ModuleList — PyTorch 2.7 documentation (original) (raw)
class torch.nn.ModuleList(modules=None)[source][source]¶
Holds submodules in a list.
ModuleList can be indexed like a regular Python list, but modules it contains are properly registered, and will be visible by allModule methods.
Parameters
modules (iterable , optional) – an iterable of modules to add
Example:
class MyModule(nn.Module): def init(self) -> None: super().init() self.linears = nn.ModuleList([nn.Linear(10, 10) for i in range(10)])
def forward(self, x):
# ModuleList can act as an iterable, or be indexed using ints
for i, l in enumerate(self.linears):
x = self.linears[i // 2](x) + l(x)
return x
append(module)[source][source]¶
Append a given module to the end of the list.
Parameters
module (nn.Module) – module to append
Return type
extend(modules)[source][source]¶
Append modules from a Python iterable to the end of the list.
Parameters
modules (iterable) – iterable of modules to append
Return type
Self
insert(index, module)[source][source]¶
Insert a given module before a given index in the list.
Parameters