第P9周：YOLOv5-Backbone模块实现

计算机真好丸

已于 2024-09-12 17:17:57 修改

阅读量488

点赞数 5

文章标签：深度学习人工智能 YOLO 算法 pytorch

于 2024-09-12 17:15:07 首次发布

本文链接：https://blog.csdn.net/weixin_52447211/article/details/142180512

版权

文章目录

一、前期准备
- 2.导入数据
- 3.划分数据集
二、搭建包含Backbone模块的模型
- 1.搭建模型
- 2.查看模型详情
三、训练模型
四、结果可视化
- 1.Loss与Accuracy图
五、总结：

🍨 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

一、前期准备

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")      ## 忽略警告信息

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

输出：

device(type='cpu')

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]  ## 手动划分
## classeNames

classeNames = [path.name for path in data_paths if path.is_dir()]  ## 仅提取子目录的名字
classeNames

输出：

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

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    ## transforms.RandomHorrizontalFlip(),
    transforms.ToTensor(),            ## 将PIL Image或numpy.ndarray转换为tensor并归一化到[0,1]之间
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])
])

test_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])
    
])

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

输出：

  Dataset ImageFolder
    Number of datapoints: 1125
    Root location: ./weather_photos
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

total_data.class_to_idx

输出：

{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}

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])  
train_dataset, test_dataset

输出：

(<torch.utils.data.dataset.Subset at 0x149bfe230>,
 <torch.utils.data.dataset.Subset at 0x149bfe440>)

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)       ##ToDo
    break

输出：

Shape of X [N, C, H, W,]:  torch.Size([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64

二、搭建包含Backbone模块的模型

1.搭建模型

在这里插入图片描述

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(分组卷积（groups），默认为 1，表示标准卷积。如果 g 大于 1，则表示进行分组卷积。)
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)   ## bias=False:不使用偏置，因为批归一化层后通常不需要偏置。
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
        ## 如果act是一个nn.Module实例，则直接使用传入的激活函数。如果act参数为False或者未识别的值，则使用 nn.Indentity()即不做任何激活
        
    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(expansion ratio:用来调整瓶颈中的中间通道数)    
        super().__init__()
        c_ = int(c2 * e)        ## hidden channels, 减少中间层的计算量
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2         ## self.add 是一个布尔值，决定是否在前向传播时使用快捷连接。如果 shortcut 参数为 True，并且 c1 等于 c2（即输入和输出的通道数相同），则 self.add 为 True。
        
    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, 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)))
        ## self.m 是一个由多个 Bottleneck 组成的模块，Bottleneck 是前面定义的瓶颈层。n 是 Bottleneck 模块的重复次数。
        
    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
        ## 将 self.m(self.cv1(x)) 和 self.cv2(x) 的输出在通道维度上（即第 1 维）进行拼接
        
class SPPF(nn.Module):
    ## Spatital 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(将输入的通道数 c1 减半，得到 c_，减少计算量)
        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)  ## 当k为偶数时，padding=k // 2不能保证输出特征图的尺寸和输入特征图的尺寸一致
    
    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')   ## suppress torch 1.9.0 max_pool2d()
            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)   ##(ch_in, ch_out, kernel_size, stride, padding)
        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

输出：

Using cpu device





YOLOv5_backbone(
  (Conv_1): Conv(
    (conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(2, 2), bias=False)
    (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (Conv_2): Conv(
    (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_3): C3(
    (cv1): Conv(
      (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_4): Conv(
    (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_5): C3(
    (cv1): Conv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_6): Conv(
    (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_7): C3(
    (cv1): Conv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_8): Conv(
    (conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_9): C3(
    (cv1): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (SPPF): SPPF(
    (cv1): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=65536, out_features=100, bias=True)
    (1): ReLU()
    (2): Linear(in_features=100, out_features=4, bias=True)
  )
)

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))

