目录

• 分类器任务和数据介绍
• 训练分类器的步骤
• 在GPU上训练模型

分类器任务和数据介绍

训练分类器的步骤

#1import torchimport torchvisionimport torchvision.transforms as transformstransform=transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))]) #三个部分的数据的均值，标准差都为0.5trainset=torchvision.datasets.CIFAR10(root='./data1',train=True,download=True,transform=transform)trainloader=torch.utils.data.DataLoader(trainset,batch_size=4,shuffle=True)testset=torchvision.datasets.CIFAR10(root='./data1',train=False,download=True,transform=transform)testloader=torch.utils.data.DataLoader(testset,batch_size=4,shuffle=True)classes=('plane','car','bird','cat','deer','dog','frog','horse','ship','truck')

展示若干训练集图片

#2import torch.nn as nnimport torch.nn.functional as Fclass Net(nn.Module):def __init__(self):super(Net,self).__init__()self.conv1=nn.Conv2d(3,6,5)self.conv2=nn.Conv2d(6,16,5)self.pool=nn.MaxPool2d(2,2)self.fc1=nn.Linear(16*5*5,120)self.fc2=nn.Linear(120,84)self.fc3=nn.Linear(84,10)def forward(self,x):x=self.pool(F.relu(self.conv1(x)))x=self.pool(F.relu(self.conv2(x)))x=x.view(-1,16*5*5)x=F.relu(self.fc1(x))x=F.relu(self.fc2(x))x=self.fc3(x)return xnet=Net()print(net)

#3import torch.optim as optimcriterion=nn.CrossEntropyLoss()optimizer=optim.SGD(net.parameters(),lr=0.001,momentum=0.9)

#4for epoch in range(2):running_loss=0.0#按批次迭代训练模型for i,data in enumerate(trainloader,0):inputs,labels=dataoptimizer.zero_grad()outputs=net(inputs)loss=criterion(outputs,labels)loss.backward()optimizer.step()#打印训练信息running_loss+=loss.item()if (i+1)%2000==0:print('[%d,%5d] loss:%.3f'%(epoch+1,i+1,running_loss/2000))running_loss=0print('finished training')#设定模型保存位置PATH='./cifar_net.pth'#保存模型的状态字典torch.save(net.state_dict(),PATH)

#5dataiter=iter(testloader)images,labels=next(dataiter)print('groundtrue:',' '.join('%5s'%classes[labels[j]] for j in range(4)))#加载模型参数，在测试阶段net.load_state_dict(torch.load(PATH))#利用模型对图片进行预测outputs=net(images)_,predicted=torch.max(outputs,1)print('predicted:',''.join('%5s'%classes[predicted[j]] for j in range(4)))

#5#在整个测试集上测试模型准确率correct=0total=0with torch.no_grad():for data in testloader:images,labels=dataoutputs=net(images)_,predicted=torch.max(outputs.data,1) #_是最大值，predicted是最大值下标total+=labels.size(0)correct+=(predicted==labels).sum().item()print('accuracy of the network on the 10000 test images:%d %%'%(100*correct/total))

注

分别测试不同类别的模型准确率

在GPU上训练模型