Logistic Regression - Pytorch

笔记来自课程《Pytorch深度学习实践》Lecture 6

Linear Regression v.s. Logistic Regression

Linear Regression 代码：

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

Logistic Regression 代码：

import torch.nn.functional as F

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

 Logisttic Regression 实现

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

# 2. Design Model
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

model = LogisticRegressionModel()

# 3. Loss and Optimizer
criterion = torch.nn.BCELoss(size_average=False) 
optimizer = torch.optim.SGD(model.parameters(), lr=0.01) 

# 4. Training cycle 
for epoch in range(1000):
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data) 
    print(epoch, loss.item())

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

测试与画图

import numpy as np
import matplotlib.pyplot as plt

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)
plt.plot([0, 10], [0.5, 0.5], c='r') 
plt.xlabel('Hours') 
plt.ylabel('Probability of Pass') 
plt.grid()
plt.show()

绘制的图像为：

多维输入

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__() 
        self.linear = torch.nn.Linear(8, 1) 
        self.sigmoid = torch.nn.Sigmoid()
    def forward(self, x):
        x = self.sigmoid(self.linear(x)) 
        return x

model = Model()

Linear Layer：

完整代码：

1. 准备数据集

import numpy as np

xy = np.loadtxt('diabetes.csv.gz', delimiter=',', dtype=np.float32) 
x_data = torch.from_numpy(xy[:,:-1])
y_data = torch.from_numpy(xy[:, [-1]])

 2. 定义模型

import torch

class Model(torch.nn.Module): 
    def __init__(self):
        super(Model, self).__init__() 
        self.linear1 = torch.nn.Linear(8, 6) 
        self.linear2 = torch.nn.Linear(6, 4) 
        self.linear3 = torch.nn.Linear(4, 1) 
        self.sigmoid = torch.nn.Sigmoid()
    def forward(self, x):
        x = self.sigmoid(self.linear1(x)) 
        x = self.sigmoid(self.linear2(x)) 
        x = self.sigmoid(self.linear3(x)) 
        return x

model = Model()

3. Loss and Optimizer

criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

4. Training Cycle

for epoch in range(100): 
    # Forward
    y_pred = model(x_data)
    loss = criterion(y_pred, y_data)
    print(epoch, loss.item())

    # Backward
    optimizer.zero_grad()
    loss.backward()

    # Update
    optimizer.step()

补充：尝试不同的激活函数

import torch

class Model(torch.nn.Module): 
    def __init__(self):
        super(Model, self).__init__() 
        self.linear1 = torch.nn.Linear(8, 6) 
        self.linear2 = torch.nn.Linear(6, 4) 
        self.linear3 = torch.nn.Linear(4, 1) 
        self.activate = torch.nn.ReLU()
    def forward(self, x):
        x = self.activate(self.linear1(x)) 
        x = self.activate(self.linear2(x)) 
        x = self.activate(self.linear3(x)) return x

model = Model()