news 2026/1/30 4:26:04

Pytorch学习系列08 | YOLOv5-C3模块实现

作者头像

张小明

前端开发工程师

1.2k 24
文章封面图
Pytorch学习系列08 | YOLOv5-C3模块实现
  • 🍨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、前置知识

1、YOLOv5算法中的C3模块介绍

先引用一个生活化的案例图快速理解一下

C3 模块的全称是CSP Bottleneck with 3 convolutions。它是 YOLOv5 在 YOLOv4 的 CSP（Cross Stage Partial）架构基础上改进而来的。

  1. 核心思想：CSP（跨阶段局部网络）C3 的核心在于“分治”。它将输入特征图分为两部分：
    • 一部分通过一系列的残差块（Bottleneck）进行深度的特征变换，负责学习复杂的特征。
    • 另一部分直接通过一个卷积层，走“捷径”去和后面汇合。
    • 这种设计可以让梯度的传播更加顺畅，减少了计算量，同时保证了特征的丰富性。
  1. 为什么叫 "C3"？因为它主要包含3 个标准卷积层（Conv）以及多个 Bottleneck 模块：
    • Conv 1：主干分支的入口。
    • Conv 2：侧路分支（捷径）的入口。
    • Conv 3：最后负责融合两个分支输出的出口。
    • 注：中间的 Bottleneck 里虽然也有卷积，但不算在 C3 命名的这“3”个主控制卷积里。
  1. C3 的作用
    • 轻量化：相比于之前的 CSP 结构，C3 去掉了一些不必要的卷积，参数更少，速度更快。
    • 特征提取能力强：它是 YOLOv5 网络主干（Backbone）和颈部（Neck）中的核心组件，网络的深度（depth）主要就是通过控制 C3 中 Bottleneck 的重复次数（N）来实现的。

二、代码实现

1、设置GPU

若设备支持GPU就使用GPU,否则使用CPU

import torch import torch.nn as nn import matplotlib.pyplot as plt import torchvision import warnings import torchvision.transforms as transforms from torchvision import transforms, datasets # 忽略来自 torch.cuda 的 pynvml 弃用警告 warnings.filterwarnings( "ignore", message="The pynvml package is deprecated.*", category=FutureWarning, module="torch.cuda" ) device = torch.device("cuda" if torch.cuda.is_available() else "cpu") device
device(type='cuda')

2、数据准备

2.1、识别数据路径

import os import pathlib # 查看当前工作路径（确认路径是否正确） print("当前工作路径：", os.getcwd()) # 定义数据目录（建议用绝对路径更稳妥，相对路径依赖当前工作路径） data_dir = './data/天气识别数据集/' data_dir = pathlib.Path(data_dir) # 获取数据目录下的所有子路径（文件夹或文件） data_paths = list(data_dir.glob('*')) # 提取每个子路径的名称（即类别名，自动适配系统分隔符） classeNames = [path.name for path in data_paths] classeNames
当前工作路径： /root/365天训练营/Pytorch实战 ['cloudy', 'rain', 'shine', 'sunrise']

2.2、获取数据

data_dir = './data/天气识别数据集/' # 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(data_dir, transform=train_transforms) total_data
Dataset ImageFolder Number of datapoints: 1125 Root location: ./data/天气识别数据集/ StandardTransform Transform: Compose( Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn) ToTensor() Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) )
total_data.class_to_idx
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}

2.3、划分数据集

train_size = int(0.8 * len(total_data)) test_size = len(total_data) - train_size train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size]) train_dataset, test_dataset batch_size = 4 train_dl = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=1) test_dl = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=True, num_workers=1) for X, y in test_dl: print("Shape of X [N, C, H, W]: ", X.shape) print("Shape of y: ", y.shape, y.dtype) break
Shape of X [N, C, H, W]: torch.Size([4, 3, 224, 224]) Shape of y: torch.Size([4]) torch.int64

3、模型搭建

3.1、搭建C3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) model
Using cuda device model_K( (Conv): Conv( (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (C3_1): C3( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv3): Conv( (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (m): Sequential( (0): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) (1): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) (2): Bottleneck( (cv1): Conv( (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) (cv2): Conv( (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (act): SiLU() ) ) ) ) (classifier): Sequential( (0): Linear(in_features=802816, out_features=100, bias=True) (1): ReLU() (2): Linear(in_features=100, out_features=4, bias=True) ) )

