如何修复:运行时错误:pyTorch 中的大小不匹配

Question

我是 pyTorch 的新手，并收到以下大小不匹配错误：

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

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

我曾经尝试将x = x.view(x.shape[0], -1)更改为x = x.view(x.size(0), -1)但这也没有奏效。图像尺寸为 512x384。并使用以下转换：

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

Answer 1

问题是最后一个最大池化层的输出尺寸与第一个全连接层的输入不匹配。这是直到输入形状(3, 512, 384)的最后一个最大池层的网络结构：

----------------------------------------------------------------
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
================================================================

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，您需要第一个全连接层具有180 * 125 * 93 = 2092500输入大小。这很多，所以我建议你改进你的架构。在任何情况下，如果将第一个全连接层的输入大小更改为2092500，它都可以工作：

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

提供以下体系结构：

----------------------------------------------------------------
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
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

(您可以使用火炬摘要包生成这些表。