Why does maxpool layer get reused?

1

I am following the CNN example at : https://github.com/pytorch/tutorials/blob/master/beginner_source/blitz/cifar10_tutorial.py
and noticed that the MaxPool layer gets reused with different conv layers (conv1, conv2).

Can someone explain what is the logic behind reusing the pool layer?

    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x```
2

Since MaxPool2d doesn’t have any parameters/state. Alternatively, you can use the functional form nn.functional.max_pool_2d