python 图片识别实现pytorch实现
时间: 2023-05-29 08:01:55 浏览: 133
要实现图片识别,需要使用PyTorch库对模型进行训练和预测。以下是一个简单的Python程序,可以用来训练和测试一个简单的图像分类模型:
```python
# 导入需要的库
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
# 定义模型
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
# 定义训练和测试函数
def train(model, trainloader, criterion, optimizer, epochs=2):
for epoch in range(epochs):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
optimizer.zero_grad()
outputs = model(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
def test(model, testloader):
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = model(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))
# 加载和预处理训练和测试数据集
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)
# 训练和测试模型
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
train(net, trainloader, criterion, optimizer, epochs=2)
test(net, testloader)
```
以上代码训练和测试一个简单的卷积神经网络(CNN)模型,对CIFAR-10数据集中的图像进行分类。模型由两个卷积层和三个全连接层组成,通过训练CIFAR-10数据集来优化模型的权重和偏置。最后,程序计算出网络在测试集上的准确性,可以看出模型对CIFAR-10数据集的图像分类任务具有良好的性能。
阅读全文