googlenet图像分类cifar-10代码
时间: 2024-03-25 13:37:00 浏览: 176
基于 Pytorch GoogLeNet 的图像分类实战 完整代码 数据 可直接运行 CIFAR-10分类
以下是使用GoogleNet进行CIFAR-10图像分类的代码(使用PyTorch实现):
```python
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
# 定义GoogleNet模型
class GoogLeNet(nn.Module):
def __init__(self):
super(GoogLeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1)
self.conv2 = nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1)
self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(p=0.4)
self.fc1 = nn.Linear(1024, 10)
def forward(self, x):
x = nn.functional.relu(self.conv1(x))
x = nn.functional.max_pool2d(x, kernel_size=3, stride=2, padding=1)
x = nn.functional.relu(self.conv2(x))
x = nn.functional.max_pool2d(x, kernel_size=3, stride=2, padding=1)
x = self.inception3a(x)
x = self.inception3b(x)
x = nn.functional.max_pool2d(x, kernel_size=3, stride=2, padding=1)
x = self.inception4a(x)
x = self.inception4b(x)
x = self.inception4c(x)
x = self.inception4d(x)
x = self.inception4e(x)
x = nn.functional.max_pool2d(x, kernel_size=3, stride=2, padding=1)
x = self.inception5a(x)
x = self.inception5b(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.dropout(x)
x = self.fc1(x)
return x
# 定义Inception模块
class Inception(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(Inception, self).__init__()
# 1x1卷积层
self.branch1 = nn.Sequential(
nn.Conv2d(in_channels, ch1x1, kernel_size=1),
nn.BatchNorm2d(ch1x1),
nn.ReLU(inplace=True)
)
# 1x1卷积层 + 3x3卷积层
self.branch2 = nn.Sequential(
nn.Conv2d(in_channels, ch3x3red, kernel_size=1),
nn.BatchNorm2d(ch3x3red),
nn.ReLU(inplace=True),
nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),
nn.BatchNorm2d(ch3x3),
nn.ReLU(inplace=True)
)
# 1x1卷积层 + 5x5卷积层
self.branch3 = nn.Sequential(
nn.Conv2d(in_channels, ch5x5red, kernel_size=1),
nn.BatchNorm2d(ch5x5red),
nn.ReLU(inplace=True),
nn.Conv2d(ch5x5red, ch5x5, kernel_size=5, padding=2),
nn.BatchNorm2d(ch5x5),
nn.ReLU(inplace=True)
)
# 3x3最大池化层 + 1x1卷积层
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
nn.Conv2d(in_channels, pool_proj, kernel_size=1),
nn.BatchNorm2d(pool_proj),
nn.ReLU(inplace=True)
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
outputs = [branch1, branch2, branch3, branch4]
return torch.cat(outputs, 1)
# 导入数据集并进行预处理
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=128, shuffle=False, num_workers=2)
# 定义损失函数和优化器
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net = GoogLeNet().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=5e-4)
# 训练模型
for epoch in range(200):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data[0].to(device), data[1].to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 100 == 99:
print('[%d, %5d] loss: %.3f' % (epoch+1, i+1, running_loss/100))
running_loss = 0.0
# 在测试集上测试模型
correct, total = 0, 0
with torch.no_grad():
for data in testloader:
images, labels = data[0].to(device), data[1].to(device)
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))
print('Finished Training')
```
注意:该代码可能需要在GPU上运行,因为GoogleNet比较深,计算量较大。如果没有GPU,可能需要更长的训练时间。
阅读全文