当前位置：首页 > article >正文

PyTorch实战-手写数字识别-MLP模型

article 2024/11/5 2:34:46

1 需求

10分钟入门神经网络 PyTorch 手写数字识别_哔哩哔哩_bilibili

pytorch tutorial: PyTorch 手写数字识别教程代码

从零设计并训练一个神经网络，你就能真正理解它了_哔哩哔哩_bilibili

https://github.com/xhh890921/mnist_network

2 接口

3 豆包生成代码

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.datasets as datasets
import torchvision.transforms as transforms

# 定义超参数
batch_size = 128
learning_rate = 0.001
num_epochs = 10

# 数据预处理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

# 加载 MNIST 数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform)

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 MLP 模型
class MLP(nn.Module):
    def __init__(self):
        super(MLP, 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 = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 实例化模型
model = MLP()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
for epoch in range(num_epochs):
    for batch_idx, (data, targets) in enumerate(train_loader):
        # 前向传播
        outputs = model(data)
        loss = criterion(outputs, targets)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch_idx % 100 == 0:
            print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{batch_idx + 1}/{len(train_loader)}], Loss: {loss.item()}')

# 在测试集上评估模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for data, targets in test_loader:
        outputs = model(data)
        _, predicted = torch.max(outputs.data, 1)
        total += targets.size(0)
        correct += (predicted == targets).sum().item()

    accuracy = correct / total
    print(f'Test Accuracy: {accuracy * 100:.2f}%')

3

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.datasets import MNIST
import matplotlib.pyplot as plt

class Net(torch.nn.Module):

    def __init__(self):
        super().__init__()
        self.fc1 = torch.nn.Linear(28 * 28, 64)
        self.fc2 = torch.nn.Linear(64, 64)
        self.fc3 = torch.nn.Linear(64, 64)
        self.fc4 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = torch.nn.functional.relu(self.fc1(x))
        x = torch.nn.functional.relu(self.fc2(x))
        x = torch.nn.functional.relu(self.fc3(x))
        x = torch.nn.functional.log_softmax(self.fc4(x), dim=1)
        return x


def get_data_loader(is_train):
    to_tensor = transforms.Compose([transforms.ToTensor()])
    data_set = MNIST("", is_train, transform=to_tensor, download=True)
    return DataLoader(data_set, batch_size=15, shuffle=True)


def evaluate(test_data, net):
    n_correct = 0
    n_total = 0
    with torch.no_grad():
        for (x, y) in test_data:
            outputs = net.forward(x.view(-1, 28 * 28))
            for i, output in enumerate(outputs):
                if torch.argmax(output) == y[i]:
                    n_correct += 1
                n_total += 1
    return n_correct / n_total


def main():
    train_data = get_data_loader(is_train=True)
    test_data = get_data_loader(is_train=False)
    net = Net()

    print("initial accuracy:", evaluate(test_data, net))
    optimizer = torch.optim.Adam(net.parameters(), lr=0.001)
    for epoch in range(2):
        for (x, y) in train_data:
            net.zero_grad()
            output = net.forward(x.view(-1, 28 * 28))
            loss = torch.nn.functional.nll_loss(output, y)
            loss.backward()
            optimizer.step()
        print("epoch", epoch, "accuracy:", evaluate(test_data, net))

    for (n, (x, _)) in enumerate(test_data):
        if n > 3:
            break
        predict = torch.argmax(net.forward(x[0].view(-1, 28 * 28)))
        plt.figure(n)
        plt.imshow(x[0].view(28, 28))
        plt.title("prediction: " + str(int(predict)))
    plt.show()


if __name__ == "__main__":
    main()