在 PyTorch 中调用 forward 方法与调用 model 实例

Question

A lot of the PyTorch tutorials I've been viewing do something like this.

Define model:

class Network(nn.Module):
    def __init__():
        super().__init__()
        self.conv1 = ..
        ... 
    
    def forward(x)
        ...
    ...

Once the Network has been instantiated ( net = Network() ), the people in the tutorials write net(input_data) instead of net.forward(input_data) . I tried net.forward() and it gives the same results as net() .

Why is this a common practice, and also why does this work?

Answer 1

You should avoid calling Module.forward . The difference is that all the hooks are dispatched in the __call__ function see this , so if you call .forward and have hooks in your model, the hooks won't have any effect.

Inshort when you call Module.forward , pytorch hooks wont have any effect

Detailed answer can be found in this post