使用python编写基于pytorch中的深度学习算法设计实现手写数字识别系统,使用MNIST手写完整的运行代码
时间: 2024-10-09 18:01:23 浏览: 21
在Python中利用PyTorch构建手写数字识别系统,我们可以采用经典的卷积神经网络(Convolutional Neural Network,CNN)作为模型基础,这里我会提供一个简化的示例代码来演示如何训练并测试MNIST数据集。首先,你需要安装必要的库:
```bash
pip install torch torchvision numpy
```
然后,以下是完整的代码示例:
```python
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
# 数据预处理
transform = transforms.Compose([
transforms.ToTensor(), # 将图像转为张量
transforms.Normalize((0.5,), (0.5,)) # 归一化到[0,1]区间
])
# 加载MNIST数据集
train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)
# 创建数据加载器
batch_size = 64
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
# 定义简单的LeNet模型
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10) # 10代表MNIST有10个类别
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 320) # reshape to suitable for fully connected layers
x = F.relu(self.fc1(x))
x = self.fc2(x)
return x
model = Net()
criterion = nn.CrossEntropyLoss() # 损失函数
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9) # 使用SGD优化器
# 训练过程
num_epochs = 10
for epoch in range(num_epochs):
running_loss = 0.0
for i, data in enumerate(train_loader, 0):
inputs, labels = data
optimizer.zero_grad() # 清零梯度
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 100 == 99: # 每100批次打印一次进度
print(f'Epoch {epoch + 1}, Batch {i + 1}/{len(train_loader)}, Loss: {running_loss / 100}')
running_loss = 0.0
# 测试模型
correct_count, total = 0, 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct_count += (predicted == labels).sum().item()
print(f'Test Accuracy of the model on the 10000 test images: {100 * correct_count / total}%')
#