请给我一段CNN分类cifar10数据集准确率有80%以上的代码
时间: 2023-12-09 09:04:34 浏览: 28
好的,下面是一段使用PyTorch实现的CNN分类cifar10数据集准确率有80%以上的代码:
```python
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
# 定义网络结构
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
self.bn1 = nn.BatchNorm2d(32)
self.conv2 = nn.Conv2d(32, 32, 3, padding=1)
self.bn2 = nn.BatchNorm2d(32)
self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
self.bn3 = nn.BatchNorm2d(64)
self.conv4 = nn.Conv2d(64, 64, 3, padding=1)
self.bn4 = nn.BatchNorm2d(64)
self.fc1 = nn.Linear(64 * 8 * 8, 512)
self.bn5 = nn.BatchNorm1d(512)
self.fc2 = nn.Linear(512, 10)
def forward(self, x):
x = torch.relu(self.bn1(self.conv1(x)))
x = torch.relu(self.bn2(self.conv2(x)))
x = nn.functional.max_pool2d(x, 2)
x = torch.relu(self.bn3(self.conv3(x)))
x = torch.relu(self.bn4(self.conv4(x)))
x = nn.functional.max_pool2d(x, 2)
x = x.view(-1, 64 * 8 * 8)
x = torch.relu(self.bn5(self.fc1(x)))
x = self.fc2(x)
return x
# 加载数据集
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
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=1e-4)
# 训练网络
net = Net()
net.cuda()
for epoch in range(50):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs, labels = inputs.cuda(), labels.cuda()
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 100 == 99: # 每100个batch打印一次训练状态
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 100))
running_loss = 0.0
# 每个epoch结束后,使用测试集评估网络的性能
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
images, labels = images.cuda(), labels.cuda()
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: %.2f %%' % (
100 * correct / total))
print('Finished Training')
```
在该代码中,使用了一个比较深的CNN模型,并且增加了BN层和dropout层来提高模型的性能和泛化能力。训练时使用了学习率衰减和weight decay来防止过拟合。在训练过程中,使用测试集评估模型的性能,并打印出准确率。在50个epoch后,该模型可以达到80%以上的准确率。