0012-pytorch-入门图片分类脚本

╰+攻爆jí腚メ 2022-11-19 11:16 23阅读 0赞

# 数据获取
    pytorch提供了torchvision包封装了常见数据集的数据加载函数，除此之外，它还提供了torchvision.datasets和torch.utils.data.Dataloader实现图像数据转换功能
    
    #加载并处理数据
    import torch
    import torchvision
    import torchvision.transforms as transforms
    
    transform = transforms.Compose(
        [transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    
    
    trainset = torchvision.datasets.CIFAR10("D:\PycharmProjects\learning\pytorch_handbook\data\cifar-10-batches-py",train=True,download=True,transform=transforms)
    
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
    
    testset = torchvision.datasets.CIFAR10(root='D:\PycharmProjects\learning\pytorch_handbook\data\cifar-10-batches-py',
                                           train=False,
                                           download=True, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                             shuffle=False, num_workers=2)
    
    classes = ('plane', 'car', 'bird', 'cat',
               'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
    
    
    #输出图片看看
    import matplotlib.pyplot as plt
    import numpy as np
    
    def imshow(img):
        img = img/2+0.5
        img = img.numpy()
        plt.imshow(np.transpose(img,(1,2,0)))
    
    #获取训练数据
    dataiter = iter(trainloader)
    images,labels = dataiter.next()
    
    #展示图片
    imshow(torchvision.utils.make_grid(images))
    
    from torch.autograd import Variable
    import torch.nn as nn
    import torch.nn.functional as F
    
    
    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool = nn.MaxPool2d(2, 2)
            self.conv2 = nn.Conv2d(6, 16, 5)
            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 x
    
    
    net = Net()
    
    # 定义损失函数和优化器
    import torch.optim as optim
    
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
    
    # 训练神经网络
    for epoch in range(2):  #
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
            inputs, labels = Variable(inputs), Variable(labels)
    
            # zero the parameter gradients
            optimizer.zero_grad()
            # 前项传播+后向传播+优化函数
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            # 统计函数
            running_loss += loss.data[0]
            if i % 2000 == 1999:
                print('[%d, %5d] loss: %.3f' %
                      (epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0
    
    
    #用测试数据进行测试
    dataiter = iter(testloader)
    images,labels = dataiter.next()
    #打印图片
    imshow(torchvision.utils.make_grid(images))
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    outputs = net(Variable(images))
    
    #transform from score to label
    _,predicted = torch.max(outputs.data,1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                                  for j in range(4)))
    
    
    #整个测试集
    correct = 0
    total = 0
    for data in testloader:
        images,labels = data
        outputs = net(Variable(images))
        _,predicted = torch.max(outputs.data,1)
        total += labels.size()
        correct += (predicted==labels).sum()
    
    print('Accuracy of the network on the 10000 test images: %d %%' % (
        100 * correct / total))
    
    
    
    #输出每个类别的准确率
    class_correct = list(0. for i in range(10))
    class_total = list(0. for i in range(10))
    for data in testloader:
        images, labels = data
        outputs = net(Variable(images))
        _, predicted = torch.max(outputs.data, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i]
            class_total[label] += 1
    
    
    for i in range(10):
        print('Accuracy of %5s : %2d %%' % (
            classes[i], 100 * class_correct[i] / class_total[i]))