多分类问题

一、使用softmax分类器进行分类

分布上的性质要求 1.所有结果的概率都大于0；
2.所有结果的概率之和等于1。
普通的sigmoid函数一般不用于解决多分类的问题
因此使用softmax函数来满足其性质

import numpy as np
y=np.array([1,0,0])
z=np.array([0.2,0.1,-0.1])
y_pred=np.exp(z)/np.exp(z).sum()
loss=(-y*np.log(y_pred)).sum()
print(loss)

import torch
criterion=torch.nn.CrossEntropyLoss()
y=torch.LongTensor([2,0,1])
y_pred1=torch.Tensor([[0.1,0.2,0.9],
                   [1.1,0.1,0.2],
                   [0.2,2.1,0.1]])
y_pred2=torch.Tensor([[0.8,0.2,0.3],
                    [0.2,0.3,0.5],
                    [0.2,0.2,0.5]])
l1=criterion(y_pred1,y)
l2=criterion(y_pred2,y)
print("Batch Loss1=",l1.data,"\nBatch Loss2=",l2.data)

minist数据集做多分类

import torch
from torchvision import transforms  # 对数据集做图像处理
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim  # 优化器

# Totensor 转变成c、h、w张量
# Tensor转换成w,h,c张量
batch_size = 64
transforms = transforms.Compose([transforms.ToTensor(),
                                 transforms.Normalize((0.1307,), (0.3081,))])
# Normalize第一个参数是均值、第二个参数是标准差

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               download=True,
                               transform=transforms)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              download=True,
                              transform=transforms)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)


def forward(self, x):
    x = x.view(-1, 784)  # 将其
    x = F.relu(self.l1(x))
    x = F.relu(self.l2(x))
    x = F.relu(self.l3(x))
    x = F.relu(self.l4(x))
    return self.l5(x)


model = Net()

criterion = torch.nn.CrossEntropyLoss()  # 损失函数
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)  # 带冲量的优化器


def train(epoch):
    running_loss = 0.0
    for batch_idex, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()  # 优化器清零
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()  # 反馈
        optimizer.step()

        running_loss += loss.item()
        if batch_idex % 300 == 299:
            print('[%d,%5d] loss: %0.3f' % (epoch + 1, batch_idex + 1, running_loss / 300))
            running_loss = 0.0


def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            print('accuracy on test sst :%d %%' % (100 * correct / total))


if __name__ == 'main':
    for epoch in range(10):
        train(epoch)
        test()