RuntimeError: mat1和mat2形状不能相乘(32x400和600x120)

Question

我有下面的CNN，我得到以下错误 RuntimeError: mat1 and mat2 shapes cannot be multiplied (32x400 and 600x120)。我使用的是CIFAR10数据集，它总共包含6000张32 × 32的图像，有10个标签。如果我理解正确的话，x = F.relu(self.fc1(x))的输入尺寸应该是600x200，但输入实际上是32x400。我迷失的地方是我需要更改(或计算)的部分。

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])
batch_size = 32
cifar10 = torchvision.datasets.CIFAR10(root='./data', download=True, transform=torchvision.transforms.ToTensor())
pivot = 40000
cifar10 = sorted(cifar10, key=lambda x: x[1])
train_set = torch.utils.data.Subset(cifar10, range(pivot))
val_set = torch.utils.data.Subset(cifar10, range(pivot, len(cifar10)))
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(val_set, batch_size=batch_size, shuffle=True)
class Network(nn.Module):
    def __init__(self):
        super(Network, 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(600, 120)
        self.fc2 = nn.Linear(120, 2)
        self.fc3 = nn.Linear(2, 10)
        self.flatten = nn.Flatten(1)
    
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.flatten(x)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
model = Network()

我尝试解决类似错误的其他帖子，但无法修复我的代码。我也尝试添加torch.nn.AdaptiveMaxPool2d，但我不认为我正确使用，不确定我是否真的需要使用它。

Answer 1

最好使用"same"如果通过平均池化执行下采样，则填充卷积2d。

class Network(nn.Module):
    def __init__(self):
        super(Network, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, kernel_size=5, padding=2)
        self.pool = nn.MaxPool2d(2, 2) # downsample / 2
        self.conv2 = nn.Conv2d(6, 16, kernel_size=5, padding=2)
        self.fc1 = nn.Linear(8*8*16, 120)
        self.fc2 = nn.Linear(120, 2)
        self.fc3 = nn.Linear(2, 10)
        self.flatten = nn.Flatten(1)
    
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.flatten(x)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x