pytorch中Module模块中named_parameters函数

函数named_parameters()，返回各层中参数名称和数据

class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.hidden = nn.Sequential(
            nn.Linear(256,64),
            nn.ReLU(inplace=True),
            nn.Linear(64,10)
                )
    def forward(self, x):
        return self.hidden(x)

    
#x = torch.randperm(256*2).view(-1,256)
net = MLP()
net(x.float())
#随机输出结果
tensor([[  73.2550,  -51.5631,    4.3549,   19.0657,  -55.6626,  -80.8340,
          -21.1650,   93.4071,   -9.8959,  -49.4214],
        [  39.6934,   -2.6528,   63.8478,   -5.0462,  -83.4204, -128.7376,
           72.5279,    3.0522,   77.3654,  -70.5397]], grad_fn=<AddmmBackward>)

params = net.named_parameters()
for name, param in params:
    print(name, param.data.shape)
    print(type(param))
hidden.0.weight torch.Size([64, 256])
hidden.0.bias torch.Size([64])
hidden.2.weight torch.Size([10, 64])
hidden.2.bias torch.Size([10])
<class 'torch.nn.parameter.Parameter'>

源码：

 def _named_members(self, get_members_fn, prefix='', recurse=True):
        r"""Helper method for yielding various names + members of modules."""
        memo = set()
        modules = self.named_modules(prefix=prefix) if recurse else [(prefix, self)]
        for module_prefix, module in modules:
            members = get_members_fn(module)
            for k, v in members:
                if v is None or v in memo:
                    continue
                memo.add(v)
                name = module_prefix + ('.' if module_prefix else '') + k
                yield name, v

def named_parameters(self, prefix='', recurse=True):
        r"""Returns an iterator over module parameters, yielding both the
        name of the parameter as well as the parameter itself.

        Args:
            prefix (str): prefix to prepend to all parameter names.
            recurse (bool): if True, then yields parameters of this module
                and all submodules. Otherwise, yields only parameters that
                are direct members of this module.

        Yields:
            (string, Parameter): Tuple containing the name and parameter

        Example::

            >>> for name, param in self.named_parameters():
            >>>    if name in ['bias']:
            >>>        print(param.size())

        """
        gen = self._named_members(
            lambda module: module._parameters.items(),
            prefix=prefix, recurse=recurse)
        for elem in gen:
            yield elem

来源：CSDN

作者：小白827

链接：https://blog.csdn.net/qq_24503095/article/details/103630382