LiMeng95 / MultiPoseNet.pytorch

pytorch implementation of MultiPoseNet (ECCV 2018, Muhammed Kocabas et al.)
196 stars 32 forks source link

有关intermediate supervision的问题 #27

Closed BananaLv26 closed 5 years ago

BananaLv26 commented 5 years ago

为什么代码里面计算intermediate supervision 的时候计算heatmap通道数是19?和GT对应的话不是应该18吗 self.convfin_k2 = nn.Conv2d(256, 19, kernel_size=1, stride=1, padding=0) self.convfin_k3 = nn.Conv2d(256, 19, kernel_size=1, stride=1, padding=0) self.convfin_k4 = nn.Conv2d(256, 19, kernel_size=1, stride=1, padding=0) self.convfin_k5 = nn.Conv2d(256, 19, kernel_size=1, stride=1, padding=0)

accountcwd commented 5 years ago

多出来的通道应该是做分割的mask,详细看这里的loss定义,不过貌似大佬屏蔽掉了,应该没做好吧。

BananaLv26 commented 5 years ago

多出来的通道应该是做分割的mask,详细看这里的loss定义,不过貌似大佬屏蔽掉了,应该没做好吧。

好的,感谢!