Sequential module - forward() method

Now, that you have defined all the modules that the network needs, it is time to apply them in the forward() method. For context, we are giving the code for the forward() method, if the net was written in the usual way.

class Net(nn.Module):
    def __init__(self, num_classes):
        super(Net, self).__init__()

        self.conv1 = nn.Conv2d(in_channels=1, out_channels=5, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(in_channels=5, out_channels=10, kernel_size=3, padding=1)
        self.conv3 = nn.Conv2d(in_channels=10, out_channels=20, kernel_size=3, padding=1)
        self.conv4 = nn.Conv2d(in_channels=20, out_channels=40, kernel_size=3, padding=1)

        self.relu = nn.ReLU()

        self.pool = nn.MaxPool2d(2, 2)

        self.fc1 = nn.Linear(7 * 7 * 40, 1024)
        self.fc2 = nn.Linear(1024, 2048)
        self.fc3 = nn.Linear(2048, 10) 

    def forward():
        x = self.relu(self.conv1(x))
        x = self.relu(self.pool(self.conv2(x)))
        x = self.relu(self.conv3(x))
        x = self.relu(self.pool(self.conv4(x)))
        x = x.view(-1, 7 * 7 * 40)
        x = self.relu(self.fc1(x))
        x = self.relu(self.fc2(x))
        x = self.fc3(x)
        return x

Note: for evaluation purposes, the entire code of the class needs to be in the script. We are using the __init__ method as you have coded it on the previous exercise, while you are going to code the forward() method here.

Extract the features from the images.
Squeeze the three spatial dimensions of the feature maps into one using the view() method.
Classify images based on the extracted features.

Exercise

Sequential module - forward() method

Instructions