-
Notifications
You must be signed in to change notification settings - Fork 4
Open
Description
我用hrsc训练的时候,通道注意力的
def forward(self, x):
avg_pool = F.avg_pool2d(x, x.size(2), stride=x.size(2))# 平均池化操作
res=self.gate_c(avg_pool).unsqueeze(2).unsqueeze(3).expand_as(x)# 通过通道注意力模块处理平均池化的结果
return res
平均池化报错了,RuntimeError: Given input size: (256x100x96). Calculated output size: (256x1x0). Output size is too small
因该是部分图片大小不太规矩,请问您当时是怎么解决的呢?
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels