python训练营day45
知识点回顾：
- tensorboard的发展历史和原理
- tensorboard的常见操作
- tensorboard在cifar上的实战：MLP和CNN模型
效果展示如下，很适合拿去组会汇报撑页数：
作业：对resnet18在cifar10上采用微调策略下，用tensorboard监控训练过程。
PS:
- tensorboard和torch版本存在一定的不兼容性，如果报错请新建环境尝试。启动tensorboard的时候需要先在cmd中进入对应的环境，conda activate xxx，再用cd命令进入环境（如果本来就是正确的则无需操作）。
- tensorboard的代码还有有一定的记忆量，实际上深度学习的经典代码都是类似于八股文，看多了就习惯了，难度远远小于考研数学等需要思考的内容
- 实际上对目前的ai而言，你只需要先完成最简单的demo，然后让他给你加上tensorboard需要打印的部分即可。---核心是弄懂tensorboard可以打印什么信息，以及如何看可视化后的结果，把ai当成记忆大师用到的时候通过它来调取对应的代码即可。
log_dir = 'runs/cifar10_mlp_experiment'
if os.path.exists(log_dir):i = 1while os.path.exists(f"{log_dir}_{i}"):i += 1log_dir = f"{log_dir}_{i}"
writer = SummaryWriter(log_dir) #关键入口，用于写入数据到日志目录# 记录每个 Batch 的损失和准确率
writer.add_scalar('Train/Batch_Loss', batch_loss, global_step)
writer.add_scalar('Train/Batch_Accuracy', batch_acc, global_step)# 记录每个 Epoch 的训练指标
writer.add_scalar('Train/Epoch_Loss', epoch_train_loss, epoch)
writer.add_scalar('Train/Epoch_Accuracy', epoch_train_acc, epoch)dataiter = iter(train_loader)
images, labels = next(dataiter)
images = images.to(device)
writer.add_graph(model, images) # 通过真实输入样本生成模型计算图\# 可视化原始训练图像
img_grid = torchvision.utils.make_grid(images[:8].cpu()) # 将多张图像拼接成网格状（方便可视化），将前8张图像拼接成一个网格
writer.add_image('原始训练图像', img_grid)# 可视化错误预测样本（训练结束后）
wrong_img_grid = torchvision.utils.make_grid(wrong_images[:display_count])
writer.add_image('错误预测样本', wrong_img_grid)if (batch_idx + 1) % 500 == 0:for name, param in model.named_parameters():writer.add_histogram(f'weights/{name}', param, global_step) # 权重分布if param.grad is not None:writer.add_histogram(f'grads/{name}', param.grad, global_step) # 梯度分布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 + Dropoutx = 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 + Dropoutx = 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 = 1while os.path.exists(f"{log_dir}_{i}"):i += 1log_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 = 0.0correct = 0total = 0for batch_idx, (data, target) in enumerate(train_loader):data, target = data.to(device), target.to(device) # 移至GPUoptimizer.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TensorBoardif (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 = 0correct_test = 0total_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}%")import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import matplotlib.pyplot as plt
import numpy as np
import os
import torchvision # 记得导入 torchvision，之前代码里用到了其功能但没导入# 设置中文字体支持
plt.rcParams["font.family"] = ["SimHei"]
plt.rcParams['axes.unicode_minus'] = False # 解决负号显示问题# 检查GPU是否可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"使用设备: {device}")# 1. 数据预处理
train_transform = transforms.Compose([transforms.RandomCrop(32, padding=4),transforms.RandomHorizontalFlip(),transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.1),transforms.RandomRotation(15),transforms.ToTensor(),transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])test_transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
])# 2. 加载CIFAR-10数据集
train_dataset = datasets.CIFAR10(root='./data',train=True,download=True,transform=train_transform
)test_dataset = datasets.CIFAR10(root='./data',train=False,transform=test_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)# 4. 定义CNN模型的定义（替代原MLP）
class CNN(nn.Module):def __init__(self):super(CNN, self).__init__() # 继承父类初始化# ---------------------- 第一个卷积块 ----------------------# 卷积层1：输入3通道（RGB），输出32个特征图，卷积核3x3，边缘填充1像素self.conv1 = nn.Conv2d(in_channels=3, # 输入通道数（图像的RGB通道）out_channels=32, # 输出通道数（生成32个新特征图）kernel_size=3, # 卷积核尺寸（3x3像素）padding=1 # 边缘填充1像素，保持输出尺寸与输入相同)# 批量归一化层：对32个输出通道进行归一化，加速训练self.bn1 = nn.BatchNorm2d(num_features=32)# ReLU激活函数：引入非线性，公式：max(0, x)self.relu1 = nn.ReLU()# 最大池化层：窗口2x2，步长2，特征图尺寸减半（32x32→16x16）self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2) # stride默认等于kernel_size# ---------------------- 第二个卷积块 ----------------------# 卷积层2：输入32通道（来自conv1的输出），输出64通道self.conv2 = nn.Conv2d(in_channels=32, # 输入通道数（前一层的输出通道数）out_channels=64, # 输出通道数（特征图数量翻倍）kernel_size=3, # 卷积核尺寸不变padding=1 # 保持尺寸：16x16→16x16（卷积后）→8x8（池化后）)self.bn2 = nn.BatchNorm2d(num_features=64)self.relu2 = nn.ReLU()self.pool2 = nn.MaxPool2d(kernel_size=2) # 尺寸减半：16x16→8x8# ---------------------- 第三个卷积块 ----------------------# 卷积层3：输入64通道，输出128通道self.conv3 = nn.Conv2d(in_channels=64, # 输入通道数（前一层的输出通道数）out_channels=128, # 输出通道数（特征图数量再次翻倍）kernel_size=3,padding=1 # 保持尺寸：8x8→8x8（卷积后）→4x4（池化后）)self.bn3 = nn.BatchNorm2d(num_features=128)self.relu3 = nn.ReLU() # 复用激活函数对象（节省内存）self.pool3 = nn.MaxPool2d(kernel_size=2) # 尺寸减半：8x8→4x4# ---------------------- 全连接层（分类器） ----------------------# 计算展平后的特征维度：128通道 × 4x4尺寸 = 128×16=2048维self.fc1 = nn.Linear(in_features=128 * 4 * 4, # 输入维度（卷积层输出的特征数）out_features=512 # 输出维度（隐藏层神经元数）)# Dropout层：训练时随机丢弃50%神经元，防止过拟合self.dropout = nn.Dropout(p=0.5)# 输出层：将512维特征映射到10个类别（CIFAR-10的类别数）self.fc2 = nn.Linear(in_features=512, out_features=10)def forward(self, x):# 输入尺寸：[batch_size, 3, 32, 32]（batch_size=批量大小，3=通道数，32x32=图像尺寸）# ---------- 卷积块1处理 ----------x = self.conv1(x) # 卷积后尺寸：[batch_size, 32, 32, 32]（padding=1保持尺寸）x = self.bn1(x) # 批量归一化，不改变尺寸x = self.relu1(x) # 激活函数，不改变尺寸x = self.pool1(x) # 池化后尺寸：[batch_size, 32, 16, 16]（32→16是因为池化窗口2x2）# ---------- 卷积块2处理 ----------x = self.conv2(x) # 卷积后尺寸：[batch_size, 64, 16, 16]（padding=1保持尺寸）x = self.bn2(x)x = self.relu2(x)x = self.pool2(x) # 池化后尺寸：[batch_size, 64, 8, 8]# ---------- 卷积块3处理 ----------x = self.conv3(x) # 卷积后尺寸：[batch_size, 128, 8, 8]（padding=1保持尺寸）x = self.bn3(x)x = self.relu3(x)x = self.pool3(x) # 池化后尺寸：[batch_size, 128, 4, 4]# ---------- 展平与全连接层 ----------# 将多维特征图展平为一维向量：[batch_size, 128*4*4] = [batch_size, 2048]x = x.view(-1, 128 * 4 * 4) # -1自动计算批量维度，保持批量大小不变x = self.fc1(x) # 全连接层：2048→512，尺寸变为[batch_size, 512]x = self.relu3(x) # 激活函数（复用relu3，与卷积块3共用）x = self.dropout(x) # Dropout随机丢弃神经元，不改变尺寸x = self.fc2(x) # 全连接层：512→10，尺寸变为[batch_size, 10]（未激活，直接输出logits）return x # 输出未经过Softmax的logits，适用于交叉熵损失函数# 初始化模型
model = CNN()
model = model.to(device) # 将模型移至GPU（如果可用）criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, # 指定要控制的优化器（这里是Adam）mode='min', # 监测的指标是"最小化"（如损失函数）patience=3, # 如果连续3个epoch指标没有改善，才降低LRfactor=0.5, # 降低LR的比例（新LR = 旧LR × 0.5）verbose=True # 打印学习率调整信息
)# ======================== TensorBoard 核心配置 ========================
# 创建 TensorBoard 日志目录（自动避免重复）
log_dir = "runs/cifar10_cnn_exp"
if os.path.exists(log_dir):version = 1while os.path.exists(f"{log_dir}_v{version}"):version += 1log_dir = f"{log_dir}_v{version}"
writer = SummaryWriter(log_dir) # 初始化 SummaryWriter# 5. 训练模型（整合 TensorBoard 记录）
def train(model, train_loader, test_loader, criterion, optimizer, scheduler, device, epochs, writer):model.train()all_iter_losses = [] iter_indices = [] global_step = 0 # 全局步骤，用于 TensorBoard 标量记录# （可选）记录模型结构：用一个真实样本走一遍前向传播，让 TensorBoard 解析计算图dataiter = iter(train_loader)images, labels = next(dataiter)images = images.to(device)writer.add_graph(model, images) # 写入模型结构到 TensorBoard# （可选）记录原始训练图像：可视化数据增强前/后效果img_grid = torchvision.utils.make_grid(images[:8].cpu()) # 取前8张writer.add_image('原始训练图像（增强前）', img_grid, global_step=0)for epoch in range(epochs):running_loss = 0.0correct = 0total = 0for batch_idx, (data, target) in enumerate(train_loader):data, target = data.to(device), target.to(device)optimizer.zero_grad()output = model(data)loss = criterion(output, target)loss.backward()optimizer.step()# 记录迭代级损失iter_loss = loss.item()all_iter_losses.append(iter_loss)iter_indices.append(global_step + 1) # 用 global_step 对齐# 统计准确率running_loss += iter_loss_, predicted = output.max(1)total += target.size(0)correct += predicted.eq(target).sum().item()# ======================== TensorBoard 标量记录 ========================# 记录每个 batch 的损失、准确率batch_acc = 100. * correct / totalwriter.add_scalar('Train/Batch Loss', iter_loss, global_step)writer.add_scalar('Train/Batch Accuracy', batch_acc, global_step)# 记录学习率（可选）writer.add_scalar('Train/Learning Rate', optimizer.param_groups[0]['lr'], global_step)# 每 200 个 batch 记录一次参数直方图（可选，耗时稍高）if (batch_idx + 1) % 200 == 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'Gradients/{name}', param.grad, global_step)# 每 100 个 batch 打印控制台日志（同原代码）if (batch_idx + 1) % 100 == 0:print(f'Epoch: {epoch+1}/{epochs} | Batch: {batch_idx+1}/{len(train_loader)} 'f'| 单Batch损失: {iter_loss:.4f} | 累计平均损失: {running_loss/(batch_idx+1):.4f}')global_step += 1 # 全局步骤递增# 计算 epoch 级训练指标epoch_train_loss = running_loss / len(train_loader)epoch_train_acc = 100. * correct / total# ======================== TensorBoard epoch 标量记录 ========================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()test_loss = 0correct_test = 0total_test = 0wrong_images = [] # 存储错误预测样本（用于可视化）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()# 收集错误预测样本（用于可视化）wrong_mask = (predicted != target)if wrong_mask.sum() > 0:wrong_batch_images = data[wrong_mask][:8].cpu() # 最多存8张wrong_batch_labels = target[wrong_mask][:8].cpu()wrong_batch_preds = predicted[wrong_mask][:8].cpu()wrong_images.extend(wrong_batch_images)wrong_labels.extend(wrong_batch_labels)wrong_preds.extend(wrong_batch_preds)# 计算 epoch 级测试指标epoch_test_loss = test_loss / len(test_loader)epoch_test_acc = 100. * correct_test / total_test# ======================== TensorBoard 测试集记录 ========================writer.add_scalar('Test/Epoch Loss', epoch_test_loss, epoch)writer.add_scalar('Test/Epoch Accuracy', epoch_test_acc, epoch)# （可选）可视化错误预测样本if wrong_images:wrong_img_grid = torchvision.utils.make_grid(wrong_images)writer.add_image('错误预测样本', wrong_img_grid, epoch)# 写入错误标签文本（可选）wrong_text = [f"真实: {classes[wl]}, 预测: {classes[wp]}" for wl, wp in zip(wrong_labels, wrong_preds)]writer.add_text('错误预测标签', '\n'.join(wrong_text), epoch)# 更新学习率调度器scheduler.step(epoch_test_loss)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}%')# 关闭 TensorBoard 写入器writer.close()# 绘制迭代级损失曲线（同原代码）plot_iter_losses(all_iter_losses, iter_indices)return epoch_test_acc# 6. 绘制迭代级损失曲线（同原代码，略）
def plot_iter_losses(losses, indices):plt.figure(figsize=(10, 4))plt.plot(indices, losses, 'b-', alpha=0.7, label='Iteration Loss')plt.xlabel('Iteration（Batch序号）')plt.ylabel('损失值')plt.title('每个 Iteration 的训练损失')plt.legend()plt.grid(True)plt.tight_layout()plt.show()# （可选）CIFAR-10 类别名
classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')# 7. 执行训练（传入 TensorBoard writer）
epochs = 20
print("开始使用CNN训练模型...")
print(f"TensorBoard 日志目录: {log_dir}")
print("训练后执行: tensorboard --logdir=runs 查看可视化")final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, scheduler, device, epochs, writer)
print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")# 省略预处理、模型定义代码# ======================== TensorBoard 核心配置 ========================
# 在使用tensorboard前需要先指定日志保存路径
log_dir = "runs/cifar10_cnn_exp" # 指定日志保存路径
if os.path.exists(log_dir): #检查刚才定义的路径是否存在version = 1 while os.path.exists(f"{log_dir}_v{version}"): # 如果路径存在且版本号一致version += 1 # 版本号加1log_dir = f"{log_dir}_v{version}" # 如果路径存在，则创建一个新版本
writer = SummaryWriter(log_dir) # 初始化SummaryWriter
print(f"TensorBoard 日志目录: {log_dir}") # 所以第一次是cifar10_cnn_exp、第二次是cifar10_cnn_exp_v1# 5. 训练模型（整合 TensorBoard 记录）
def train(model, train_loader, test_loader, criterion, optimizer, scheduler, device, epochs, writer):model.train()global_step = 0 # 全局步骤，用于 TensorBoard 标量记录# 记录模型结构和训练图像dataiter = iter(train_loader)images, labels = next(dataiter)images = images.to(device)writer.add_graph(model, images)img_grid = torchvision.utils.make_grid(images[:8].cpu())writer.add_image('原始训练图像（增强前）', img_grid, global_step=0)for epoch in range(epochs):running_loss = 0.0correct = 0total = 0for batch_idx, (data, target) in enumerate(train_loader):data, target = data.to(device), target.to(device)optimizer.zero_grad()output = model(data)loss = criterion(output, target)loss.backward()optimizer.step()# 统计准确率running_loss += loss.item()_, predicted = output.max(1)total += target.size(0)correct += predicted.eq(target).sum().item()# 记录每个 batch 的损失、准确率和学习率batch_acc = 100. * correct / totalwriter.add_scalar('Train/Batch Loss', loss.item(), global_step)writer.add_scalar('Train/Batch Accuracy', batch_acc, global_step)writer.add_scalar('Train/Learning Rate', optimizer.param_groups[0]['lr'], global_step)# 每 200 个 batch 记录一次参数直方图if (batch_idx + 1) % 200 == 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'Gradients/{name}', param.grad, global_step)global_step += 1# 计算 epoch 级训练指标epoch_train_loss = running_loss / len(train_loader)epoch_train_acc = 100. * correct / totalwriter.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()test_loss = 0correct_test = 0total_test = 0wrong_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()# 收集错误预测样本wrong_mask = (predicted != target)if wrong_mask.sum() > 0:wrong_batch_images = data[wrong_mask][:8].cpu()wrong_batch_labels = target[wrong_mask][:8].cpu()wrong_batch_preds = predicted[wrong_mask][:8].cpu()wrong_images.extend(wrong_batch_images)wrong_labels.extend(wrong_batch_labels)wrong_preds.extend(wrong_batch_preds)# 计算 epoch 级测试指标epoch_test_loss = test_loss / len(test_loader)epoch_test_acc = 100. * correct_test / total_testwriter.add_scalar('Test/Epoch Loss', epoch_test_loss, epoch)writer.add_scalar('Test/Epoch Accuracy', epoch_test_acc, epoch)# 可视化错误预测样本if wrong_images:wrong_img_grid = torchvision.utils.make_grid(wrong_images)writer.add_image('错误预测样本', wrong_img_grid, epoch)wrong_text = [f"真实: {classes[wl]}, 预测: {classes[wp]}" for wl, wp in zip(wrong_labels, wrong_preds)]writer.add_text('错误预测标签', '\n'.join(wrong_text), epoch)# 更新学习率调度器scheduler.step(epoch_test_loss)print(f'Epoch {epoch+1}/{epochs} 完成 | 测试准确率: {epoch_test_acc:.2f}%')writer.close()return epoch_test_acc# （可选）CIFAR-10 类别名
classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')# 执行训练
epochs = 20
print("开始使用CNN训练模型...")
print("训练后执行: tensorboard --logdir=runs 查看可视化")final_accuracy = train(model, train_loader, test_loader, criterion, optimizer, scheduler, device, epochs, writer)
print(f"训练完成！最终测试准确率: {final_accuracy:.2f}%")@浙大疏锦行