'RuntimeError: The size of tensor a (10) must match the size of tensor b (35000) at non-singleton dimension 1

data = b1.send(bob)
data.shape  # torch.Size([35000, 1, 28, 28]) 


pred = model(data)
pred.shape #torch.Size([35000, 10])


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(784, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        return x
model=Net()


for i in range(10):

    # Train Bob's Model
    opt.zero_grad()
    pred = model(data)
    loss = criterion(pred, target.view(1, -1))
    loss.backward()

    opt.step()
   

This throws the error:

RuntimeError: The size of tensor a (10) must match the size of tensor b (35000) at non-singleton dimension 1


Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source