Softmax解决离散值回归问题(分类问题)[pytorch]
文章目录
一、理论知识
1、线性回归与softmax回归的区别:
- 线性回归:一对一
- softmax回归:一对多
- softmax回归的输出层也是一个全连接层
2、根据输入特征维度和输出维度可以确定权重的维度
3、softmax运算符主要解决两个问题:
- 输出层的输出值的范围不确定,难以直观判断这些值背后的意义
- 真实值是离散值,离散值与不确定范围之间的误差难以衡量
y ^ 1 , y ^ 2 , y ^ 3 = softmax ( o 1 , o 2 , o 3 ) \hat{y}_1, \hat{y}_2, \hat{y}_3 = \text{softmax}(o_1, o_2, o_3)y^1,y^2,y^3=softmax(o1,o2,o3)
其中
y ^ 1 = exp ( o 1 ) ∑ i = 1 3 exp ( o i ) , y ^ 2 = exp ( o 2 ) ∑ i = 1 3 exp ( o i ) , y ^ 3 = exp ( o 3 ) ∑ i = 1 3 exp ( o i ) . \hat{y}1 = \frac{ \exp(o_1)}{\sum_{i=1}^3 \exp(o_i)},\quad \hat{y}2 = \frac{ \exp(o_2)}{\sum_{i=1}^3 \exp(o_i)},\quad \hat{y}3 = \frac{ \exp(o_3)}{\sum_{i=1}^3 \exp(o_i)}.y^1=∑i=13exp(oi)exp(o1),y^2=∑i=13exp(oi)exp(o2),y^3=∑i=13exp(oi)exp(o3).
**Note:**为什么要用指数???
解决概率为负数的情况以及容易求导
softmax回归对样本i ii分类的矢量计算表达式为
o ( i ) = x ( i ) W + b , y ^ ( i ) = softmax ( o ( i ) ) . \begin{aligned} \boldsymbol{o}^{(i)} &= \boldsymbol{x}^{(i)} \boldsymbol{W} + \boldsymbol{b},\\ \boldsymbol{\hat{y}}^{(i)} &= \text{softmax}(\boldsymbol{o}^{(i)}). \end{aligned}o(i)y^(i)=x(i)W+b,=softmax(o(i)).
4、使用线性回归的损失函数不能很好地反映预测准确值的好坏,所以离散值的回归问题中使用交叉熵来衡量。
H ( y ( i ) , y ^ ( i ) ) = − ∑ j = 1 q y j ( i ) log y ^ j ( i ) , H\left(\boldsymbol y^{(i)}, \boldsymbol {\hat y}^{(i)}\right ) = -\sum_{j=1}^q y_j^{(i)} \log \hat y_j^{(i)},H(y(i),y^(i))=−j=1∑qyj(i)logy^j(i),
交叉熵的损失函数定义为:
ℓ ( Θ ) = 1 n ∑ i = 1 n H ( y ( i ) , y ^ ( i ) ) , \ell(\boldsymbol{\Theta}) = \frac{1}{n} \sum_{i=1}^n H\left(\boldsymbol y^{(i)}, \boldsymbol {\hat y}^{(i)}\right ),ℓ(Θ)=n1i=1∑nH(y(i),y^(i)),
最小化交叉熵损失函数等价于最大化训练数据集所有标签类别的联合预测概率
5、模型的预测和评价:在多分类问题中,那个预测的概率大即可确定标签为那个
准确率:为预测正确的个数/总数
6、交叉熵函数与极大似然估计的区别??????
