pytorch(九）：YOLOv5-Backbone模块实现

  本文为365天深度学习训练营 中的学习记录博客

  参考文章：365天深度学习训练营-第P9周：YOLOv5-C3模块实现（训练营内部成员可读）

  原作者：K同学啊|接辅导、项目定制

 

        YOLOv5是目标检测算法，本次课题尝试将其网络结构用在目标识别上，或进行改进形成一个全新的算法。下图为YOLOv5_6.0版本的算法框架图。

 

1 开发环境

电脑系统：ubuntu16.04

编译器：Jupter Lab

语言环境：Python 3.7

深度学习环境：Pytorch

2 前期准备

2.1 设置GPU

        如果设备上支持GPU就使用GPU，否则使用CPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib, warnings
 
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
print(device)

 

2.2 导入数据

import os,PIL,random,pathlib
data_dir_str = 'data/3-data/'
data_dir = pathlib.Path(data_dir_str)
print("data_dir:", data_dir, "\n")
 
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split('/')[-1] for path in data_paths]
print('classNames:', classNames , '\n')
 
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # resize输入图片
    transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换成tensor
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 从数据集中随机抽样计算得到
])
 
total_data = datasets.ImageFolder(data_dir_str, transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)

        结果输出如下：

  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])
print(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

        结果输出如下：

 3 搭建包含Backbone模块的模型  

 3.1 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 SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, 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')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
"""
这个是YOLOv5, 6.0版本的主干网络，这里进行复现
（注：有部分删改，详细讲解将在后续进行展开）
"""
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)
        
        # 全连接网络层，用于分类
        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
 
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
    
model = YOLOv5_backbone().to(device)
model

        结果输出如下：

  3.2 查看模型详情

import torchsummary as summary
summary.summary(model, (3, 224, 224))

        结果输出如下：

 

 

4 训练模型

4.1 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
    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pred和真实值y之间的差距，y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 编写测试函数

# 训练循环
def train(dataloader, model, loss_fn):
    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
    
    # 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:  # 获取图片及其标签
            imgs, target = imgs.to(device), target.to(device)
        
            # 计算误差
            tartget_pred = model(imgs)          # 网络输出
            loss = loss_fn(tartget_pred, target)  # 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
        
            # 记录acc与loss
            test_loss += loss.item()
            test_acc  += (tartget_pred.argmax(1) == target).type(torch.float).sum().item()
            
    train_acc  /= size
    train_loss /= num_batches
 
    return train_acc, train_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 = 60
 
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

if hasattr(torch.cuda, 'empty_cache'):
    torch.cuda.empty_cache()
 
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))
 
PATH = './P9_best_model.pth'
torch.save(model.state_dict(), PATH)
 
 
print('Done')

        结果输出如下：

5 结果可视化

5.1 Loss与Accuracy图

import matplotlib.pyplot as plt
 
import warnings
warnings.filterwarnings('ignore')
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
 
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()

        输出结果如下：

 5.2 模型评估 

best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
print(epoch_test_acc, epoch_test_loss)
print(epoch_test_acc)

        输出结果如下：