Pytorch 的 add_module() 是什么？

Question

I stumbled upon the method add_module() in a Pytorch model.

The doc only states

Adds a child module to the current module.

The module can be accessed as an attribute using the given name.

I don't understand what "adding a child module" means.

How is it different from just setting a pointer to the other module using self._other module = other_module ?

What are the nuances?

Answer 1

As mentioned here: https://discuss.pytorch.org/t/when-to-use-add-module-function/10534

In general, you won't need to call add_module . One potential use case is the following:

class Net(nn.Module):
    def __init__(self):
    super(Net, self).__init__()
        modules = [...]  # some list of modules
        for module in modules:
            self.add_module(...)

Answer 2

nn.Module s have a hierarchy of child modules that you can access via methods like module.named_children() or module.children() .

As mentioned in the forum post above, doing self._other module = other_module will type check other_module , see it's an nn.Module , and also add it to the child list, so add_module isn't really necessary.

Answer 3

Adding a module as an attribute works fine, as you say. But it can be a bit difficult to do at runtime if you don't know how many modules you have in advance, and you have to construct names programmatically. In such a case, add_module() is a very convenient way to do this. I've just written a short blog post showing this in action: https://blog.d-and-j.net/deep-learning/2021/04/23/pytorch-add_module.html