如何使用导入的MNIST数据集？

MNIST数据集是一个广泛使用的手写数字识别数据集，包含了60000个训练样本和10000个测试样本，每个样本是一个28x28像素的灰度图像，代表一个手写数字（0到9）。以下是如何导入和使用MNIST数据集的基本步骤：

1. 导入MNIST数据集

使用Python和TensorFlow/Keras

import tensorflow as tf
from tensorflow.keras.datasets import mnist

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

# 查看数据集的基本信息
print("训练样本数量:", len(x_train))
print("测试样本数量:", len(x_test))

使用Python和PyTorch

import torch
from torchvision import datasets, transforms

# 定义数据预处理
transform = transforms.Compose([transforms.ToTensor()])

# 加载数据集
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
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=64, shuffle=False)

2. 数据预处理

归一化

为了提高模型的训练效果，通常需要对图像数据进行归一化处理。

# TensorFlow/Keras
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0

# PyTorch
# transform中已经包含了ToTensor()，它会自动将像素值归一化到[0, 1]

调整数据维度

确保数据维度符合模型的输入要求。

# TensorFlow/Keras
x_train = x_train.reshape((x_train.shape[0], 28, 28, 1))
x_test = x_test.reshape((x_test.shape[0], 28, 28, 1))

# PyTorch
# transform中已经包含了ToTensor()，它会自动调整维度

3. 构建模型

使用TensorFlow/Keras

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D

model = Sequential([
    Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),
    MaxPooling2D((2, 2)),
    Conv2D(64, (3, 3), activation='relu'),
    MaxPooling2D((2, 2)),
    Conv2D(64, (3, 3), activation='relu'),
    Flatten(),
    Dense(64, activation='relu'),
    Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

使用PyTorch

import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.fc1 = nn.Linear(64 * 5 * 5, 64)
        self.fc2 = nn.Linear(64, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)
        x = x.view(-1, 64 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

model = Net()

4. 训练模型

TensorFlow/Keras

model.fit(x_train, y_train, epochs=5, batch_size=64, validation_split=0.1)

PyTorch

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

for epoch in range(5):
    for data, target in train_loader:
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()

5. 评估模型

TensorFlow/Keras

test_loss, test_acc = model.evaluate(x_test, y_test)
print(f'Test accuracy: {test_acc}')

PyTorch

model.eval()
correct = 0
total = 0
with torch.no_grad():
    for data, target in test_loader:
        outputs = model(data)
        _, predicted = torch.max(outputs.data, 1)
        total += target.size(0)
        correct += (predicted == target).sum().item()

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