PyTorch零基础入门之逻辑斯蒂回归

# -*- coding: utf-8 -*-
"""
Created on Mon Oct 18 08:35:00 2021

@author: 86493
"""
import torch
import torch.nn as nn
import matplotlib.pyplot as plt  
import torch.nn.functional as F
import numpy as np

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


losslst = []

class LogisticRegressionModel(nn.Module):
    def __init__(self):
        super(LogisticRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)
        
    def forward(self, x):
    	# 和线性模型的网络的唯一区别在这句，多了F.sigmoid
        y_predict = F.sigmoid(self.linear(x))
        return y_predict
    
model = LogisticRegressionModel()

# 使用交叉熵作损失函数
criterion = torch.nn.BCELoss(size_average = False)
optimizer = torch.optim.SGD(model.parameters(), 
                            lr = 0.01)

# 训练
for epoch in range(1000):
    y_predict = model(x_data)
    loss = criterion(y_predict, y_data)
    # 打印loss对象会自动调用__str__
    print(epoch, loss.item())
    losslst.append(loss.item())
    # 梯度清零后反向传播
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

# 画图
plt.plot(range(1000), losslst)
plt.ylabel('Loss')
plt.xlabel('epoch')
plt.show()


# test
# 每周学习的时间，200个点
x = np.linspace(0, 10, 200)
x_t = torch.Tensor(x).view((200, 1))
y_t = model(x_t)
y = y_t.data.numpy()
plt.plot(x, y)
# 画 probability of pass = 0.5的红色横线
plt.plot([0, 10], [0.5, 0.5], c = 'r')
plt.xlabel('Hours')
plt.ylabel('Probability of Pass')
plt.grid()
plt.show()