📝Docs: [Lab-2] Completed

Lab-2/src/data_load.py

@@ -0,0 +1,67 @@
+import torch
+import torchvision
+import matplotlib.pyplot as plt
+from torchvision import transforms
+from torch.utils.data import random_split, DataLoader
+
+
+def load_and_preview_mnist(data_size=100, batch_size=16, seed=42, root='../data'):
+    """
+    加载并预览 MNIST 数据集。
+    Parameters:
+    - data_size (int): 加载的数据条目数。
+    - batch_size (int): 每批次处理的数据数量。
+    - seed (int): 随机种子，用于保证数据切割的可重复性。
+    - root (str): 数据集保存的路径。
+    """
+    # 数据预处理
+    transform = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize((0.5,), (0.5,))
+    ])
+
+    # 载入数据集
+    train_dataset = torchvision.datasets.MNIST(
+        root=root,
+        train=True,
+        download=True,
+        transform=transform
+    )
+
+    # 截取指定数量的数据
+    data_train, _ = random_split(
+        dataset=train_dataset,
+        lengths=[data_size, len(train_dataset) - data_size],
+        generator=torch.Generator().manual_seed(seed)
+    )
+
+    # 加载数据集
+    train_loader = DataLoader(
+        dataset=data_train,
+        batch_size=batch_size,
+        shuffle=True
+    )
+
+    # 数据预览
+    images, labels = next(iter(train_loader))
+
+    # 将图像拼接为网格
+    img_grid = torchvision.utils.make_grid(images, nrow=batch_size // 4)
+    img = img_grid.numpy().transpose(1, 2, 0)
+    std = [0.5]
+    mean = [0.5]
+    img = img * std + mean
+
+    # 显示图像
+    print([labels[i] for i in range(batch_size)])
+    plt.imshow(img, cmap='gray')
+    plt.axis('off')
+    plt.show()
+
+
+if __name__ == '__main__':
+    # 使用默认参数调用函数
+    load_and_preview_mnist()
+
+    # 或者使用自定义参数
+    # load_and_preview_mnist(data_size=200, batch_size=8, seed=123, root='./data')

Lab-2/src/data_transform.py

@@ -0,0 +1,89 @@
+import torch
+import torchvision
+import torchvision.transforms as transforms
+import matplotlib.pyplot as plt
+from torch.utils.data import DataLoader, random_split
+
+
+def get_transform():
+    """
+    返回 torchvision.transforms.Compose 对象，包含数据预处理变换操作。
+
+    Returns:
+    - transform (torchvision.transforms.Compose): 包含数据预处理变换的 Compose 对象。
+    """
+    return transforms.Compose([
+        transforms.ToTensor(),  # 将输入数据类型转换为 Tensor
+        transforms.Normalize((0.5,), (0.5,))  # 对数据进行标准化处理，均值和标准差均为 0.5
+    ])
+
+
+def load_mnist(data_size=100, batch_size=16, seed=42, root='../data', train=True):
+    """
+    加载 MNIST 数据集。
+
+    Parameters:
+    - data_size (int): 加载的数据条目数。
+    - batch_size (int): 每批次处理的数据数量。
+    - seed (int): 随机种子，用于保证数据切割的可重复性。
+    - root (str): 数据集保存的路径。
+    - train (bool): 是否加载训练集。
+
+    Returns:
+    - DataLoader: 数据加载器。
+    """
+    transform = get_transform()
+
+    dataset = torchvision.datasets.MNIST(
+        root=root,
+        train=train,
+        download=True,
+        transform=transform
+    )
+
+    data_subset, _ = random_split(
+        dataset=dataset,
+        lengths=[data_size, len(dataset) - data_size],
+        generator=torch.Generator().manual_seed(seed)
+    )
+
+    data_loader = DataLoader(
+        dataset=data_subset,
+        batch_size=batch_size,
+        shuffle=True
+    )
+
+    return data_loader
+
+
+def load_and_preview_mnist(data_size=100, batch_size=16, seed=42, root='../data'):
+    """
+    加载并预览 MNIST 数据集。
+
+    Parameters:
+    - data_size (int): 加载的数据条目数。
+    - batch_size (int): 每批次处理的数据数量。
+    - seed (int): 随机种子，用于保证数据切割的可重复性。
+    - root (str): 数据集保存的路径。
+    """
+    train_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=True)
+
+    images, labels = next(iter(train_loader))
+
+    img_grid = torchvision.utils.make_grid(images, nrow=batch_size // 4)
+    img = img_grid.numpy().transpose(1, 2, 0)
+    mean = [0.5]
+    std = [0.5]
+    img = img * std + mean
+
+    print([labels[i] for i in range(batch_size)])
+    plt.imshow(img, cmap='gray')
+    plt.axis('off')
+    plt.show()
+
+
+if __name__ == '__main__':
+    load_and_preview_mnist()
+
+    # Or use custom parameters:
+    # load_and_preview_mnist(data_size=200, batch_size=8, seed=123, root='./data')

