Closed BananaLv26 closed 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)
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!
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)