,4,1).contiguous() #b,B,12,12,16

pose's shape is (b, self.B, H, W), how can it be reshaped into ( b, 16, self.B, H, W) in the next line????? why does no one point this out? no error reported????

哦,明白了,pose对x的切片第二个维度是倒数self.B。那就说得通了。我的眼科问题。抱歉。