Syntax problems about net

vision
1

the code is shown below:

class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)
out = net(input)

x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)), self.conv1 is an instance of nn.Conv2d defined in the __init__function, but how to understand the operation self.conv1(x) since conv1 has been initialized. As I know, self.conv1() is a operation initializing an instance.
The second problem is the same as above. “net” has been initialized in the code “net = Net()”, how to understand “net(input)”?

2

Calling a nn.Module like self.conv1(x) or net(input) calls the internal __call__ method.
Have a look at the source. This method performs some operations regarding forward and backward hooks and calls forward.

3

Can I use net.forword(x) instead?

4

You could, but shouldn’t, since the hooks won’t be called.