深度学习笔记_7经典网络模型LSTM解决FashionMNIST分类问题

1、调用模型库，定义参数，做数据预处理

import numpy as np
import torch
from torchvision.datasets import FashionMNIST
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
from torch import nn
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score, roc_curve, auc
import matplotlib.pyplot as plt

# 检查 GPU 可用性
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using device:", device)

# 设置超参数
sequence_length = 28
input_size = 28  
hidden_size = 128
num_layers = 2 
num_classes = 10
batch_size = 64
learning_rate = 0.001
num_epochs = 50

# 定义数据转换操作
transform = transforms.Compose([
    transforms.RandomRotation(degrees=[-30, 30]),   # 随机旋转
    transforms.RandomHorizontalFlip(),   # 随机水平翻转
    transforms.RandomCrop(size=28, padding=4),   # 随机裁剪
    transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.2),   # 颜色抖动
    transforms.ToTensor(),  # 将图像转换为张量
    transforms.Normalize((0.5,), (0.5,))
])

2、下载FashionMNIST训练集

# 下载FashionMNIST训练集
trainset = FashionMNIST(root='data', train=True,
                        download=True, transform=transform)

# 下载FashionMNIST测试集
testset = FashionMNIST(root='data', train=False,
                       download=True, transform=transform)

# 创建 DataLoader 对象
train_loader = DataLoader(trainset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(testset, batch_size=batch_size, shuffle=False)

3、定义LSTM模型

# 定义LSTM模型
class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(LSTM, self).__init__()
        self.hidden_size = hidden_size  # LSTM隐含层神经元数
        self.num_layers = num_layers  # LSTM层数
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)  # LSTM层
        self.fc = nn.Linear(hidden_size, num_classes)  # 全连接层

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)  # 初始化状态
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        out, _ = self.lstm(x, (h0, c0))  # LSTM前向传播
        out = self.fc(out[:, -1, :])  # 只取序列最后一个时间步的输出
        return F.log_softmax(out, dim=1)  # 使用log_softmax作为输出

# 初始化模型、优化器和损失函数
model = LSTM(input_size, hidden_size, num_layers, num_classes).to(device)
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
criterion = nn.CrossEntropyLoss()

# 记录训练和测试过程中的损失和准确率
train_losses = []
test_losses = []
train_accuracies = []
test_accuracies = []

conf_matrix_list = []
accuracy_list = []
error_rate_list = []
precision_list = []
recall_list = []
f1_score_list = []
roc_auc_list = []

4、训练循环

for epoch in range(num_epochs):
    model.train()
    train_loss = 0.0
    correct = 0
    total = 0

    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        data, target = data.to(device), target.to(device)  # 将数据移到 GPU 上
        data = data.view(-1, sequence_length, input_size)

        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()

        # 计算训练准确率
        _, predicted = output.max(1)
        total += target.size(0)
        correct += predicted.eq(target).sum().item()

    # 计算平均训练损失和训练准确率
    train_loss /= len(train_loader)
    train_accuracy = 100. * correct / total
    train_losses.append(train_loss)
    train_accuracies.append(train_accuracy)

    # 测试模型
    model.eval()
    test_loss = 0.0
    correct = 0
    all_labels = []
    all_preds = []

    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)  # 将数据移到 GPU 上
            data = data.view(-1, sequence_length, input_size)
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()
            all_labels.extend(target.cpu().numpy())  # 将结果移到 CPU 上
            all_preds.extend(pred.cpu().numpy())  # 将结果移到 CPU 上

    # 计算平均测试损失和测试准确率
    test_loss /= len(test_loader)
    test_accuracy = 100. * correct / len(test_loader.dataset)
    test_losses.append(test_loss)
    test_accuracies.append(test_accuracy)

    # 计算额外的指标
    conf_matrix = confusion_matrix(all_labels, all_preds)
    conf_matrix_list.append(conf_matrix)

    accuracy = accuracy_score(all_labels, all_preds)
    accuracy_list.append(accuracy)

    error_rate = 1 - accuracy
    error_rate_list.append(error_rate)

    precision = precision_score(all_labels, all_preds, average='weighted')
    recall = recall_score(all_labels, all_preds, average='weighted')
    f1 = f1_score(all_labels, all_preds, average='weighted')

    precision_list.append(precision)
    recall_list.append(recall)
    f1_score_list.append(f1)

    fpr, tpr, thresholds = roc_curve(all_labels, all_preds, pos_label=1)
    roc_auc = auc(fpr, tpr)
    roc_auc_list.append(roc_auc)

    # 打印每个 epoch 的指标
    print(f'Epoch [{epoch + 1}/{num_epochs}] -> Train Loss: {train_loss:.4f}, Train Accuracy: {train_accuracy:.2f}%, Test Loss: {test_loss:.4f}, Test Accuracy: {test_accuracy:.2f}%')
# 打印或绘制训练后的最终指标
print(f'Final Confusion Matrix:\n{conf_matrix_list[-1]}')
print(f'Final Accuracy: {accuracy_list[-1]:.2%}')
print(f'Final Error Rate: {error_rate_list[-1]:.2%}')
print(f'Final Precision: {precision_list[-1]:.2%}')
print(f'Final Recall: {recall_list[-1]:.2%}')
print(f'Final F1 Score: {f1_score_list[-1]:.2%}')
print(f'Final ROC AUC: {roc_auc_list[-1]:.2%}')

5、绘制Loss、Accuracy曲线图，计算混淆矩阵

import seaborn as sns
# 绘制Loss曲线图
plt.figure()
plt.plot(train_losses, label='Train Loss', color='blue')
plt.plot(test_losses, label='Test Loss', color='red')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.title('Loss Curve')
plt.grid(True)
plt.savefig('loss_curve.png')
plt.show()


# 绘制Accuracy曲线图
plt.figure()
plt.plot(train_accuracies, label='Train Accuracy', color='red')  # 绘制训练准确率曲线
plt.plot(test_accuracies, label='Test Accuracy', color='green')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.title('Accuracy Curve')
plt.grid(True)
plt.savefig('accuracy_curve.png')
plt.show()


# 计算混淆矩阵
class_labels = [str(i) for i in range(10)]
confusion_mat = confusion_matrix(all_labels, all_preds)
plt.figure()
sns.heatmap(confusion_mat, annot=True, fmt='d', cmap='Blues', cbar=False)
plt.xlabel('Predicted Labels')
plt.ylabel('True Labels')
plt.title('Confusion Matrix')
plt.savefig('confusion_matrix.png')
plt.show()