3.2、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))
---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Conv2d-1 [-1, 32, 112, 112] 864 BatchNorm2d-2 [-1, 32, 112, 112] 64 SiLU-3 [-1, 32, 112, 112] 0 Conv-4 [-1, 32, 112, 112] 0 Conv2d-5 [-1, 32, 112, 112] 1,024 BatchNorm2d-6 [-1, 32, 112, 112] 64 SiLU-7 [-1, 32, 112, 112] 0 Conv-8 [-1, 32, 112, 112] 0 Conv2d-9 [-1, 32, 112, 112] 1,024 BatchNorm2d-10 [-1, 32, 112, 112] 64 SiLU-11 [-1, 32, 112, 112] 0 Conv-12 [-1, 32, 112, 112] 0 Conv2d-13 [-1, 32, 112, 112] 9,216 BatchNorm2d-14 [-1, 32, 112, 112] 64 SiLU-15 [-1, 32, 112, 112] 0 Conv-16 [-1, 32, 112, 112] 0 Bottleneck-17 [-1, 32, 112, 112] 0 Conv2d-18 [-1, 32, 112, 112] 1,024 BatchNorm2d-19 [-1, 32, 112, 112] 64 SiLU-20 [-1, 32, 112, 112] 0 Conv-21 [-1, 32, 112, 112] 0 Conv2d-22 [-1, 32, 112, 112] 9,216 BatchNorm2d-23 [-1, 32, 112, 112] 64 SiLU-24 [-1, 32, 112, 112] 0 Conv-25 [-1, 32, 112, 112] 0 Bottleneck-26 [-1, 32, 112, 112] 0 Conv2d-27 [-1, 32, 112, 112] 1,024 BatchNorm2d-28 [-1, 32, 112, 112] 64 SiLU-29 [-1, 32, 112, 112] 0 Conv-30 [-1, 32, 112, 112] 0 Conv2d-31 [-1, 32, 112, 112] 9,216 BatchNorm2d-32 [-1, 32, 112, 112] 64 SiLU-33 [-1, 32, 112, 112] 0 Conv-34 [-1, 32, 112, 112] 0 Bottleneck-35 [-1, 32, 112, 112] 0 Conv2d-36 [-1, 32, 112, 112] 1,024 BatchNorm2d-37 [-1, 32, 112, 112] 64 SiLU-38 [-1, 32, 112, 112] 0 Conv-39 [-1, 32, 112, 112] 0 Conv2d-40 [-1, 64, 112, 112] 4,096 BatchNorm2d-41 [-1, 64, 112, 112] 128 SiLU-42 [-1, 64, 112, 112] 0 Conv-43 [-1, 64, 112, 112] 0 C3-44 [-1, 64, 112, 112] 0 Linear-45 [-1, 100] 80,281,700 ReLU-46 [-1, 100] 0 Linear-47 [-1, 4] 404 ================================================================ Total params: 80,320,536 Trainable params: 80,320,536 Non-trainable params: 0 ---------------------------------------------------------------- Input size (MB): 0.57 Forward/backward pass size (MB): 150.06 Params size (MB): 306.40 Estimated Total Size (MB): 457.04 ----------------------------------------------------------------

4、训练模型

4.1、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_loss

4.2、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_loss

4.3、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 = './model/p8_best_model.pth' # 保存的参数文件名 torch.save(best_model.state_dict(), PATH) print('Done')
Epoch: 1, Train_acc:74.1%, Train_loss:1.327, Test_acc:86.2%, Test_loss:0.431, Lr:1.00E-04 Epoch: 2, Train_acc:89.6%, Train_loss:0.306, Test_acc:90.2%, Test_loss:0.374, Lr:1.00E-04 Epoch: 3, Train_acc:94.3%, Train_loss:0.165, Test_acc:87.1%, Test_loss:0.356, Lr:1.00E-04 Epoch: 4, Train_acc:97.9%, Train_loss:0.073, Test_acc:91.1%, Test_loss:0.297, Lr:1.00E-04 ... Epoch:18, Train_acc:99.7%, Train_loss:0.006, Test_acc:92.0%, Test_loss:0.297, Lr:1.00E-04 Epoch:19, Train_acc:99.9%, Train_loss:0.002, Test_acc:94.7%, Test_loss:0.204, Lr:1.00E-04 Epoch:20, Train_acc:99.9%, Train_loss:0.002, Test_acc:94.2%, Test_loss:0.212, Lr:1.00E-04 Done

5、结果可视化

5.1、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) # 打卡请带上时间戳，否则代码截图无效 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()

6、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
(0.9466666666666667, 0.20435180879150325)
版权声明: 本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若内容造成侵权/违法违规/事实不符，请联系邮箱：809451989@qq.com进行投诉反馈，一经查实，立即删除！
网站建设 2026/1/27 5:13:45

YOLOv8-Ultralytics 系列文章目录

YOLOv8-Ultralytics 系列文章目录 文章目录YOLOv8-Ultralytics 系列文章目录前言YOLOv8-Ultralytics 概述核心定位与优势核心技术架构YOLOv8-Ultralytics 源码讲解目标检测部分总结前言 YOLOv8是由Ultralytics公司（创始人也是YOLO系列核心作者Joseph Redmon的合作者…

作者头像 李华
网站建设 2026/1/26 7:48:05

自动化运维工程师之ansible启动rpcbind和nfs服务

通过 systemd 模块分别启动 rpcbind 和 nfs 服务，并设置它们为开机自启，是 NFS 服务部署中启动相关服务的典型配置。下面我会逐部分解析代码的含义、作用以及关键细节。 一、代码整体功能总结 这段代码包含两个独立的 systemd 模块任务，依次完…

作者头像 李华
网站建设 2026/1/26 3:06:43

数字供应链系统哪个好？2025 供应链系统推荐排名来了，八大供应链系统

当数字化转型从“可选项”变为“必选项”，S2B2B供应链系统已成为企业重构供应链竞争力的核心工具。无论是解决传统批发企业“订单传递慢、库存不清”的沉疴，还是支撑新兴跨境商家“多渠道协同、全链路合规”的需求，一款高效的供应链系统都能让…

作者头像 李华
网站建设 2026/1/26 17:34:01

M.I.B.终极指南：解锁汽车娱乐系统的隐藏功能

你是否曾经对车载系统的功能限制感到困扰？为什么高端汽车的原厂娱乐系统总是缺少你想要的功能？如果你的车辆使用的是Harman MHI2或MHIG系列娱乐系统，那么M.I.B.就是你的完美解决方案。这个开源工具就像一个汽车系统的"多功能工具"&…

作者头像 李华
网站建设 2026/1/26 22:43:12

终极PHP兼容性检查工具：轻松应对版本迁移挑战

终极PHP兼容性检查工具：轻松应对版本迁移挑战 【免费下载链接】PHPCompatibility PHPCompatibility/PHPCompatibility: PHPCompatibility是一个针对PHP代码进行兼容性检查的Composer库，主要用于PHP版本迁移时确保现有代码能够适应新版本的PHP语言特性&am…

作者头像 李华