Learning CNN and getting below error

vision
1

Hi,
I know below error is discussed many times but i am still not able to figure out.
The error i am getting is :
RuntimeError: Given groups=1, weight of size [12, 6, 5, 5], expected input[100, 1, 32, 32] to have 6 channels, but got 1 channels instead

below is my code:

class Network(nn.Module):
def init(self):
super(Network, self).init()
self.conv1 = nn.Conv2d(in_channels=1, out_channels= 6, kernel_size=5)
self.conv2 = nn.Conv2d(in_channels=6, out_channels=12, kernel_size=5)

    self.fc1 = nn.Linear(in_features=12*4*4, out_features=120)
    self.fc2 = nn.Linear(in_features=120, out_features=60)
    self.out = nn.Linear(in_features=60, out_features=10)

def forward(self, t):
    #input layer
    t = t

    #hidden conv layer1
    x = F.relu(self.conv1(t))
    x = F.max_pool2d(x,kernel_size= 2, stride=2)

    # hidden conv layer2
    x = F.relu(self.conv2(t))
    x = F.max_pool2d(t,kernel_size= 2, stride=2)

    #hidden linear layer
    x = x.view(-1, 12 * 4 * 4)
    x = F.relu(self.fc1(x))
    x = F.relu(x)

    #hidden linear layer
    x = self.fc2(x)
    x = F.relu(x)

    x = self.out(x)
    #return F.log_softmax(x, dim=1)
    return x

I am converting the RGB image to grayscale by using below lines:

transform = transforms.Compose(
[torchvision.transforms.Grayscale(num_output_channels=1), transforms.ToTensor(),
transforms.Normalize([0.5],[0.5])])

Not sure where the problem is, can someone point it out to me?

2

You are passing the input tensor t again to self.conv2 instead of x.

3

Thank you, silly mistake…