- 先导入需要的包torch和matplotlib
import torch
import matplotlib.pyplot as plt
2.导入数据,并定义随机定义w的初始值 然后定义前向传播函数(forward)定义损失函数(loss)
x_data = [1, 2, 3.0] y_data = [2, 4, 6.0] w = torch.tensor([1.0]) w.requires_grad = True def forward(x): return x * w def loss(x, y): y_pre = forward(x) return (y_pre - y) ** 2
3.定义训练过程
首先指定了一个预测输入值x=4的时候,还没有进行优化要输出的值
print('before training', 4, forward(4).item())
注意:因为传播过程中,w和y_hat都是以梯度的方式存放的,forward储存的变量类型是Tensor,所以要通过item()改成标量的形式
选定要epoch的次数,选择100次
sum1 = 0 sum2_list = [] l_list = [] for epoch in range(100): sum1 += 1 for x, y in zip(x_data, y_data): l = loss(x, y) l.backward() # 反向传播计算w的梯度 print('\tgrad:', x, y, w.grad.item()) w.data = w.data - 0.01 * w.grad.data # 更新w w.grad.data.zero_() # w置零 l_list.append(l.item()) sum2_list.append(sum1) print('progress:', epoch, l.item()) # 打印迭代的次数和损失值 print("predict(after training)", 4, forward(4).item())
4.最后进行可视化:
plt.plot(sum2_list,l_list) plt.xlabel('epoch') plt.ylabel('loss') plt.show()
5.结果展示:
progress: 95 9.094947017729282e-13
grad: 1 2 -7.152557373046875e-07
grad: 2 4 -2.86102294921875e-06
grad: 3.0 6.0 -5.7220458984375e-06
progress: 96 9.094947017729282e-13
grad: 1 2 -7.152557373046875e-07
grad: 2 4 -2.86102294921875e-06
grad: 3.0 6.0 -5.7220458984375e-06
progress: 97 9.094947017729282e-13
grad: 1 2 -7.152557373046875e-07
grad: 2 4 -2.86102294921875e-06
grad: 3.0 6.0 -5.7220458984375e-06
progress: 98 9.094947017729282e-13
grad: 1 2 -7.152557373046875e-07
grad: 2 4 -2.86102294921875e-06
grad: 3.0 6.0 -5.7220458984375e-06
progress: 99 9.094947017729282e-13
predict(after training) 4 7.999998569488525
我也是初学者,哪里有问题请各位大佬指正