update

2024.12.02_MNIST/download_MNIST_and_show_image.py

@@ -0,0 +1,33 @@
+"""
+This code is supported by the website: https://www.guanjihuan.com
+The newest version of this code is on the web page: https://www.guanjihuan.com/archives/43720
+"""
+
+from torchvision import datasets, transforms
+
+transform = transforms.Compose([transforms.ToTensor()]) # 定义数据预处理步骤（转换为Tensor）
+train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform) # 加载 MNIST 数据集，训练集
+print(type(train_dataset))
+size_of_train_dataset = len(train_dataset)
+print(size_of_train_dataset)
+test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform) # 加载 MNIST 数据集，测试集
+print(type(test_dataset))
+size_of_test_dataset = len(test_dataset)
+print(size_of_test_dataset)
+
+import random
+rand_number = random.randint(0, size_of_train_dataset-1)
+image, label = train_dataset[rand_number] # 获取一张图像和标签
+print(type(image))
+print(image.shape)
+image = image.squeeze(0)  # 去掉单通道的维度 (1, 28, 28) -> (28, 28)
+print(type(image))
+print(image.shape)
+
+import matplotlib.pyplot as plt
+# import os
+# os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE" # 解决可能的多个 OpenMP 库版本冲突的问题。如果有 OMP 报错，可以试着使用这个解决。
+plt.imshow(image, cmap='gray') # 显示图像
+plt.title(f"Label: {label}")  # 标签值（理论值）
+plt.axis('off')  # 不显示坐标轴
+plt.show()

2024.12.02_MNIST/train_and_predict_MNIST.PY

@@ -0,0 +1,100 @@
+"""
+This code is supported by the website: https://www.guanjihuan.com
+The newest version of this code is on the web page: https://www.guanjihuan.com/archives/43720
+"""
+
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader, TensorDataset
+from torchvision import datasets, transforms
+
+transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,), (0.5,))])  # 数据转换（将图片转换为 Tensor 并进行归一化处理，均值和标准差为 0.5）
+train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform) # 下载训练数据集
+test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform) # 下载测试数据集
+
+# 训练函数
+def train(model, train_loader, criterion, optimizer, num_epochs=5):
+    for epoch in range(num_epochs):
+        model.train()
+        running_loss = 0.0
+        correct = 0
+        total = 0
+        for images, labels in train_loader:
+            # print(images.shape)
+            optimizer.zero_grad()  # 清除以前的梯度
+            outputs = model(images) # 前向传播
+            loss = criterion(outputs, labels)
+            loss.backward() # 反向传播和优化
+            optimizer.step()  
+            running_loss += loss.item() 
+            _, predicted = torch.max(outputs, 1) # 计算准确率
+            total += labels.size(0)
+            correct += (predicted == labels).sum().item()     
+        avg_loss = running_loss / len(train_loader)
+        accuracy = 100 * correct / total
+        print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {avg_loss:.4f}, Accuracy: {accuracy:.2f}%')
+
+# 测试函数
+def test(model, test_loader):
+    model.eval()  # 设置为评估模式
+    correct = 0
+    total = 0
+    with torch.no_grad():  # 禁用梯度计算
+        for images, labels in test_loader:
+            outputs = model(images)
+            _, predicted = torch.max(outputs, 1)
+            total += labels.size(0)
+            correct += (predicted == labels).sum().item()
+    accuracy = 100 * correct / total
+    print(f'Test Accuracy: {accuracy:.2f}%')
+
+# 训练和测试
+def train_and_test(model, train_loader, test_loader):
+    criterion = nn.CrossEntropyLoss()  # 交叉熵损失
+    optimizer = optim.Adam(model.parameters(), lr=0.001)
+    train(model, train_loader, criterion, optimizer, num_epochs=10)
+    test(model, test_loader)
+
+# 扁平化数据，并重建 DataLoader（用于全连接神经网络输入端的数据处理）
+def flatten_data(data_loader): 
+    images_array = []
+    labels_array = []
+    for images, labels in data_loader:
+        images = torch.flatten(images, start_dim=1) # 除去batch维度后，其他维度展平
+        images_array.append(images)
+        labels_array.append(labels)
+    images_array = torch.cat(images_array, dim=0)
+    labels_array = torch.cat(labels_array, dim=0)
+    dataset_new = TensorDataset(images_array, labels_array)
+    loader_new = DataLoader(dataset_new, batch_size=64, shuffle=True)
+    return loader_new
+
+# 数据加载器
+train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
+test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)
+
+# 扁平化数据
+train_loader_new = flatten_data(train_loader)
+test_loader_new = flatten_data(test_loader)
+
+# 安装软件包：pip install --upgrade guan
+import guan
+
+hidden_size = 64
+
+print('---全连接神经网络模型（包含一个隐藏层）---')
+model = guan.fully_connected_neural_network_with_one_hidden_layer(input_size=28*28, hidden_size=hidden_size, output_size=10, activation='relu')
+train_and_test(model, train_loader_new, test_loader_new)
+
+print('---全连接神经网络模型（包含两个隐藏层）---')
+model = guan.fully_connected_neural_network_with_two_hidden_layers(input_size=28*28, hidden_size_1=hidden_size, hidden_size_2=hidden_size, output_size=10, activation_1='relu', activation_2='relu')
+train_and_test(model, train_loader_new, test_loader_new)
+
+print('---全连接神经网络模型（包含三个隐藏层）---')
+model = guan.fully_connected_neural_network_with_three_hidden_layers(input_size=28*28, hidden_size_1=hidden_size, hidden_size_2=hidden_size, hidden_size_3=hidden_size, output_size=10, activation_1='relu', activation_2='relu', activation_3='relu')
+train_and_test(model, train_loader_new, test_loader_new)
+
+print('---卷积神经网络模型（包含两个卷积层和两个全连接层）---')
+model = guan.convolutional_neural_network_with_two_convolutional_layers_and_two_fully_connected_layers(in_channels=1, out_channels_1=32, out_channels_2=64, kernel_size_1=3, kernel_size_2=3, stride_1=1, stride_2=1, padding_1=1, padding_2=1, pooling=1, pooling_kernel_size=2, pooling_stride=2, input_size=7*7*64, hidden_size_1=hidden_size, hidden_size_2=hidden_size, output_size=10)
+train_and_test(model, train_loader, test_loader)