使用PyTorch采用深度学习的方法写图像识别代码
时间: 2024-01-31 14:02:47 浏览: 27
好的,以下是一个使用 PyTorch 实现图像分类的示例代码,包括数据准备、模型构建、模型训练和模型评估等部分。
```python
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
# 数据准备
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)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
# 模型构建
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 64, 3, padding=1)
self.conv2 = nn.Conv2d(64, 128, 3, padding=1)
self.conv3 = nn.Conv2d(128, 256, 3, padding=1)
self.pool = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(256 * 4 * 4, 512)
self.fc2 = nn.Linear(512, 10)
def forward(self, x):
x = F.relu(self.conv1(x))
x = self.pool(F.relu(self.conv2(x)))
x = self.pool(F.relu(self.conv3(x)))
x = x.view(-1, 256 * 4 * 4)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return x
net = Net()
# 模型训练
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
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 % 100 == 99:
print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
running_loss = 0.0
# 模型评估
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))
```
这个示例代码使用了 CIFAR-10 数据集,使用了一个包含三个卷积层和两个全连接层的卷积神经网络进行图像分类,训练了10个epoch,最终在测试集上达到了较高的准确率。您可以根据自己的需求进行修改和优化。
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![-](https://csdnimg.cn/download_wenku/file_type_lunwen.png)
![-](https://csdnimg.cn/download_wenku/file_type_lunwen.png)
![-](https://csdnimg.cn/download_wenku/file_type_lunwen.png)
![-](https://csdnimg.cn/download_wenku/file_type_lunwen.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)