问题描述
def __init__(self):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(1, 64, kernel_size=5, stride=2, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.Conv2d(64, 64, kernel_size=3, stride=2, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.Conv2d(64, 64, kernel_size=3, stride=2, bias=False),
nn.BatchNorm2d(64),
)
如何处理此错误?我认为错误是出在self.fc上，但我不能说如何解决.
How can I deal with this error? I think the error is with self.fc, but I can't say how to fix it.
推荐答案
self.conv(x)的输出的形状为 torch.Size([32，64，2，2]): 32 * 64 * 2 * 2 = 8192 (等效于( self.conv_out_size ).全连接层的输入需要一个一维向量，即在向前功能中传递到完全连接的层之前，需要先将其展平.
The output from self.conv(x) is of shape torch.Size([32, 64, 2, 2]): 32*64*2*2= 8192 (this is equivalent to (self.conv_out_size). The input to fully connected layer expects a single dimension vector i.e. you need to flatten it before passing to a fully connected layer in the forward function.
即
class Network():
...
def foward():
...
conv_out = self.conv(x)
print(conv_out.shape)
conv_out = conv_out.view(-1, 32*64*2*2)
print(conv_out.shape)
x = self.fc(conv_out)
return x
输出
torch.Size([32, 64, 2, 2])
torch.Size([1, 8192])
我认为您使用的是 self._get_conv_out 函数错误.
I think you're using self._get_conv_out function wrong.
应该是
def _get_conv_out(self, shape):
output = self.conv(torch.zeros(1, *shape)) # not (32, *size)
return int(numpy.prod(output.size()))
然后，在前进通道中，您可以使用
then, in the forward pass, you can use
conv_out = self.conv(x)
# flatten the output of conv layers
conv_out = conv_out.view(conv_out.size(0), -1)
x = self.fc(conv_out)
对于输入(32，1，110，110)，输出应为 torch.Size([32，2]).
这篇关于*** RuntimeError:每当我运行模型时，mat1 dim 1必须与mat2 dim 0匹配.的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！