Python训练打卡Day45

Tensorboard使用介绍

在神经网络训练中，，使用了很多的组件，比如训练进度条、可视化的loss下降曲线、权重分布图，运行结束后还可以查看单张图的推理效果。tensorboard这个可视化交互工具可以通过按钮完成这些辅助功能那。尤其是他可以在运行过程中实时渲染，方便我们根据图来动态调整训练策略，而不是训练完了才知道好不好。

TensorBoard 的核心原理就是在训练过程中，把训练过程中的数据（比如损失、准确率、图片等）先记录到日志文件里，再通过工具把这些日志文件可视化成图表

 pip install tensorboard -i https://pypi.tuna.tsinghua.edu.cn/simple

TensorBoard核心代码

#日志目录自动管理
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#记录标量数据
# 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)#可视化模型结构数据
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#可视化图像
# 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)#记录权重和梯度直方图
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#启动TensorBoard
#运行代码后，会在指定目录（如 runs/cifar10_mlp_experiment_1）生成 .tfevents 文件，存储所有 TensorBoard 数据

在终端执行（需进入项目根目录）：

tensorboard --logdir=runs  # 假设日志目录在 runs/ 下

打开浏览器，输入终端提示的 URL（通常为 http://localhost:6006）。

实例：cifar-10 MLP

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}%")

TensorBoard日志保存在: runs/cifar10_mlp_experiment_1

可以在命令行中进入目前的环境，然后通过tensorboard --logdir=xxxx（目录）即可调出本地链接，点进去就是目前的训练信息，可以不断F5刷新来查看变化。

在TensorBoard界面中，你可以看到：

1. SCALARS 选项卡：展示损失曲线、准确率变化、学习率等标量数据----Scalar意思是标量，指只有大小、没有方向的量。

2. IMAGES 选项卡：展示原始训练图像和错误预测的样本

3. GRAPHS 选项卡：展示模型的计算图结构

4. HISTOGRAMS 选项卡：展示模型参数和梯度的分布直方图