第八周：YOLOV5-C3模块实现

🏡 我的环境：

语言环境：Python3.87
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
from torchvision import transforms, datasets
import torchvision
import os, PIL, pathlib, warnings

warnings.filterwarnings('ignore')
device = 'cuda' if torch.cuda.is_available() else 'cpu'
device

1.2 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('*'))
print(data_paths)
classname = [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('./8-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 = 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)

2 搭建包含C3模块的模型

2.1 搭建模型

import torch.nn as nn

def autpad(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] # autpad
    return p

    
class Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): #c1:ch_in, c2:ch_out, k:kernel_size, s:stride, p:padding,g:groups
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autpad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
         # 这段代码的作用是根据条件选择不同的激活函数。
        # 如果act为True，则使用nn.SiLU()作为激活函数；如果act是一个自定义的激活函数模块，则使用该模块作为激活函数；否则，使用nn.Identity()作为激活函数，即不进行任何操作。
        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): # 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):
    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) # 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)
        
        # 全连接层，用于分类
        self.classfier = nn.Sequential(
            nn.Linear(in_features=802816, out_features=100),
            nn.ReLU(),
            nn.Linear(in_features=100, out_features=2)
        )
    def forward(self, x):
        x = self.Conv(x)
        x = self.C3_1(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classfier(x)
        
        return x
model = model_K().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 编写训练模型

def train(dataloader, model, loss_fun, optimizer):
    size = len(dataloader.dataset)
    num_batchsize = len(dataloader)
    
    train_acc, train_loss = 0, 0
    for x, y in dataloader:
        x, y = x.to(device), y.to(device)
        
        # 计算预测值和预测误差
        pred = model(x)
        loss = loss_fun(pred, y)
        
        # 反向传播
        optimizer.zero_grad() # grad属性归零
        loss.backward() # 反向传播
        optimizer.step()  # 更新参数
        
        # 计算loss与acc
        train_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
        train_loss += loss.item()
    
    train_acc /= size
    train_loss /= num_batchsize
    return train_acc, train_loss

3.2 编写测试函数

def test(dataloader, model, loss_fun):
    
    size = len(dataloader.dataset)
    num_batchsize = len(dataloader)
    
    test_acc, test_loss = 0, 0
    for x, y in dataloader:
        x, y = x.to(device), y.to(device)
        
       # 计算loss
        pred = model(x)
        loss = loss_fun(pred, y)
        
        test_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
        test_loss += loss.item()
    
    test_acc /= size
    test_loss /= num_batchsize
    
    return test_acc, test_loss

3.3 正式训练

import copy

optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
loss_fun = nn.CrossEntropyLoss()

epochs = 20

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

best_acc = 0 #设置一个最佳准确率，作为最佳模型的判别标准

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fun, optimizer)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fun)
    
    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
#     print(optimizer.state_dict())
    lr = optimizer.state_dict()['param_groups'][0]['lr']
    template = ('Epoch:{:2d}, Train_acc:{:.1f}, Train_loss:{:.2f}, Test_acc:{:.1f}, Test_lossL{:.2f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr))

path = './best_model.pth'
torch.save(model.state_dict(), path)
print('Done')
    

4 结果可视化

4.1 Loss 与 Accuracy图

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['figure.dpi'] = 100

plt.figure(figsize=(12,3))
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

est_model.eval()
epoch_test_acc_e, epoch_test_loss_e = test(test_dl, best_model, loss_fun)
epoch_test_acc_e, epoch_test_loss_e

# 查看是否与我们记录的最高准确率一致
best_acc