我是pyTorch的新手,并遇到以下“大小不匹配”错误:

RuntimeError: size mismatch, m1: [7 x 2092500], m2: [180 x 120] at ..\aten\src\TH/generic/THTensorMath.cpp:961


模型:

class Net(nn.Module):
def __init__(self):
    super(Net, self).__init__()
    self.conv1 = nn.Conv2d(3, 200, 5)
    self.pool = nn.MaxPool2d(2, 2)
    self.conv2 = nn.Conv2d(200, 180, 5)
    self.fc1 = nn.Linear(180, 120)
    self.fc2 = nn.Linear(120, 84)
    self.fc3 = nn.Linear(84,5)

def forward(self, x):
    x = self.pool(F.relu(self.conv1(x)))
    x = self.pool(F.relu(self.conv2(x)))
    x = x.view(x.shape[0], -1)
    x = F.relu(self.fc1(x))
    x = F.relu(self.fc2(x))
    x = self.fc3(x)
    return x


我曾经尝试过将x = x.view(x.shape[0], -1)更改为x = x.view(x.size(0), -1),但是那也没有用。图片尺寸为512x384。并使用了以下转换:

def load_dataset():
data_path = './dataset/training'

transform = transforms.Compose(
               [transforms.Resize((512,384)),
                transforms.ToTensor(),
                transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])


train_dataset = torchvision.datasets.ImageFolder(root=data_path,transform=transform)
train_loader = torch.utils.data.DataLoader(train_dataset,batch_size=7,num_workers=0,shuffle=True)

return train_loader

最佳答案

问题在于最后一个最大池化层的输出尺寸与第一个完全连接的层的输入尺寸不匹配。这是直到输入形状(3, 512, 384)的最后一个最大池层为止的网络结构:

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1        [-1, 200, 508, 380]          15,200
         MaxPool2d-2        [-1, 200, 254, 190]               0
            Conv2d-3        [-1, 180, 250, 186]         900,180
         MaxPool2d-4         [-1, 180, 125, 93]               0
================================================================


该表的最后一行表示MaxPool2d-4输出180个通道(滤波器输出),宽度为125,高度为93。因此,您需要第一个完全连接的层具有180 * 125 * 93 = 2092500输入大小。这很多,所以我建议您改进体系结构。无论如何,如果将第一个完全连接的图层的输入大小更改为2092500,它将起作用:

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 200, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(200, 180, 5)
        #self.fc1 = nn.Linear(180, 120)
        self.fc1 = nn.Linear(2092500, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84,5)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(x.shape[0], -1)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


提供以下架构:

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1        [-1, 200, 508, 380]          15,200
         MaxPool2d-2        [-1, 200, 254, 190]               0
            Conv2d-3        [-1, 180, 250, 186]         900,180
         MaxPool2d-4         [-1, 180, 125, 93]               0
            Linear-5                  [-1, 120]     251,100,120
            Linear-6                   [-1, 84]          10,164
            Linear-7                    [-1, 5]             425
================================================================
Total params: 252,026,089
Trainable params: 252,026,089
Non-trainable params: 0


(您可以使用torchsummary包来生成这些表。)

关于python - 如何修复:RuntimeError:pyTorch中的大小不匹配,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/57534072/

10-15 01:23
查看更多