第P8周：YOLOv5-C3模块实现

>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/0dvHCaOoFnW8SCp3JpzKxg) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

• 语言环境：Python3.8
• 编译器：Jupyter Lab
• 深度学习环境：
  • torch==2.3.1+cpu
  • torchvision==0.18.1+cpu

目录

1. 前期准备 

  1. 1设置cpu： 

 1.2 导入数据

  1.3 划分数据集

2. 搭建包含C模块的模型 

2.1 搭建模型 

2.2 查看模型详情 

三. 训练模型 

    3.1 编写训练函数

  3.2 编写测试函数

  3.3 正式训练

 4. 结果可视化

  4.1 Loss 与 Accuracy 图

4.2 模型评估

---

1. 前期准备 

  1. 1设置cpu： 

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

device

代码输出： 

device(type='cpu')

 1.2 导入数据

import os,PIL,random,pathlib

data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames

代码输出： 

['cloudy', 'rain', 'shine', 'sunrise']

# 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。
])

total_data = datasets.ImageFolder("./weather_photos/",transform=train_transforms)
total_data

  1.3 划分数据集

# train_size表示训练集大小，通过将总体数据长度的80%转换为整数得到；
# test_size表示测试集大小，是总体数据长度减去训练集大小。
train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size

# 使用torch.utils.data.random_split()方法进行数据集划分。该方法将总体数据total_data按照指定的大小比例（[train_size, test_size]）随机划分为训练集和测试集，
# 并将划分结果分别赋值给train_dataset和test_dataset两个变量。
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])

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

2. 搭建包含C模块的模型 

2.1 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)
model

2.2 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))

3. 训练模型 

    3.1 编写训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)   # 批次数目，1875（60000/32）

    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

  3.2 编写测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片
    num_batches = len(dataloader)          # 批次数目，313（10000/32=312.5，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

  3.3 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 = './best_model_8.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

print('Done')

代码输出：

Epoch: 1, Train_acc:70.6%, Train_loss:1.395, Test_acc:90.7%, Test_loss:0.458, Lr:1.00E-04
Epoch: 2, Train_acc:86.7%, Train_loss:0.407, Test_acc:88.4%, Test_loss:0.792, Lr:1.00E-04
Epoch: 3, Train_acc:94.3%, Train_loss:0.202, Test_acc:89.8%, Test_loss:0.692, Lr:1.00E-04
Epoch: 4, Train_acc:96.0%, Train_loss:0.153, Test_acc:88.0%, Test_loss:0.726, Lr:1.00E-04
Epoch: 5, Train_acc:96.7%, Train_loss:0.137, Test_acc:89.8%, Test_loss:0.475, Lr:1.00E-04
Epoch: 6, Train_acc:98.1%, Train_loss:0.063, Test_acc:88.9%, Test_loss:0.745, Lr:1.00E-04
Epoch: 7, Train_acc:98.3%, Train_loss:0.044, Test_acc:89.8%, Test_loss:0.608, Lr:1.00E-04
Epoch: 8, Train_acc:98.7%, Train_loss:0.051, Test_acc:93.3%, Test_loss:0.743, Lr:1.00E-04
Epoch: 9, Train_acc:97.9%, Train_loss:0.087, Test_acc:89.8%, Test_loss:1.218, Lr:1.00E-04
Epoch:10, Train_acc:97.1%, Train_loss:0.130, Test_acc:89.3%, Test_loss:0.801, Lr:1.00E-04
Epoch:11, Train_acc:99.1%, Train_loss:0.037, Test_acc:92.0%, Test_loss:0.747, Lr:1.00E-04
Epoch:12, Train_acc:99.3%, Train_loss:0.014, Test_acc:92.0%, Test_loss:0.642, Lr:1.00E-04
Epoch:13, Train_acc:98.2%, Train_loss:0.065, Test_acc:88.4%, Test_loss:0.881, Lr:1.00E-04
Epoch:14, Train_acc:98.2%, Train_loss:0.053, Test_acc:92.4%, Test_loss:0.857, Lr:1.00E-04
Epoch:15, Train_acc:99.2%, Train_loss:0.044, Test_acc:88.4%, Test_loss:0.646, Lr:1.00E-04
Epoch:16, Train_acc:99.2%, Train_loss:0.017, Test_acc:88.4%, Test_loss:0.811, Lr:1.00E-04
Epoch:17, Train_acc:100.0%, Train_loss:0.003, Test_acc:91.1%, Test_loss:0.743, Lr:1.00E-04
Epoch:18, Train_acc:99.8%, Train_loss:0.004, Test_acc:93.3%, Test_loss:0.544, Lr:1.00E-04
Epoch:19, Train_acc:96.2%, Train_loss:0.230, Test_acc:88.4%, Test_loss:1.133, Lr:1.00E-04
Epoch:20, Train_acc:97.8%, Train_loss:0.078, Test_acc:93.3%, Test_loss:0.918, Lr:1.00E-04
Done

 4. 结果可视化

  4.1 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

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.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()

代码输出：

4.2 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

代码输出：

(0.9333333333333333, 0.7428147030978105)

个人碎碎念： 

        这周通过手动搭建包含C模块的模型，有点难度，勉强还能接受的了……