学习b站刘二大人视频所写
视频传送门
import torch
import matplotlib.pyplot as plt
import numpy as np
xy = np.loadtxt('000.txt', delimiter=' ', dtype=np.float32)
x_data = torch.from_numpy(xy[:, :-1]) # 取前九列
y_data = torch.from_numpy(xy[:, [-1]]) # 取最后一列
class Model(torch.nn.Module):
def __init__(self):
super(Model, self).__init__()
self.linear1 = torch.nn.Linear(9, 6)
# linear(x1,x2)的两个参数分别表示输入输出的维度(矩阵的列数)
#这里的9与数据集的列数一至
self.linear2 = torch.nn.Linear(6, 4)
self.linear3 = torch.nn.Linear(4, 1)
self.sigmoid = torch.nn.Sigmoid()
#激活函数用于实现非线性化
def forward(self, x1):
x1 = self.sigmoid(self.linear1(x1))
x1 = self.sigmoid(self.linear2(x1))
x1 = self.sigmoid(self.linear3(x1))
return x1
model = Model()
# construct loss and optimizer
criterion = torch.nn.BCELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=0.02)
# model.parameters()自动完成参数的初始化操作
loss_sum = []
# training cycle forward, backward, update
for epoch in range(100):
y_pred = model(x_data) # forward 算预测值
loss = criterion(y_pred, y_data) # forward: 算损失值
print(epoch, loss.item())
loss_sum.append(loss)
optimizer.zero_grad() # 清除上一轮的梯度,防止累积
loss.backward() # backward: autograd,自动计算梯度,反向传播
optimizer.step() # update 参数,即更新w和b的值
x = range(100)
y = loss_sum
plt.plot(x, y)
plt.xlabel('Epoch')
plt.ylabel('loss')
plt.grid() # 生成网格
plt.show()