二、代码实现(基于Fashion-MNIST数据集)
1、加载显示数据集
1. torchvision.datasets: 一些加载数据的函数及常用的数据集接口;
2. torchvision.models: 包含常用的模型结构(含预训练模型),例如AlexNet、VGG、ResNet等;
3. torchvision.transforms: 常用的图片变换,例如裁剪、旋转等;
4. torchvision.utils: 其他的一些有用的方法。
# import needed package
###读取数据 显示数据 小批量处理,计算读取数据所用的时间
%matplotlib inline
from IPython import display
import matplotlib.pyplot as plt
import torch
import torchvision 构建计算机视觉模型
import torchvision.transforms as transforms
import time
import sys
sys.path.append("/home/kesci/input")
#import d2lzh1981 as d2l
print(torch.__version__)
print(torchvision.__version__)
mnist_train = torchvision.datasets.FashionMNIST(root='/home/kesci/input/FashionMNIST2065', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='/home/kesci/input/FashionMNIST2065', train=False, download=True, transform=transforms.ToTensor())
# show result
print(type(mnist_train))
print(len(mnist_train), len(mnist_test)) #60000 for training 10000 for test
feature, label = mnist_train[100]
print(feature.shape, label) # Channel x Height x Width
#打印通道数、图像的高度和宽度 以及标签
mnist_PIL = torchvision.datasets.FashionMNIST(root='/home/kesci/input/FashionMNIST2065', train=True, download=True)
PIL_feature, label = mnist_PIL[0]
print(PIL_feature)
# 本函数已保存在d2lzh包中方便以后使用
#labels应输入字符
def get_fashion_mnist_labels(labels):
text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
return [text_labels[int(i)] for i in labels]
#画图显示
def show_fashion_mnist(images, labels):
d2l.use_svg_display() #用矢量图显示
# 这里的_表示我们忽略(不使用)的变量
_, figs = plt.subplots(1, len(images), figsize=(12, 12)) #figsize:输出图像的大小
for f, img, lbl in zip(figs, images, labels):
f.imshow(img.view((28, 28)).numpy())
f.set_title(lbl) #设置标题
f.axes.get_xaxis().set_visible(False) #设置x轴尺度是否可见
f.axes.get_yaxis().set_visible(False) #设置y轴尺度是否可见
plt.show() #画图
X, y = [], []
for i in range(10):
X.append(mnist_train[i][0]) # 将第i个feature加到X中
y.append(mnist_train[i][1]) # 将第i个label加到y中
show_fashion_mnist(X, get_fashion_mnist_labels(y))
# 读取数据
batch_size = 256
num_workers = 4
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
start = time.time()
for X, y in train_iter:
continue
print('%.2f sec' % (time.time() - start))
print(y)
class torchvision.datasets.FashionMNIST(root, train=True, transform=None, target_transform=None, download=False)
- root(string)– 数据集的根目录,其中存放processed/training.pt和processed/test.pt文件。
- train(bool, 可选)– 如果设置为True,从training.pt创建数据集,否则从test.pt创建。
- download(bool, 可选)– 如果设置为True,从互联网下载数据并放到root文件夹下。如果root目录下已经存在数据,不会再次下载。
- transform(可被调用 , 可选)– 一种函数或变换,输入PIL图片,返回变换之后的数据。如:transforms.RandomCrop。
- target_transform(可被调用 , 可选)– 一种函数或变换,输入目标,进行变换。
torch.utils.data.DataLoader(
dataset,#数据加载
batch_size = 1,#批处理大小设置
shuffle = False,#是否进项洗牌操作
sampler = None,#指定数据加载中使用的索引/键的序列
batch_sampler = None,#和sampler类似
num_workers = 0,#是否进行多进程加载数据设置
collate_fn = None,#是否合并样本列表以形成一小批Tensor
pin_memory = False,#如果True,数据加载器会在返回之前将Tensors复制到CUDA固定内存
drop_last = False,#True如果数据集大小不能被批处理大小整除,则设置为删除最后一个不完整的批处理。
timeout = 0,#如果为正,则为从工作人员收集批处理的超时值
worker_init_fn = None )
2、softmax从零开始的实现
import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
print(torchvision.__version__)
#分批加载数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')
num_inputs = 784 #输入特征
print(28*28)
num_outputs = 10 #输出标签
#模型参数初始化
W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float) #权重
