tensorboard：
log_dir = "runs/cifar10_cnn_exp"
if os.path.exists(log_dir):
version = 1
while os.path.exists(f"{log_dir}_v{version}"):
version += 1
log_dir = f"{log_dir}_v{version}"
writer = SummaryWriter(log_dir)
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
def train(model, train_loader, test_loader, criterion, optimizer, scheduler, device, epochs, writer):
model.train()
global_step = 0
# 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 = 0.0
correct = 0
total = 0
for 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 / total
writer.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 / total
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 = 0
correct_test = 0
total_test = 0
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_test
writer.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
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