Creating a sequential block

You decided to redesign your binary CNN model template by creating a block of convolutional layers. This will help you stack multiple layers sequentially. With this improved model, you will be able to easily design various CNN architectures.

torch and torch.nn as nn have been imported.

Deze oefening maakt deel uit van de cursus

Deep Learning for Images with PyTorch

Cursus bekijken

Oefeninstructies

In the __init__() method, define a block of convolutional layers and assign it to self.conv_block.
In the forward() pass, pass the inputs through the convolutional block you defined.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

class BinaryImageClassification(nn.Module):
  def __init__(self):
    super(BinaryImageClassification, self).__init__()
    # Create a convolutional block
    self.conv_block = ____(
      nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
      nn.ReLU(),
      nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1),
      nn.ReLU(),
    )
    
  def forward(self, x):
    # Pass inputs through the convolutional block
    x = ____
    return x

Code bewerken en uitvoeren