Lab-2/src/model_training.py

@@ -0,0 +1,116 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader
+from data_transform import load_mnist, load_and_preview_mnist
+import matplotlib.pyplot as plt
+import torchvision.utils as vutils
+
+
+# 定义卷积神经网络模型
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(1, 64, kernel_size=3, stride=2, padding=1),
+            nn.ReLU(),
+            nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
+            nn.ReLU(),
+            # nn.MaxPool2d(stride=2, kernel_size=2)
+        )
+
+        self.dense = nn.Sequential(
+            nn.Linear(7 * 7 * 128, 512),
+            nn.ReLU(),
+            nn.Dropout(p=0.8),
+            nn.Linear(512, 10)
+        )
+
+    def forward(self, x):
+        x = self.conv1(x)  # 卷积处理
+        x = x.view(-1, 7 * 7 * 128)  # 对参数实行扁平化处理
+        x = self.dense(x)
+        return x
+
+
+# 加载和预览数据集
+def main():
+    # 参数设置
+    data_size = 1000
+    batch_size = 4
+    seed = 42
+    root = '../data'
+    epochs_n = 5
+    learning_rate = 0.001
+
+    # 加载数据加载器
+    train_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=True)
+    test_loader = load_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root, train=False)
+
+    # 预览数据集（可选）
+    load_and_preview_mnist(data_size=data_size, batch_size=batch_size, seed=seed, root=root)
+
+    # 初始化模型
+    model = Model()
+    cost = nn.CrossEntropyLoss()
+    optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+    # 训练模型
+    for epoch in range(epochs_n):
+        model.train()
+        running_loss = 0.0
+        running_correct = 0
+        print(f"Epoch {epoch + 1}/{epochs_n}")
+        print("-" * 10)
+
+        for data in train_loader:
+            images, labels = data
+            optimizer.zero_grad()
+            outputs = model(images)
+            _, preds = torch.max(outputs.data, 1)
+            loss = cost(outputs, labels)
+            loss.backward()
+            optimizer.step()
+            running_loss += loss.item()
+            running_correct += (preds == labels).sum().item()
+
+        epoch_loss = running_loss / len(train_loader.dataset)
+        epoch_acc = 100 * running_correct / len(train_loader.dataset)
+
+        print(f"Loss: {epoch_loss:.4f}, Train Accuracy: {epoch_acc:.4f}%")
+
+        # 测试模型
+        model.eval()
+        testing_correct = 0
+        with torch.no_grad():
+            for data in test_loader:
+                images, labels = data
+                outputs = model(images)
+                _, preds = torch.max(outputs.data, 1)
+                testing_correct += (preds == labels).sum().item()
+
+            test_acc = 100 * testing_correct / len(test_loader.dataset)
+            print(f"Test Accuracy: {test_acc:.4f}%")
+
+    # 测试数据可视化
+    X_test, y_test = next(iter(test_loader))
+    with torch.no_grad():
+        pred = model(X_test)
+        _, predicted_labels = torch.max(pred, 1)
+
+    print("Predicted Labels:", [i.item() for i in predicted_labels])
+    print("True Labels:", [i.item() for i in y_test])
+
+    # 显示图像
+    img_grid = vutils.make_grid(X_test, nrow=batch_size // 4)
+    img = img_grid.numpy().transpose(1, 2, 0)
+    mean = [0.5]
+    std = [0.5]
+    img = img * std + mean
+    plt.imshow(img, cmap='gray')
+    plt.axis('off')
+    plt.show()
+
+
+if __name__ == '__main__':
+    main()

README.md

@@ -22,4 +22,26 @@
 
 ### RGB三通道分离并显示。
 
-`Lab-1/src/rgb_img.py`
+`Lab-1/src/rgb_img.py`
+
+## 基于PyTorch的Minist数据集分类
+
+### 数据预览测试和数据装载；
+
+`Lab-2/src/data_load.py`
+
+### 进行数据处理变换操作；
+
+`Lab-2/src/data_transform.py`
+
+### 模型搭建和参数优化；
+
+`Lab-2/src/model_training.py`
+
+### 基于pytorch卷积神经网络的模型训练；
+
+`Lab-2/src/model_training.py`
+
+### 基于pytorch卷积神经网络的模型测试。
+
+`Lab-2/src/model_training.py`