bpnn神经网络模型代码

### BPNN 神经网络模型代码实现

#### 使用 PyTorch 实现 BPNN 模型

在人工神经网络的发展历史中，感知机（Multilayer Perceptron, MLP）网络对人工神经网络的发展起到了重要作用[^2]。下面是一个简单的基于 PyTorch 的反向传播神经网络 (BPNN) 模型的 Python 实现：

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        pred = model(X)
        loss = loss_fn(pred, y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            current = batch * len(X)
            print(f"Loss: {loss.item():>7f} [{current:>5d}/{size:>5d}]")

device = "cuda" if torch.cuda.is_available() else "cpu"
model = NeuralNetwork().to(device)
print(model)

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)

train_dataloader = DataLoader(training_data, batch_size=64)
epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
print("Done!")

这段代码展示了如何定义一个多层感知器并训练它来完成 Fashion-MNIST 数据集上的分类任务。

#### 使用 TensorFlow 实现 BPNN 模型

对于那些希望使用 TensorFlow 来创建类似的多层感知器的人来说，这里提供了一个简单例子:

import tensorflow as tf
from tensorflow.keras.datasets import fashion_mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten

# 加载数据集
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()

# 归一化图片像素值到 [0, 1] 范围内
x_train, x_test = x_train / 255.0, x_test / 255.0

# 构建模型
model = Sequential([
    Flatten(input_shape=(28, 28)),
    Dense(128, activation='relu'),
    Dense(10)
])

# 编译模型
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# 训练模型
model.fit(x_train, y_train, epochs=5)

# 测试模型性能
test_loss, test_acc = model.evaluate(x_test,  y_test, verbose=2)
print('\nTest accuracy:', test_acc)

此段代码同样实现了对 Fashion-MNIST 数据集上执行图像分类的任务，并采用了更简洁的方式配置和编译 Keras 序列模型。