pytorch深度学习实践-逻辑斯蒂回归0104

目录

1、使用简单的逻辑斯蒂回归

2、代码绘图报错解决

---

1、使用简单的逻辑斯蒂回归

import torch
import torch.nn.functional as F

        准备数据：

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0.0], [0.0], [1.0]])

        定义模型：

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()

        构建损失和优化器：

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

        训练：

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()

        输出w和b：

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

        预测4.0时数据：

x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_test = ', y_test.data)

2、代码绘图报错解决

        参照原代码为：

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], [0.0], [1.0]])

# design module using class
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()

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

# 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()
x = np.linspace(0.0, 10.0, 200)
print(x)
x_t = torch.Tensor(x).view((200, 1))
print('   ')
y_t = model(x_t)
y = y_t.data
print(y)

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()

        运行后报错：

        解决方法：

将y = y_t.data.numpy 改为 y = y_t.data

        得到结果图：

         为什么呢？我百思不得其解，网上也找不到答案。但是今天太晚了，前面的知识以后再来探索吧！