多分类问题Softmax分类器

 

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
import torch.optim as optim

batch_size=64
transform=transforms.Compose([
    transforms.ToTensor(),  #把PIL图像转化为Tensor,W*H*C->C*W*H
    transforms.Normalize((0.1307,),(0.3081,))   #第一个是均值，第二个是标准差，针对MNIST
])

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

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)
        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()
optimizer=optim.SGD(model.parameters(),lr=0.01,momentum=0.5)

def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        optimizer.zero_grad()

        #forward+backward+update
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_idx%100==99:
            print('[%d,%5d]loss:%.3f'%(epoch+1,batch_idx+1,running_loss/100))
            running_loss=0.0

def test():
    correct=0
    total=0
    with torch.no_grad():   #不计算梯度
        for data in test_loader:    #test_loader中按batch把数据分开
            images,labels=data
            outputs=model(images)
            _,predicted=torch.max(outputs.data,dim=1)
            total+=labels.size(0)
            #print('labels=',labels)
            correct+=(predicted==labels).sum().item()
    print('Accuracy on test set:%d %%'%(100*correct/total))

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