RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[8, 1, 256, 256] to have 3 channels, but got 1 channels instead

Question

I got this error RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[8, 1, 256, 256] to have 3 channels, but got 1 channels instead. This is my code

I haven't found the cause for this. Can anyone help me to figure out the problems? Thank you

"'"


"'"
class UNet(nn.Module):
  def __init__(self, in_channels=3, features=[32,64,128,512], num_classes=3):
    super().__init__()

    self.down = []
    self.pool = nn.MaxPool2d(2,2)

    for i in range(len(features)):
      if i == 0:
        self.down.append(
            nn.Sequential(
                DoubleConv(in_channels, features[i])
            )
        )
      else:
        self.down.append(
            nn.Sequential(
                DoubleConv(features[i-1], features[i])
            )
        )
    
    self.down = nn.ModuleList(self.down)

    self.lower = DoubleConv(features[-1], features[-1]*2)

    self.up = []
    self.dbc = []

    features.reverse()
    for i in range(len(features)):
      if i == 0:
        self.up.append(
            nn.Sequential(
                nn.ConvTranspose2d(features[0]*2,features[i], 2, 2),
                nn.ReLU()
            )
        )
        self.dbc.append(DoubleConv(features[i]*2, features[i]))
      else:
        self.up.append(
            nn.Sequential(
                nn.ConvTranspose2d(features[i-1], features[i],2,2),
                nn.ReLU(),
            )
        )
        self.dbc.append(DoubleConv(features[i]*2, features[i]))
    
    self.up = nn.ModuleList(self.up)

    self.classifier = nn.Conv2d(features[-1], num_classes, 3, 1, 1)

  def forward(self, x):
    x1 = self
    x_down = []
    for i, layer in enumerate(self.down):
      x_down.append(layer(x))
      
      x = self.pool(x_down[-1])
      
      print(x.shape)
    
    x_lower = self.lower(x)
    print(x_lower.shape)

    x_down.reverse()

    x_up = []
    for i, (layer_up, layer_dbc) in enumerate(zip(self.up, self.dbc)):
      if i == 0:
        temp_x = layer_up(x_lower)
        print(temp_x.shape)
        temp_x = torch.cat((temp_x, x_down[i]), dim=1)
        x_up.append(layer_dbc(temp_x))
      
      else:
        temp_x = layer_up(x_up[-1])
        temp_x = torch.cat((temp_x, x_down[i]), dim=1)
        x_up.append(layer_dbc(temp_x))
      
      # print(x_up[-1].shape)
    
    x_classifier = self.classifier(x_up[-1])
    print(x_classifier.shape)
    return x_classifier

I tried to check the model with the input

model = UNet()
x = torch.randn(3,3,256,256)
output = model(x)

and work