torch.nn.Parameter()的用法

1.首先，一定记住：这个是 继承来自 torch.tensor的，所以本质是一个tensor.

        不过，它可以train更新参数

2.参考文章：

(1)这篇文章 和 例子超级 简洁清晰

理解torch.nn.Parameter - 知乎 (zhihu.com)

里面的实例：

import torch
import torch.nn as nn
from torch.optim import Adam

class NN_Network(nn.Module):
    def __init__(self, in_dim, hid, out_dim):
        super(NN_Network, self).__init__()
        self.linear1 = nn.Linear(in_dim, hid)
        self.linear2 = nn.Linear(hid, out_dim)
        self.linear1.weight = torch.nn.Parameter(torch.zeros(in_dim,hid))
        self.linear1.bias = torch.nn.Parameter(torch.ones(hid))
        self.linear2.weight = torch.nn.Parameter(torch.zeros(hid,out_dim))
        self.linear2.bias = torch.nn.Parameter(torch.ones(out_dim))
    def forward(self, input_array):
        h = self.linear1(input_array)
        y_pred = self.linear2(h)
        return y_pred

in_d = 5
hidn = 2
out_d = 3
net = NN_Network(in_d, hidn, out_d)

（2）其他参考文章：

torch.nn.Parameter()函数的讲解和使用-CSDN博客

torch.nn.Parameter()函数 - 知乎 (zhihu.com)