第P8周：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 | 接辅导、项目定制
• 🚀 文章来源：K同学的学习圈子

我的环境

语言环境：Python3.8
●编译器：Jupyter Lab
●深度学习环境：
○torch1.12.1+cu113
○torchvision0.13.1+cu113

一、前期准备

1.引入Python库+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

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

二、数据处理

1.数据集导入

import os,PIL,random,pathlib

data_dir = './data/P7/'
data_dir = pathlib.Path(data_dir)

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

2.数据处理

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  
    transforms.ToTensor(),          
    transforms.Normalize(           
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]),  
    transforms.ToTensor(),          
    transforms.Normalize(           
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  
])

total_data = datasets.ImageFolder("./data/P7/",transform=train_transforms)
total_data

其中’data’代表文件地址、download表示是否允许下载，transform=torchvision.transforms.ToTensor()将数据转化为Tensor类型表示。

3.数据划分

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 = 32
train_dl = torch.utils.data.DataLoader(train_ds,
                                       batch_size=batch_size,
                                       shuffle=True)
test_dl = torch.utils.data.DataLoader(test_ds,
                                      batch_size=batch_size)
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])
batch_size = 32

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)

torch.utils.data.DataLoader 对数据进行 batch 的划分。
可以快速生成迭代数据

三、网络

1.Vgg16网络构建

import torch.nn.functional as F

def autopad(k, p=None): 
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k] 
    return p

class Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  
        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):
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)  
        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):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): 
        super().__init__()
        c_ = int(c2 * e) 
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  
        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__()
        
        self.Conv = Conv(3, 32, 3, 2) 
        
        self.C3_1 = C3(32, 64, 3, 2)
        
        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

三、训练与测试函数

1.动态学习率（调用接口）

 lambda1 = lambda epoch: 0.92 ** (epoch // 4)
optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1)

2.训练函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset) 
    num_batches = len(dataloader)  

    train_loss, train_acc = 0, 0 
    
    for X, y in dataloader: 
        X, y = X.to(device), y.to(device)
        

        pred = model(X)          
        loss = loss_fn(pred, y)  
        
       
        optimizer.zero_grad()  
        loss.backward()        
        optimizer.step()       
        

        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.测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset) 
    num_batches = len(dataloader)         
    test_loss, test_acc = 0, 0
    

    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

四、训练

import copy

loss_fn    = nn.CrossEntropyLoss()
epochs     = 40

train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

best_acc = 0  

for epoch in range(epochs):

    
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
    scheduler.step() 
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    

    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)
    

    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))
    

PATH = './P6_model.pth'  
torch.save(model.state_dict(), PATH)

print('Done')

五、可视化分析

import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif']    = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['figure.dpi']         = 100

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()

六、总结

没太搞懂YOLO框架，打算之后系统性学习一下