利用pytorch实现对CIFAR-10数据集的分类

下面是关于“利用pytorch实现对CIFAR-10数据集的分类”的完整攻略。

问题描述

CIFAR-10是一个常用的图像分类数据集，其中包含10个类别的60000张32x32彩色图像。那么，如何使用pytorch实现对CIFAR-10数据集的分类？

解决方法

示例1：使用CNN实现CIFAR-10数据集的分类

以下是使用CNN实现CIFAR-10数据集的分类的示例：

1. 首先，导入必要的库：

python
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

1. 然后，加载CIFAR-10数据集：

```python
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
shuffle=False, num_workers=2)
```

1. 接着，定义CNN模型：

```python
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()
```

1. 然后，定义损失函数和优化器：

python
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

1. 接着，进行训练和测试：

```python
for epoch in range(2): # loop over the dataset multiple times

   running_loss = 0.0
   for i, data in enumerate(trainloader, 0):
       # get the inputs; data is a list of [inputs, labels]
       inputs, labels = data

       # zero the parameter gradients
       optimizer.zero_grad()

       # forward + backward + optimize
       outputs = net(inputs)
       loss = criterion(outputs, labels)
       loss.backward()
       optimizer.step()

       # print statistics
       running_loss += loss.item()
       if i % 2000 == 1999:    # print every 2000 mini-batches
           print('[%d, %5d] loss: %.3f' %
                 (epoch + 1, i + 1, running_loss / 2000))
           running_loss = 0.0

print('Finished Training')

correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
```

在上面的示例中，我们使用了CNN实现CIFAR-10数据集的分类。首先，我们导入必要的库，并加载CIFAR-10数据集。然后，我们定义CNN模型，并定义损失函数和优化器。接着，我们进行训练和测试，并输出模型的准确率。

示例2：使用ResNet实现CIFAR-10数据集的分类

以下是使用ResNet实现CIFAR-10数据集的分类的示例：

1. 首先，导入必要的库：

python
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import torch.nn.functional as F

1. 然后，加载CIFAR-10数据集：

```python
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128,
shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100,
shuffle=False, num_workers=2)
```

1. 接着，定义ResNet模型：

```python
class BasicBlock(nn.Module):
expansion = 1

   def __init__(self, in_planes, planes, stride=1):
       super(BasicBlock, self).__init__()
       self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
       self.bn1 = nn.BatchNorm2d(planes)
       self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
       self.bn2 = nn.BatchNorm2d(planes)

       self.shortcut = nn.Sequential()
       if stride != 1 or in_planes != self.expansion*planes:
           self.shortcut = nn.Sequential(
               nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
               nn.BatchNorm2d(self.expansion*planes)
           )

   def forward(self, x):
       out = F.relu(self.bn1(self.conv1(x)))
       out = self.bn2(self.conv2(out))
       out += self.shortcut(x)
       out = F.relu(out)
       return out

class ResNet(nn.Module):
def init(self, block, num_blocks, num_classes=10):
super(ResNet, self).init()
self.in_planes = 64

       self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
       self.bn1 = nn.BatchNorm2d(64)
       self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
       self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
       self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
       self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
       self.linear = nn.Linear(512*block.expansion, num_classes)

   def _make_layer(self, block, planes, num_blocks, stride):
       strides = [stride] + [1]*(num_blocks-1)
       layers = []
       for stride in strides:
           layers.append(block(self.in_planes, planes, stride))
           self.in_planes = planes * block.expansion
       return nn.Sequential(*layers)

   def forward(self, x):
       out = F.relu(self.bn1(self.conv1(x)))
       out = self.layer1(out)
       out = self.layer2(out)
       out = self.layer3(out)
       out = self.layer4(out)
       out = F.avg_pool2d(out, 4)
       out = out.view(out.size(0), -1)
       out = self.linear(out)
       return out

def ResNet18():
return ResNet(BasicBlock, [2,2,2,2])
```

1. 然后，定义损失函数和优化器：

python
net = ResNet18()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=5e-4)
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[150, 250], gamma=0.1)

1. 接着，进行训练和测试：

```python
for epoch in range(350):
net.train()
train_loss = 0
correct = 0
total = 0
for batch_idx, (inputs, targets) in enumerate(trainloader):
inputs, targets = inputs.to(device), targets.to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()

       train_loss += loss.item()
       _, predicted = outputs.max(1)
       total += targets.size(0)
       correct += predicted.eq(targets).sum().item()

   scheduler.step()

   net.eval()
   test_loss = 0
   correct = 0
   total = 0
   with torch.no_grad():
       for batch_idx, (inputs, targets) in enumerate(testloader):
           inputs, targets = inputs.to(device), targets.to(device)
           outputs = net(inputs)
           loss = criterion(outputs, targets)

           test_loss += loss.item()
           _, predicted = outputs.max(1)
           total += targets.size(0)
           correct += predicted.eq(targets).sum().item()

   print('Epoch: %d | Train Loss: %.3f | Test Loss: %.3f | Test Acc: %.3f%% (%d/%d)'
         % (epoch+1, train_loss/(batch_idx+1), test_loss/(batch_idx+1), 100.*correct/total, correct, total))

```

在上面的示例中，我们使用了ResNet实现CIFAR-10数据集的分类。首先，我们导入必要的库，并加载CIFAR-10数据集。然后，我们定义ResNet模型，并定义损失函数和优化器。接着，我们进行训练和测试，并输出模型的准确率。

结论

在本攻略中，我们介绍了使用pytorch实现对CIFAR-10数据集的分类的两种方法，并提供了示例说明。可以根据具体的需求来选择不同的方法，并根据需要调整模型、数据集和训练的参数。