一、
1、逻辑斯蒂函数,使结果映射到(0,1)之间
2、sigmoid函数:函数值有极限,单调增函数,是饱和函数(导数图像两端趋于0,中间像正态分布)。最常见的sigmoid函数是逻辑斯蒂函数
3、逻辑斯蒂回归和线性模型的明显区别是在线性模型的后面,添加了激活函数(非线性变换)
分布的差异:KL散度,cross-entropy交叉熵
4、预测与标签越接近,BCE损失越小。
5、代码F.sigmoid(self.linear(x))会引发warning,此处更改为torch.sigmoid(self.linear(x))
BCELoss 是CrossEntropyLoss的一个特例,只用于二分类问题,而CrossEntropyLoss可以用于二分类,也可以用于多分类。
如果是二分类问题,建议BCELoss
import torch
# import torch.nn.functional as F
# prepare dataset
x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])
# design model 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))
y_pred = torch.sigmoid(self.linear(x))
return y_pred
model = LogisticRegressionModel()
# construct loss and optimizer
# 默认情况下,loss会基于element平均,如果size_average=False的话,loss会被累加。
criterion = torch.nn.BCELoss(size_average=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# training cycle forward, backward, update
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()
print('w = ', model.linear.weight.item())
print('b = ', model.linear.bias.item())
x_test = torch.Tensor([[4.0]])
y_test = model(x_test)
print('y_pred = ', y_test.data)
训练1万次结果: