Error implementation in U-net

code U-net

class DoubleConv(nn.Module):
    """(convolution => [BN] => ReLU) * 2"""
    def __init__(self, in_channels, out_channels, mid_channels=None):
        super().__init__()
        if not mid_channels:
            mid_channels = out_channels
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )
    def forward(self, x):
        return self.double_conv(x)

class UNet(nn.Module):
    def __init__(self):
        super(UNet, self).__init__()
        self.n_channels = 1
        self.n_classes = 2
        self.bilinear = True 
        self.inc = DoubleConv(1, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        factor = 2 if True else 1
        self.down4 = Down(512, 1024 // factor)

class Down(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(Down,self).__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        )

    def forward(self, x):
        return self.maxpool_conv(x)
    
    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        self.up1 = Up(1024, 512 // factor, bilinear)
        self.up2 = Up(512, 256 // factor, bilinear)
        self.up3 = Up(256, 128 // factor, bilinear)
        self.up4 = Up(128, 64, bilinear)
        
class Up(nn.Module):
    """Upscaling then double conv"""
    def __init__(self, in_channels, out_channels, bilinear=True):
        super(Up,self).__init__()
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
            self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
        else:
            self.up = nn.ConvTranspose2d(in_channels , in_channels // 2, kernel_size=2, stride=2)
            self.conv = DoubleConv(in_channels, out_channels)  


    def forward(self, x1, x2):
        x1 = self.up(x1)
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]
        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)#  
        return self.conv(x)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1) 
        self.outc = OutConv(64, n_classes)

class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        return self.conv(x)

I tested this code but

I can’t seem to find the forward method in UNet class. Also can you tell me why do you need two forward method in Down class? Thank you

hi @demetere how i fix it for this code is running??

@randinoo. Hmm I think there are many things that need to be changed. First of all, I think DoubleConv is fine.

As I guess, Down is for reducing the resolution using MaxPool and doing DoubleConv after that. So I think that class is fine too.

I think Up class needs some modifications.

class Up(nn.Module):
    """Upscaling then double conv"""
    def __init__(self, in_channels, out_channels, bilinear=True):
        super(Up,self).__init__()
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
            self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
        else:
            self.up = nn.ConvTranspose2d(in_channels , in_channels // 2, kernel_size=2, stride=2)
            self.conv = DoubleConv(in_channels, out_channels)  


    def forward(self, x1, x2):
        x1 = self.up(x1)
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]
        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)#  
        return self.conv(x)

I do not know what are you doing with diffY and diffX but let’s consider those as the right ones.

I think OutConv is good too. Now for the final UNet Class

class UNet(nn.Module):
    def __init__(self):
        super(UNet, self).__init__()
        self.n_channels = 1
        self.n_classes = 2
        self.bilinear = True 
        self.inc = DoubleConv(1, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        factor = 2 if True else 1
        self.down4 = Down(512, 1024 // factor)
        self.up1 = Up(1024, 512 // factor, bilinear)
        self.up2 = Up(512, 256 // factor, bilinear)
        self.up3 = Up(256, 128 // factor, bilinear)
        self.up4 = Up(128, 64, bilinear)
        self.outc = OutConv(64, n_classes)

    def forward(self, x):
         x = self.inc(x)
         x = self.down1(x)
         x = self.down2(x)
         x = self.down3(x)
         x = self.down4(x)
         x = self.up1(x)
         x = self.up2(x)
         x = self.up3(x)
         x = self.up4(x)
         x = self.outc(x)
         return x

I have just started coding on pytorch too but I was working on UNet recently and I think that should be the right classes. I hope it helps you.

Good Luck