Building a U-Net: forward method

With the encoder and decoder layers defied, you can now implement the forward() method of the U-net. The inputs have already been passed through the encoder for you. However, you need to define the last decoder block.

The goal of the decoder is to upsample the feature maps so that its output is of the same height and width as the U-Net's input image. This will allow you to obtain pixel-level semantic masks.

Deze oefening maakt deel uit van de cursus

Deep Learning for Images with PyTorch

Cursus bekijken

Oefeninstructies

Define the last decoder block, using torch.cat() to form the skip connection.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

def forward(self, x):
    x1 = self.enc1(x)
    x2 = self.enc2(self.pool(x1))
    x3 = self.enc3(self.pool(x2))
    x4 = self.enc4(self.pool(x3))

    x = self.upconv3(x4)
    x = torch.cat([x, x3], dim=1)
    x = self.dec1(x)

    x = self.upconv2(x)
    x = torch.cat([x, x2], dim=1)
    x = self.dec2(x)

    # Define the last decoder block with skip connections
    x = ____
    x = ____
    x = ____

    return self.out(x)

Code bewerken en uitvoeren