运行时错误，输入的形状无效

Question

我正在尝试获取网络的输入和输出信息。调试时，出现此错误，Runtime, shape ‘[-1, 400]’ is invalid for input of size 384. 我尝试了不同的值，但找不到正确的值。有没有办法解决这个问题？谢谢。

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16*5*5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

input_shape = (3, 21,21)
        dummy_input = torch.randn(6,*input_shape)
        graph = torch.jit._get_trace_graph(model,  args=dummy_input, _force_outplace=False, _return_inputs_states=False)

错误信息：

RuntimeError: shape '[-1, 400]' is invalid for input of size 384

Answer 1

卷积层后张量的形状为[6,16,2,2]。因此，在将它们馈送到线性层之前，您不能将其重塑为 16*5*5。如果您想在卷积层中使用与原始过滤器大小相同的过滤器，则应将您的网络更改为下面给出的网络。

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16*2*2, 120) # changed the size
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16*2*2) # changed the size
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x