![](/img/trans.png)
[英]Pytorch : RuntimeError: mat1 dim 1 must match mat2 dim 0
[英]Pytorch nn.Linear RuntimeError: mat1 dim 1 must match mat2 dim 0
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 16, 3, padding=1)
self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
self.max_pool = nn.MaxPool2d(2)
self.fc1 = nn.Linear(7*7*32, 128)
self.fc1 = nn.Linear(128, 10)
def forward(self, x):
x = self.max_pool(F.relu(self.conv1(x)))
x = self.max_pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1)
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = F.softmax(x, dim=1)
return x
以上是model。 输入图像的形状是1×28×28,batch_size 16。我尝试在flatten后打印x.shape,即(16, 1568),完全对应self.fc1()的输入大小。 有人有什么主意吗?
您已将此 function nn.Linear(128, 10)
命名为self.fc1
即self.fc1 = nn.Linear(128, 10)
请将其更改为self.fc2 = nn.Linear(128, 10)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.