Day 45 Tensorboard使用介绍

@浙大疏锦行

import torch import torch.nn as nn import torch.optim as optim import torchvision from torchvision import datasets, transforms from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter import numpy as np import matplotlib.pyplot as plt import os # 设置随机种子以确保结果可复现 torch.manual_seed(42) np.random.seed(42) # 1. 数据预处理 transform = transforms.Compose([ transforms.ToTensor(), # 转换为张量 transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) # 标准化处理 ]) # 2. 加载CIFAR-10数据集 train_dataset = datasets.CIFAR10( root='./data', train=True, download=True, transform=transform ) test_dataset = datasets.CIFAR10( root='./data', train=False, transform=transform ) # 3. 创建数据加载器 batch_size = 64 train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True) test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False) # CIFAR-10的类别名称 classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') # 4. 定义MLP模型（适应CIFAR-10的输入尺寸） class MLP(nn.Module): def __init__(self): super(MLP, self).__init__() self.flatten = nn.Flatten() # 将3x32x32的图像展平为3072维向量 self.layer1 = nn.Linear(3072, 512) # 第一层：3072个输入，512个神经元 self.relu1 = nn.ReLU() self.dropout1 = nn.Dropout(0.2) # 添加Dropout防止过拟合 self.layer2 = nn.Linear(512, 256) # 第二层：512个输入，256个神经元 self.relu2 = nn.ReLU() self.dropout2 = nn.Dropout(0.2) self.layer3 = nn.Linear(256, 10) # 输出层：10个类别 def forward(self, x): # 第一步：将输入图像展平为一维向量 x = self.flatten(x) # 输入尺寸: [batch_size, 3, 32, 32] → [batch_size, 3072] # 第一层全连接 + 激活 + Dropout x = self.layer1(x) # 线性变换: [batch_size, 3072] → [batch_size, 512] x = self.relu1(x) # 应用ReLU激活函数 x = self.dropout1(x) # 训练时随机丢弃部分神经元输出 # 第二层全连接 + 激活 + Dropout x = self.layer2(x) # 线性变换: [batch_size, 512] → [batch_size, 256] x = self.relu2(x) # 应用ReLU激活函数 x = self.dropout2(x) # 训练时随机丢弃部分神经元输出 # 第三层（输出层）全连接 x = self.layer3(x) # 线性变换: [batch_size, 256] → [batch_size, 10] return x # 返回未经过Softmax的logits # 检查GPU是否可用 device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 初始化模型 model = MLP() model = model.to(device) # 将模型移至GPU（如果可用） criterion = nn.CrossEntropyLoss() # 交叉熵损失函数 optimizer = optim.Adam(model.parameters(), lr=0.001) # Adam优化器 # 创建TensorBoard的SummaryWriter，指定日志保存目录 log_dir = 'runs/cifar10_mlp_experiment' # 如果目录已存在，添加后缀避免覆盖 if os.path.exists(log_dir): i = 1 while os.path.exists(f"{log_dir}_{i}"): i += 1 log_dir = f"{log_dir}_{i}" writer = SummaryWriter(log_dir) # 5. 训练模型（使用TensorBoard记录各种信息） def train(model, train_loader, test_loader, criterion, optimizer, device, epochs, writer): model.train() # 设置为训练模式 # 记录训练开始时间，用于计算训练速度 global_step = 0 # 可视化模型结构 dataiter = iter(train_loader) images, labels = next(dataiter) images = images.to(device) writer.add_graph(model, images) # 添加模型图 # 可视化原始图像样本 img_grid = torchvision.utils.make_grid(images[:8].cpu()) writer.add_image('原始训练图像', img_grid) for epoch in range(epochs): running_loss = 0.0 correct = 0 total = 0 for batch_idx, (data, target) in enumerate(train_loader): data, target = data.to(device), target.to(device) # 移至GPU optimizer.zero_grad() # 梯度清零 output = model(data) # 前向传播 loss = criterion(output, target) # 计算损失 loss.backward() # 反向传播 optimizer.step() # 更新参数 # 统计准确率和损失 running_loss += loss.item() _, predicted = output.max(1) total += target.size(0) correct += predicted.eq(target).sum().item() # 每100个批次记录一次信息到TensorBoard if (batch_idx + 1) % 100 == 0: batch_loss = loss.item() batch_acc = 100. * correct / total # 记录标量数据（损失、准确率） writer.add_scalar('Train/Batch_Loss', batch_loss, global_step) writer.add_scalar('Train/Batch_Accuracy', batch_acc, global_step) # 记录学习率 writer.add_scalar('Train/Learning_Rate', optimizer.param_groups[0]['lr'], global_step) # 每500个批次记录一次直方图（权重和梯度） if (batch_idx + 1) % 500 == 0: for name, param in model.named_parameters(): writer.add_histogram(f'weights/{name}', param, global_step) if param.grad is not None: writer.add_histogram(f'grads/{name}', param.grad, global_step) print(f'Epoch: {epoch+1}/{epochs} | Batch: {batch_idx+1}/{len(train_loader)} ' f'| 单Batch损失: {batch_loss:.4f} | 累计平均损失: {running_loss/(batch_idx+1):.4f}') global_step += 1 # 计算当前epoch的平均训练损失和准确率 epoch_train_loss = running_loss / len(train_loader) epoch_train_acc = 100. * correct / total # 记录每个epoch的训练损失和准确率 writer.add_scalar('Train/Epoch_Loss', epoch_train_loss, epoch) writer.add_scalar('Train/Epoch_Accuracy', epoch_train_acc, epoch) # 测试阶段 model.eval() # 设置为评估模式 test_loss = 0 correct_test = 0 total_test = 0 # 用于存储预测错误的样本 wrong_images = [] wrong_labels = [] wrong_preds = [] with torch.no_grad(): for data, target in test_loader: data, target = data.to(device), target.to(device) output = model(data) test_loss += criterion(output, target).item() _, predicted = output.max(1) total_test += target.size(0) correct_test += predicted.eq(target).sum().item() # 收集预测错误的样本 wrong_mask = (predicted != target).cpu() if wrong_mask.sum() > 0: wrong_batch_images = data[wrong_mask].cpu() wrong_batch_labels = target[wrong_mask].cpu() wrong_batch_preds = predicted[wrong_mask].cpu() wrong_images.extend(wrong_batch_images) wrong_labels.extend(wrong_batch_labels) wrong_preds.extend(wrong_batch_preds) epoch_test_loss = test_loss / len(test_loader) epoch_test_acc = 100. * correct_test / total_test # 记录每个epoch的测试损失和准确率 writer.add_scalar('Test/Loss', epoch_test_loss, epoch) writer.add_scalar('Test/Accuracy', epoch_test_acc, epoch) # 计算并记录训练速度（每秒处理的样本数） # 这里简化处理，假设每个epoch的时间相同 samples_per_epoch = len(train_loader.dataset) # 实际应用中应该使用time.time()来计算真实时间 print(f'Epoch {epoch+1}/{epochs} 完成 | 训练准确率: {epoch_train_acc:.2f}% | 测试准确率: {epoch_test_acc:.2f}%') # 可视化预测错误的样本（只在最后一个epoch进行） if epoch == epochs - 1 and len(wrong_images) > 0: # 最多显示8个错误样本 display_count = min(8, len(wrong_images)) wrong_img_grid = torchvision.utils.make_grid(wrong_images[:display_count]) # 创建错误预测的标签文本 wrong_text = [] for i in range(display_count): true_label = classes[wrong_labels[i]] pred_label = classes[wrong_preds[i]] wrong_text.append(f'True: {true_label}, Pred: {pred_label}') writer.add_image('错误预测样本', wrong_img_grid) writer.add_text('错误预测标签', '\n'.join(wrong_text), epoch) # 关闭TensorBoard写入器 writer.close() return epoch_test_acc # 返回最终测试准确率 # 6. 执行训练和测试 epochs = 20 # 训练轮次 print("开始训练模型...") print(f"TensorBoard日志保存在: {log_dir}") print("训练完成后，使用命令 `tensorboard --logdir=runs` 启动TensorBoard查看可视化结果") final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, device, epochs, writer) print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")