基于Pytorch的简单数字识别代码
时间: 2023-11-14 20:06:17 浏览: 35
好的,以下是基于 PyTorch 的简单数字识别代码:
```python
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
# 定义超参数
learning_rate = 0.01
batch_size = 64
num_epochs = 10
# 加载数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor())
# 创建数据加载器
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)
# 定义模型
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(784, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, 10)
def forward(self, x):
x = x.view(-1, 784)
x = nn.functional.relu(self.fc1(x))
x = nn.functional.relu(self.fc2(x))
x = self.fc3(x)
return x
# 初始化模型和优化器
model = Net()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)
# 训练模型
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
# 前向传播
outputs = model(images)
loss = nn.functional.cross_entropy(outputs, labels)
# 反向传播和优化
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 输出训练信息
if (i+1) % 100 == 0:
print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, len(train_loader), loss.item()))
# 测试模型
model.eval()
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
```
这个代码基于 PyTorch 框架,使用 MNIST 数据集进行训练和测试,实现了一个简单的数字识别模型。模型由三个全连接层组成,每个层都使用 ReLU 作为激活函数,最后一层输出一个长度为 10 的向量,表示各数字的概率分布。训练过程中使用交叉熵作为损失函数,优化器使用随机梯度下降算法。测试过程中,模型使用测试集进行评估,并输出准确率。