【深度学习打卡】第9周：YOLOv5-Backbone模块实现

🏡 我的环境：

语言环境：Python3.8.7
编译器：Jupyter notebook
深度学习环境：Pytorch
torch == 2.0.1+cu117
torchvision == 0.15.2+cu117

1 前期准备

1.1 设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import datasets
import os,PIL,pathlib
device = 'cuda' if torch.cuda.is_available() else 'cpu'
device

1.2 导入数据

import os,PIL,random,pathlib
data_dir = './9-data/'
data_dir = pathlib.Path(data_dir)
data_paths=list(data_dir.glob('*'))
classNames = [str(path).split('\\')[1] for path in data_paths]
data_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('./9-data/', transform=data_transform)
total_data

1.3 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])
batch_size = 5
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)

2 搭建包含Backbone模块的模型

2.1 搭建模型

import torch.nn.functional as F
import warnings
def autopad(k, p=None):
    # pad to 'same'
    if p is None:
        p = k//2 if isinstance(k, int) else [x//2 for x in k]
    return p

class Conv(nn.Module):
    # 标准卷积
    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=1, 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 SPPF(nn.Module):
    def __init__(self, c1, c2, k=5):
        super().__init__()
        c_ = c1//2
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(4*c_, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k//2)
    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

class YOLOv5_backbone(nn.Module):
    def __init__(self):
        super(YOLOv5_backbone,self).__init__()
        self.conv_1 = Conv(3, 64, 3, 2, 2)
        self.conv_2 = Conv(64, 128, 3, 2)
        self.C3_3 = C3(128, 128)
        self.conv_4 = Conv(128, 256, 3, 2)
        self.C3_5 = C3(256, 256)
        self.conv_6 = Conv(256, 512, 3, 2)
        self.C3_7 = C3(512, 512)
        self.conv_8 = Conv(512, 1024, 3, 2)
        self.C3_9 = C3(1024, 1024)
        self.SPPF = SPPF(1024, 1024, 5)
        
        self.Classifier = nn.Sequential(
            nn.Linear(in_features=65536, out_features=100),
            nn.ReLU(),
            nn.Linear(in_features=100, out_features=4)
        )
    def forward(self, x):
        x = self.conv_1(x)
        x = self.conv_2(x)
        x = self.C3_3(x)
        x = self.conv_4(x)
        x = self.C3_5(x)
        x = self.conv_6(x)
        x = self.C3_7(x)
        x = self.conv_8(x)
        x = self.C3_9(x)
        x = self.SPPF(x)
        
        x = torch.flatten(x, start_dim=1)
        x = self.Classifier(x)
        return x

model = YOLOv5_backbone().to(device)
model```

## 2.2  查看模型详情

import torchsummary as summary
summary.summary(model, (3,224,224))
``‘’

3 训练模型

3.1 编写训练函数

def train(dataloader, model, loss_fun, optimizer):
    size = len(dataloader.dataset) # 训练集的大小
    num_batches = len(dataloader) # 每个batch的数目（size/batch_size）
    
    train_acc, train_loss = 0, 0
    for x,y in dataloader:
        x, y = x.to(device), y.to(device)
        
        pred_y = model(x)
        # 计算误差
        loss = loss_fun(pred_y, y) 
        
        # 反向传播
        optimizer.zero_grad() # grad属性归零
        loss.backward() # 反向传播
        optimizer.step()  # 自动更新梯度
        
        # 记录acc与loss
        train_acc += (pred_y.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_fun):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    
    test_acc, test_loss = 0, 0
    # 不进行梯度更新
    with torch.no_grad():
        for x,y in dataloader:
            x, y = x.to(device), y.to(device)
            pred = model(x)
            loss = loss_fun(pred, y)
            
            test_loss += loss.item()
            test_acc += (pred.argmax(1)==y).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
# 创建损失函数
loss_fun = nn.CrossEntropyLoss()
# 创建优化器
optimizer = torch.optim.Adam(model.parameters(),lr=1e-4)

epochs = 50
train_acc = []
train_loss = []
test_acc = []
test_loss = []
best_acc = 0
for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fun, optim)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fun)
    
    # 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)
    
    # 获得当前学习率
    lr = optimizer.state_dict()['param_groups'][0]['lr']
    
    template = ('Epoch:{:2d}, train_acc:{:.2f}, train_loss:{:.2f}, test_acc:{:.2f}, test_loss:{:.2f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))

# 保存最佳模型到文件中
Path = './best_model.pth'
torch.save(best_model.state_dict(), Path)
print('Done!')

4 结果可视化

4.1 Loss 与 Accuracy

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正确显示负号

plt.figure(figsize=(12,3))  #设置画布大小
# 子图1
plt.subplot(1,2,1)
plt.plot(range(epochs), train_acc, label='Training Accuracy')
plt.plot(range(epochs), test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1,2,2)
plt.plot(range(epochs), train_loss, label='Training loss')
plt.plot(range(epochs), test_loss, label='Test loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')

plt.show()

4.2 模型评估

# 将参数加载到model中
best_model.load_state_dict(torch.load(Path, map_location=device))
test_acc, test_loss = test(test_dl, best_model, loss_fun)