Size mismatch, m1: [5 x 44944], m2: [400 x 120] im new at this please help

torch.Size([3, 224, 224])

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(x.size(0), 16*53*53)
    x = F.relu(self.fc1(x))
    x = F.relu(self.fc2(x))
    x = self.fc3(x)
    return x

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)

for epoch in range(2): # loop over the dataset multiple times

running_loss = 0.0
for i, data in enumerate(train_loader, 0):
    # get the inputs; data is a list of [inputs, labels]
    inputs, labels = data

    # zero the parameter gradients
    optimizer.zero_grad()

    # forward + backward + optimize
    outputs = net(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

    # print statistics
    running_loss += loss.item()
    if i % 2000 == 1999:    # print every 2000 mini-batches
        print('[%d, %5d] loss: %.3f' %
              (epoch + 1, i + 1, running_loss / 2000))
        running_loss = 0.0

print(‘Finished Training’)Preformatted text

RuntimeError Traceback (most recent call last)

RuntimeError: size mismatch, m1: [5 x 44944], m2: [400 x 120] at …\aten\src\TH/generic/THTensorMath.cpp:41

Can you post the complete stack trace and also format the code?

I ran the code and the mistake is this:

In your model definition, the first linear layer (self.fc1) takes as input 400 neurons whereas during the forward() call, the input to the self.fc1() has the shape torch.Size([1, 44944]). So change your model definition

from:
self.fc1 = nn.Linear(16*5*5, 120)
to:
self.fc1 = nn.Linear(16*53*53, 120)

1 Like

Target 18 is out of bounds error when i changed it

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 * 53 * 53, 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(x.size(0), 165353)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)

for epoch in range(2): # loop over the dataset multiple times

running_loss = 0.0
for i, data in enumerate(train_loader, 0):
    # get the inputs; data is a list of [inputs, labels]
    inputs, labels = data

    # zero the parameter gradients
    optimizer.zero_grad()

    # forward + backward + optimize
    outputs = net(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

    # print statistics
    running_loss += loss.item()
    if i % 2000 == 1999:    # print every 2000 mini-batches
        print('[%d, %5d] loss: %.3f' %
              (epoch + 1, i + 1, running_loss / 2000))
        running_loss = 0.0

print(‘Finished Training’)

error:
IndexError Traceback (most recent call last)
in
11 # forward + backward + optimize
12 outputs = net(inputs)
—> 13 loss = criterion(outputs, labels)
14 loss.backward()
15 optimizer.step()

IndexError: Target 18 is out of bounds.

Your last layer

has only 10 output neurons which means you classify into 10 classes.

But your targets/labels go even higher than that.

Your loss-function gets the output of your network, which classifies into 10 classes, but gets class 18 as ground-truth target/label, thats why it says:

Change the 10 in this line to the number of classes your dataset has.