编程多层感知机实现手写数字识别

好的，下面是基于 Python 和 PyTorch 的多层感知机实现手写数字识别的代码示例。

首先，我们需要导入必要的库和数据集。这里我们使用 PyTorch 自带的 MNIST 数据集。

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms

# 定义数据集路径
data_path = './data'

# 定义数据预处理方式
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=(0.5,), std=(0.5,))
])

# 加载数据集
train_dataset = datasets.MNIST(root=data_path, train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root=data_path, train=False, download=True, transform=transform)

# 定义批次大小
batch_size = 128

# 创建数据加载器
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=True)

接着，我们定义多层感知机模型，这里使用两层全连接层。

class MLP(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super(MLP, self).__init__()
        self.fc1 = nn.Linear(input_dim, hidden_dim)
        self.fc2 = nn.Linear(hidden_dim, output_dim)
        self.relu = nn.ReLU()
        
    def forward(self, x):
        x = x.view(x.size(0), -1)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

然后，我们定义模型的超参数，并实例化模型和优化器。

# 定义模型的超参数
input_dim = 784
hidden_dim = 128
output_dim = 10
learning_rate = 0.001
num_epochs = 10

# 实例化模型和优化器
model = MLP(input_dim, hidden_dim, output_dim)
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

接下来，我们定义训练和测试的函数。

def train(model, train_loader, optimizer, criterion):
    model.train()
    train_loss = 0
    train_correct = 0
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        train_loss += loss.item()
        pred = output.argmax(dim=1, keepdim=True)
        train_correct += pred.eq(target.view_as(pred)).sum().item()
        loss.backward()
        optimizer.step()
    train_loss /= len(train_loader.dataset)
    train_acc = train_correct / len(train_loader.dataset)
    return train_loss, train_acc

def test(model, test_loader, criterion):
    model.eval()
    test_loss = 0
    test_correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            test_correct += pred.eq(target.view_as(pred)).sum().item()
    test_loss /= len(test_loader.dataset)
    test_acc = test_correct / len(test_loader.dataset)
    return test_loss, test_acc

最后，我们进行训练并测试模型。

criterion = nn.CrossEntropyLoss()

for epoch in range(1, num_epochs+1):
    train_loss, train_acc = train(model, train_loader, optimizer, criterion)
    test_loss, test_acc = test(model, test_loader, criterion)
    print('Epoch [{}/{}], Train Loss: {:.4f}, Train Acc: {:.4f}, Test Loss: {:.4f}, Test Acc: {:.4f}'
          .format(epoch, num_epochs, train_loss, train_acc, test_loss, test_acc))

训练完成后，我们可以使用模型进行预测。

import matplotlib.pyplot as plt
import numpy as np

# 随机选择一张测试图片
index = np.random.randint(0, len(test_dataset))
image, target = test_dataset[index]
image = image.unsqueeze(0)

# 使用模型进行预测
output = model(image)
pred = output.argmax(dim=1, keepdim=True)

# 显示图片和预测结果
plt.imshow(image.squeeze(), cmap='gray')
plt.title('Ground Truth: {}, Prediction: {}'.format(target, pred.item()))
plt.axis('off')
plt.show()

以上就是基于 Python 和 PyTorch 的多层感知机实现手写数字识别的代码示例。