pytorch深度学习实践（刘二大人）课堂代码&作业——逻辑回归

skyyeahhh

已于 2024-08-02 20:50:46 修改

阅读量95

点赞数 3

分类专栏： pytorch深度学习实践（刘二大人）课堂代码&作业文章标签：深度学习 pytorch 逻辑回归人工智能

于 2024-08-02 20:50:27 首次发布

本文链接：https://blog.csdn.net/weixin_51944652/article/details/140880061

版权

pytorch深度学习实践（刘二大人）课堂代码&作业专栏收录该内容

5 篇文章 1 订阅

订阅专栏

一、课堂代码

import torch
import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])

class LogisticRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LogisticRegressionModel,self).__init__()
        self.linear = torch.nn.Linear(1, 1)
    
    def forward(self, x):
        y_pred = F.sigmoid(self.linear(x))
        return y_pred


l_list = []
epoch_list = []

model = LogisticRegressionModel()

criterion = torch.nn.BCELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

for epoch in range(3000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())
    epoch_list.append(epoch)
    l_list.append(loss.item())

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

print('w =', model.linear.weight.item())
print('b =', model.linear.bias.item())

plt.plot(epoch_list, l_list)
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.savefig('逻辑回归.png')
plt.close()

x = np.linspace(0, 10, 200)   #0~10采样200个点
x_t = torch.Tensor(x).view(200,1) #转变成200行1列的矩阵
y_t = model(x_t)
y = y_t.data.numpy()  #用.numpy得到n维数组
plt.plot(x, y)
plt.plot([0, 10], [0.5, 0.5], c='r')  #画直线，起点[0,0,5]终点[10,0.5]，红色
plt.xlabel('Hours')
plt.ylabel('Probability of Pass')
plt.grid()  #带网格
plt.savefig('Probability of Pass.png')
plt.show()

结果：