问题
I am new to pyTorch and getting following Size Mismatch error:
RuntimeError: size mismatch, m1: [7 x 2092500], m2: [180 x 120] at ..\aten\src\TH/generic/THTensorMath.cpp:961
Model:
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
How ever I tried changing x = x.view(x.shape[0], -1) to x = x.view(x.size(0), -1) but that also did'nt work. Dimension of images is 512x384. and have used following transformation:
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
回答1:
The problem is that the dimensions of the output of your last max pooling layer don't match the input of the first fully connected layer. This is the network structure until the last max pool layer for input shape (3, 512, 384):
----------------------------------------------------------------
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
================================================================
The last row of the table means that MaxPool2d-4 outputs 180 channels (filter outputs) of 125 width and 93 height. So you need your first fully connected layer to have 180 * 125 * 93 = 2092500 input size. This is a lot, so I'd advise you to refine your architecture. In any case, if you change the input size of the first fully connected layer to 2092500, it works:
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
Giving the following architecture:
----------------------------------------------------------------
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
(You can use the torchsummary package to generate these tables.)
来源：https://stackoverflow.com/questions/57534072/how-to-fix-runtimeerror-size-mismatch-in-pytorch