b = torch.zeros(num_outputs, dtype=torch.float) #偏置
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
#对多维Tensor按维度操作
X = torch.tensor([[1, 2, 3], [4, 5, 6]])
print(X.sum(dim=0, keepdim=True)) # dim为0,按照相同的列求和,并在结果中保留列特征
print(X.sum(dim=1, keepdim=True)) # dim为1,按照相同的行求和,并在结果中保留行特征
print(X.sum(dim=0, keepdim=False)) # dim为0,按照相同的列求和,不在结果中保留列特征
print(X.sum(dim=1, keepdim=False)) # dim为1,按照相同的行求和,不在结果中保留行特征
#定义softmax操作
def softmax(X):
X_exp = X.exp()
partition = X_exp.sum(dim=1, keepdim=True)
# print("X size is ", X_exp.size())
# print("partition size is ", partition, partition.size())
return X_exp / partition # 这里应用了广播机制
X = torch.rand((2, 5))
print(X)
X_prob = softmax(X)
print(X_prob, '\n', X_prob.sum(dim=1))
def net(X):
return softmax(torch.mm(X.view((-1, num_inputs)), W) + b) #mm需要保证两个矩阵可以相乘,mul需要保证两个矩阵维度一一致,对应项相乘
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y = torch.LongTensor([0, 2])
print(y)
y_hat.gather(1,y.view(-1, 1))
#gather函数详解
#b = torch.Tensor([[1,2,3],[4,5,6]])
#index_1 = torch.LongTensor([[0,1],[2,0]])
#index_2 = torch.LongTensor([[0,1,1],[0,0,0]])
#print torch.gather(b, dim=1, index=index_1)
#print torch.gather(b, dim=0, index=index_2)
### dim=1表示横向,index表示索引,对列操作,输出矩阵的维度与index矩阵的维度一致
### dim=0与此相反
###交叉损失
def cross_entropy(y_hat, y):
return - torch.log(y_hat.gather(1, y.view(-1, 1)))
#准确率
def accuracy(y_hat, y):
return (y_hat.argmax(dim=1) == y).float().mean().item()
# 本函数已保存在d2lzh_pytorch包中方便以后使用。该函数将被逐步改进:它的完整实现将在“图像增广”一节中描述
def evaluate_accuracy(data_iter, net):
acc_sum, n = 0.0, 0
for X, y in data_iter:
acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
n += y.shape[0]
return acc_sum / n
###训练模型
num_epochs, lr = 5, 0.1
# 本函数已保存在d2lzh_pytorch包中方便以后使用
###神经网络,训练集,测试集,损失函数, 批量大小,权重,偏置,学习率
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
d2l.sgd(params, lr, batch_size)
else:
optimizer.step()
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)
###模型预测
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
3、softmax的简单实现(把一些模块进行了封装)
具体步骤:
- 读取数据集
- 初始化模型参数
- 定义损失函数
- 定义优化函数
- 训练
- 测试(正确率的评估)
# 加载各种包或者模块
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
#初始化参数和读取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065') #调取d2l中读取数据模块
num_inputs = 784
num_outputs = 10
#定义类
class LinearNet(nn.Module):
def __init__(self, num_inputs, num_outputs):
super(LinearNet, self).__init__()
self.linear = nn.Linear(num_inputs, num_outputs)
def forward(self, x): # x 的形状: (batch, 1, 28, 28)
y = self.linear(x.view(x.shape[0], -1))
return y
# net = LinearNet(num_inputs, num_outputs)
class FlattenLayer(nn.Module):
def __init__(self):
super(FlattenLayer, self).__init__()
def forward(self, x): # x 的形状: (batch, *, *, ...)
return x.view(x.shape[0], -1)
from collections import OrderedDict
net = nn.Sequential(
# FlattenLayer(),
# LinearNet(num_inputs, num_outputs)
OrderedDict([
('flatten', FlattenLayer()),
('linear', nn.Linear(num_inputs, num_outputs))]) # 或者写成我们自己定义的 LinearNet(num_inputs, num_outputs) 也可以
)
#初始化模型参数
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)
#损失函数
loss = nn.CrossEntropyLoss() # 下面是他的函数原型
# class torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')
#优化函数
optimizer = torch.optim.SGD(net.parameters(), lr=0.1) # 下面是函数原型
# class torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)
num_epochs = 5 #训练周期
#开始训练
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)