- 🍨本文为🔗365天深度学习训练营中的学习记录博客
- 🍖原作者：K同学啊
一、前期准备
1.设置GPU
import torch import torch.nn as nn import torchvision.transforms as transforms import torchvision from torchvision import transforms, datasets import os,PIL,pathlib,warnings warnings.filterwarnings("ignore") #忽略警告信息 device = torch.device("cuda" if torch.cuda.is_available() else "cpu") device2.导入数据
import os,PIL,random,pathlib data_dir = './8-data/' data_dir = pathlib.Path(data_dir) data_paths = list(data_dir.glob('*')) classeNames = [str(path).split("\\")[1] for path in data_paths] classeNames# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863 train_transforms = transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 # transforms.RandomHorizontalFlip(), # 随机水平翻转 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间 transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛 mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。 ]) test_transform = transforms.Compose([ transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸 transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间 transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛 mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。 ]) total_data = datasets.ImageFolder("./8-data/",transform=train_transforms) total_data3.划分数据集
二、搭建包含C3模块的模型
1.搭建模型
import torch.nn.functional as F def autopad(k, p=None): # kernel, padding # Pad to 'same' if p is None: p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad return p class Conv(nn.Module): # Standard convolution def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups super().__init__() self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False) self.bn = nn.BatchNorm2d(c2) self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity()) def forward(self, x): return self.act(self.bn(self.conv(x))) class Bottleneck(nn.Module): # Standard bottleneck def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_, c2, 3, 1, g=g) self.add = shortcut and c1 == c2 def forward(self, x): return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x)) class C3(nn.Module): # CSP Bottleneck with 3 convolutions def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2) self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) def forward(self, x): return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1)) class model_K(nn.Module): def __init__(self): super(model_K, self).__init__() # 卷积模块 self.Conv = Conv(3, 32, 3, 2) # C3模块1 self.C3_1 = C3(32, 64, 3, 2) # 全连接网络层，用于分类 self.classifier = nn.Sequential( nn.Linear(in_features=802816, out_features=100), nn.ReLU(), nn.Linear(in_features=100, out_features=4) ) def forward(self, x): x = self.Conv(x) x = self.C3_1(x) x = torch.flatten(x, start_dim=1) x = self.classifier(x) return x device = "cuda" if torch.cuda.is_available() else "cpu" print("Using {} device".format(device)) model = model_K().to(device) model2. 查看模型详情
# 统计模型参数量以及其他指标 import torchsummary as summary summary.summary(model, (3, 224, 224))三、 训练模型
1.训练函数
# 训练循环 def train(dataloader, model, loss_fn, optimizer): size = len(dataloader.dataset) # 训练集的大小 num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整) train_loss, train_acc = 0, 0 # 初始化训练损失和正确率 for X, y in dataloader: # 获取图片及其标签 X, y = X.to(device), y.to(device) # 计算预测误差 pred = model(X) # 网络输出 loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失 # 反向传播 optimizer.zero_grad() # grad属性归零 loss.backward() # 反向传播 optimizer.step() # 每一步自动更新 # 记录acc与loss train_acc += (pred.argmax(1) == y).type(torch.float).sum().item() train_loss += loss.item() train_acc /= size train_loss /= num_batches return train_acc, train_loss2.测试函数
def test (dataloader, model, loss_fn): size = len(dataloader.dataset) # 测试集的大小 num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整) test_loss, test_acc = 0, 0 # 当不进行训练时，停止梯度更新，节省计算内存消耗 with torch.no_grad(): for imgs, target in dataloader: imgs, target = imgs.to(device), target.to(device) # 计算loss target_pred = model(imgs) loss = loss_fn(target_pred, target) test_loss += loss.item() test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item() test_acc /= size test_loss /= num_batches return test_acc, test_loss3.正式训练
import copy optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4) loss_fn = nn.CrossEntropyLoss() # 创建损失函数 epochs = 20 train_loss = [] train_acc = [] test_loss = [] test_acc = [] best_acc = 0 # 设置一个最佳准确率，作为最佳模型的判别指标 for epoch in range(epochs): model.train() epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer) model.eval() epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn) # 保存最佳模型到 best_model if epoch_test_acc > best_acc: best_acc = epoch_test_acc best_model = copy.deepcopy(model) train_acc.append(epoch_train_acc) train_loss.append(epoch_train_loss) test_acc.append(epoch_test_acc) test_loss.append(epoch_test_loss) # 获取当前的学习率 lr = optimizer.state_dict()['param_groups'][0]['lr'] template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}') print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr)) # 保存最佳模型到文件中 PATH = './best_model.pth' # 保存的参数文件名 torch.save(best_model.state_dict(), PATH) print('Done')四、结果可视化
1.Loss与Accuracy图
import matplotlib.pyplot as plt #隐藏警告 import warnings warnings.filterwarnings("ignore") #忽略警告信息 plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签 plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号 plt.rcParams['figure.dpi'] = 100 #分辨率 from datetime import datetime current_time = datetime.now() # 获取当前时间 epochs_range = range(epochs) plt.figure(figsize=(12, 3)) plt.subplot(1, 2, 1) plt.plot(epochs_range, train_acc, label='Training Accuracy') plt.plot(epochs_range, test_acc, label='Test Accuracy') plt.legend(loc='lower right') plt.title('Training and Validation Accuracy') plt.xlabel(current_time) plt.subplot(1, 2, 2) plt.plot(epochs_range, train_loss, label='Training Loss') plt.plot(epochs_range, test_loss, label='Test Loss') plt.legend(loc='upper right') plt.title('Training and Validation Loss') plt.show()2.模型评估
best_model.eval() epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)epoch_test_acc, epoch_test_loss# 查看是否与我们记录的最高准确率一致 epoch_test_acc五、个人总结
C3模块相关知识总结
- C3 模块：YOLO（v5、v7 等）的核心特征提取单元，结合残差连接与特征拼接，平衡模型容量与计算效率，是提升特征表达能力的关键模块。
- Bottleneck 模块：C3 的内部组件，通过 “Conv-Conv - 残差相加” 的结构，在加深网络的同时缓解梯度消失问题。
- Conv 模块：基础特征变换单元，由 “Conv2d + 批归一化 + SiLU 激活” 组成，实现特征的维度变换与非线性增强。
针对 “调整这些模块提高准确率” 的可行策略：
调整 C3 模块的 Bottleneck 数量（N 值）
- )增大 N：提升网络深度，增强复杂特征的提取能力（适配复杂数据集）；需配合 dropout 等正则化手段，避免过拟合。
- )减小 N：降低冗余计算（适配简单数据集），避免模型复杂度超出数据需求导致泛化能力下降。
优化 C3 的结构变体
替换为增强版变体（如 C3TR、C3Ghost）：引入注意力机制（C3TR）或轻量化卷积（C3Ghost），在增强特征判别性的同时控制计算量。调整 Conv 模块的参数
- )卷积核尺寸：将部分 3×3 卷积替换为 5×5（扩大感受野，适配大目标），或补充 1×1 卷积（压缩通道维度，降低冗余）。
- )通道数适配：根据特征层级调整输出通道数（如高层特征使用更多通道，强化语义表达）。
增加模块层级
在 backbone/neck 的关键语义阶段，插入额外的 C3/Conv 模块，强化对关键特征的捕捉。
