pytorch 线性模型LinearModel 的使用

import matplotlib.pyplot as plt
import numpy as np
import torch
 
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])
 
w_list = []
b_list = []
mse_list = []
class LinearModel(torch.nn.Module):
    """
    线性模型类
    """
    def __init__(self):
        super(LinearModel, self).__init__()
        self.linear =  torch.nn.Linear(1, 1)
        #Linear（x,y,true）输入维度x，输出维度y,是否带偏置
 
    def forward(self, x):
        """
        前向传播
        :param x: 输入向量 
        :return:  前向传播预测值
        """
        y_pred = self.linear(x)
        return y_pred
	# pytorch根据计算图自动求导，不需要定义反向传播函数
 
#创建线性模型类
model = LinearModel()
# 定义模型的损失函数
criterion = torch.nn.MSELoss(size_average=False)
# criterion = torch.nn.MSELoss(reduction='sum')
 
# 定义模型的优化器
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)
 
# 反向传播更新参数
for epoch in range(100):
    y_pred = model.forward(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch+1, loss.item())
 
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    w_list.append(model.linear.weight.item())
    mse_list.append(loss.item())
    b_list.append((model.linear.bias.item()))
 
print('w = {}'.format(model.linear.weight.item()))
print('b = {}'.format(model.linear.bias.item()))
 
 
#绘图
# x,y = np.meshgrid(w_list,b_list)
ax = plt.axes(projection='3d')
ax.plot3D(w_list,b_list, mse_list)
ax.set_xlabel('w')
ax.set_ylabel('b')
ax.set_zlabel('loss')
plt.show()