引言

在很多经典网络结构中都有nn.Parameter()这个函数，故对其进行了解

pytorch官方介绍：

语法结构：

torch.nn.parameter.Parameter(data=None, requires_grad=True)
"""
data (Tensor) – parameter tensor. —— 输入得是一个tensor。
requires_grad (bool, optional) – if the parameter requires gradient. See Locally disabling gradient computation for more details。
Default: True —— 这个不用解释，需要注意的是nn.Parameter()默认有梯度。
"""

torch.nn.Parameter继承torch.Tensor，其作用将一个不可训练的类型为Tensor的参数转化为可训练的类型为parameter的参数，并将这个参数绑定到module里面，成为module中可训练的参数。

torch.nn.Parameter(Tensor data, bool requires_grad)

其中：data为传入Tensor类型参数，requires_grad默认值为True，表示可训练，False表示不可训练。

以nn.Linear为例：

class Linear(Module):
    r"""Applies a linear transformation to the incoming data: :math:`y = xA^T + b`
    Args:
        in_features: size of each input sample
        out_features: size of each output sample
        bias: If set to ``False``, the layer will not learn an additive bias.
            Default: ``True``
    Shape:
        - Input: :math:`(N, *, H_{in})` where :math:`*` means any number of
          additional dimensions and :math:`H_{in} = \text{in\_features}`
        - Output: :math:`(N, *, H_{out})` where all but the last dimension
          are the same shape as the input and :math:`H_{out} = \text{out\_features}`.
    Attributes:
        weight: the learnable weights of the module of shape
            :math:`(\text{out\_features}, \text{in\_features})`. The values are
            initialized from :math:`\mathcal{U}(-\sqrt{k}, \sqrt{k})`, where
            :math:`k = \frac{1}{\text{in\_features}}`
        bias:   the learnable bias of the module of shape :math:`(\text{out\_features})`.
                If :attr:`bias` is ``True``, the values are initialized from
                :math:`\mathcal{U}(-\sqrt{k}, \sqrt{k})` where
                :math:`k = \frac{1}{\text{in\_features}}`
    Examples::
        >>> m = nn.Linear(20, 30)
        >>> input = torch.randn(128, 20)
        >>> output = m(input)
        >>> print(output.size())
        torch.Size([128, 30])
    """
    __constants__ = ['in_features', 'out_features']

    def __init__(self, in_features, out_features, bias=True):
        super(Linear, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = Parameter(torch.Tensor(out_features, in_features))
        if bias:
            self.bias = Parameter(torch.Tensor(out_features))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self):
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound)

    def forward(self, input):
        return F.linear(input, self.weight, self.bias)

    def extra_repr(self):
        return 'in_features={}, out_features={}, bias={}'.format(
            self.in_features, self.out_features, self.bias is not None
        )

注解：

1. 在__init__(self, in_features, out_features,
   bias=True)中初始化两个参数：self.weight和self.bias。
2. self.weight = Parameter(torch.Tensor(out_features,
   in_features))定义一个形状为（out_features, in_features）可训练参数。
3. self.bias同理。
4. 与torch.tensor([1,2,3],requires_grad=True)的区别，这个只是将参数变成可训练的，并没有绑定在module的parameter列表中。