PyTorch实现AlexNet示例

以下是PyTorch实现AlexNet示例的完整攻略，包括两个示例说明。

1. 下载数据集

1. 下载数据集

在ImageNet官网下载ImageNet数据集。

1. 解压数据集

将下载的数据集解压到本地文件夹中。

2. 示例1：使用PyTorch实现AlexNet

以下是使用PyTorch实现AlexNet的步骤：

1. 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. 定义数据预处理

python
transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])])

1. 加载数据集

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

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

1. 定义AlexNet模型

```python
class AlexNet(nn.Module):
def init(self, num_classes=1000):
super(AlexNet, self).init()
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(64, 192, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(192, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
self.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, num_classes),
)

   def forward(self, x):
       x = self.features(x)
       x = self.avgpool(x)
       x = torch.flatten(x, 1)
       x = self.classifier(x)
       return x

```

1. 定义损失函数和优化器

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

1. 训练模型

```python
for epoch in range(10):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 2000 == 1999:
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0

print('Finished Training')
```

1. 测试模型

```python
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))
```

3. 示例2：使用预训练的AlexNet进行迁移学习

以下是使用预训练的AlexNet进行迁移学习的步骤：

1. 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. 定义数据预处理

python
transform = transforms.Compose(
[transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])])

1. 加载数据集

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

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

1. 加载预训练的AlexNet模型

python
net = torchvision.models.alexnet(pretrained=True)

1. 冻结AlexNet的前几层

python
for param in net.parameters():
param.requires_grad = False

1. 修改AlexNet的最后一层

python
num_ftrs = net.classifier[6].in_features
net.classifier[6] = nn.Linear(num_ftrs, 2)

1. 定义损失函数和优化器

python
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.classifier[6].parameters(), lr=0.001, momentum=0.9)

1. 训练模型

```python
for epoch in range(10):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 2000 == 1999:
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0

print('Finished Training')
```

1. 测试模型

```python
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))
```

以上就是PyTorch实现AlexNet示例的完整攻略，包括两个示例说明。