输出：

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1         [-1, 64, 113, 113]           1,728
       BatchNorm2d-2         [-1, 64, 113, 113]             128
              SiLU-3         [-1, 64, 113, 113]               0
              Conv-4         [-1, 64, 113, 113]               0
            Conv2d-5          [-1, 128, 57, 57]          73,728
       BatchNorm2d-6          [-1, 128, 57, 57]             256
              SiLU-7          [-1, 128, 57, 57]               0
              Conv-8          [-1, 128, 57, 57]               0
            Conv2d-9           [-1, 64, 57, 57]           8,192
      BatchNorm2d-10           [-1, 64, 57, 57]             128
             SiLU-11           [-1, 64, 57, 57]               0
             Conv-12           [-1, 64, 57, 57]               0
           Conv2d-13           [-1, 64, 57, 57]           4,096
      BatchNorm2d-14           [-1, 64, 57, 57]             128
             SiLU-15           [-1, 64, 57, 57]               0
             Conv-16           [-1, 64, 57, 57]               0
           Conv2d-17           [-1, 64, 57, 57]          36,864
      BatchNorm2d-18           [-1, 64, 57, 57]             128
             SiLU-19           [-1, 64, 57, 57]               0
             Conv-20           [-1, 64, 57, 57]               0
       Bottleneck-21           [-1, 64, 57, 57]               0
           Conv2d-22           [-1, 64, 57, 57]           8,192
      BatchNorm2d-23           [-1, 64, 57, 57]             128
             SiLU-24           [-1, 64, 57, 57]               0
             Conv-25           [-1, 64, 57, 57]               0
           Conv2d-26          [-1, 128, 57, 57]          16,384
      BatchNorm2d-27          [-1, 128, 57, 57]             256
             SiLU-28          [-1, 128, 57, 57]               0
             Conv-29          [-1, 128, 57, 57]               0
               C3-30          [-1, 128, 57, 57]               0
           Conv2d-31          [-1, 256, 29, 29]         294,912
      BatchNorm2d-32          [-1, 256, 29, 29]             512
             SiLU-33          [-1, 256, 29, 29]               0
             Conv-34          [-1, 256, 29, 29]               0
           Conv2d-35          [-1, 128, 29, 29]          32,768
      BatchNorm2d-36          [-1, 128, 29, 29]             256
             SiLU-37          [-1, 128, 29, 29]               0
             Conv-38          [-1, 128, 29, 29]               0
           Conv2d-39          [-1, 128, 29, 29]          16,384
      BatchNorm2d-40          [-1, 128, 29, 29]             256
             SiLU-41          [-1, 128, 29, 29]               0
             Conv-42          [-1, 128, 29, 29]               0
           Conv2d-43          [-1, 128, 29, 29]         147,456
      BatchNorm2d-44          [-1, 128, 29, 29]             256
             SiLU-45          [-1, 128, 29, 29]               0
             Conv-46          [-1, 128, 29, 29]               0
       Bottleneck-47          [-1, 128, 29, 29]               0
           Conv2d-48          [-1, 128, 29, 29]          32,768
      BatchNorm2d-49          [-1, 128, 29, 29]             256
             SiLU-50          [-1, 128, 29, 29]               0
             Conv-51          [-1, 128, 29, 29]               0
           Conv2d-52          [-1, 256, 29, 29]          65,536
      BatchNorm2d-53          [-1, 256, 29, 29]             512
             SiLU-54          [-1, 256, 29, 29]               0
             Conv-55          [-1, 256, 29, 29]               0
               C3-56          [-1, 256, 29, 29]               0
           Conv2d-57          [-1, 512, 15, 15]       1,179,648
      BatchNorm2d-58          [-1, 512, 15, 15]           1,024
             SiLU-59          [-1, 512, 15, 15]               0
             Conv-60          [-1, 512, 15, 15]               0
           Conv2d-61          [-1, 256, 15, 15]         131,072
      BatchNorm2d-62          [-1, 256, 15, 15]             512
             SiLU-63          [-1, 256, 15, 15]               0
             Conv-64          [-1, 256, 15, 15]               0
           Conv2d-65          [-1, 256, 15, 15]          65,536
      BatchNorm2d-66          [-1, 256, 15, 15]             512
             SiLU-67          [-1, 256, 15, 15]               0
             Conv-68          [-1, 256, 15, 15]               0
           Conv2d-69          [-1, 256, 15, 15]         589,824
      BatchNorm2d-70          [-1, 256, 15, 15]             512
             SiLU-71          [-1, 256, 15, 15]               0
             Conv-72          [-1, 256, 15, 15]               0
       Bottleneck-73          [-1, 256, 15, 15]               0
           Conv2d-74          [-1, 256, 15, 15]         131,072
      BatchNorm2d-75          [-1, 256, 15, 15]             512
             SiLU-76          [-1, 256, 15, 15]               0
             Conv-77          [-1, 256, 15, 15]               0
           Conv2d-78          [-1, 512, 15, 15]         262,144
      BatchNorm2d-79          [-1, 512, 15, 15]           1,024
             SiLU-80          [-1, 512, 15, 15]               0
             Conv-81          [-1, 512, 15, 15]               0
               C3-82          [-1, 512, 15, 15]               0
           Conv2d-83           [-1, 1024, 8, 8]       4,718,592
      BatchNorm2d-84           [-1, 1024, 8, 8]           2,048
             SiLU-85           [-1, 1024, 8, 8]               0
             Conv-86           [-1, 1024, 8, 8]               0
           Conv2d-87            [-1, 512, 8, 8]         524,288
      BatchNorm2d-88            [-1, 512, 8, 8]           1,024
             SiLU-89            [-1, 512, 8, 8]               0
             Conv-90            [-1, 512, 8, 8]               0
           Conv2d-91            [-1, 512, 8, 8]         262,144
      BatchNorm2d-92            [-1, 512, 8, 8]           1,024
             SiLU-93            [-1, 512, 8, 8]               0
             Conv-94            [-1, 512, 8, 8]               0
           Conv2d-95            [-1, 512, 8, 8]       2,359,296
      BatchNorm2d-96            [-1, 512, 8, 8]           1,024
             SiLU-97            [-1, 512, 8, 8]               0
             Conv-98            [-1, 512, 8, 8]               0
       Bottleneck-99            [-1, 512, 8, 8]               0
          Conv2d-100            [-1, 512, 8, 8]         524,288
     BatchNorm2d-101            [-1, 512, 8, 8]           1,024
            SiLU-102            [-1, 512, 8, 8]               0
            Conv-103            [-1, 512, 8, 8]               0
          Conv2d-104           [-1, 1024, 8, 8]       1,048,576
     BatchNorm2d-105           [-1, 1024, 8, 8]           2,048
            SiLU-106           [-1, 1024, 8, 8]               0
            Conv-107           [-1, 1024, 8, 8]               0
              C3-108           [-1, 1024, 8, 8]               0
          Conv2d-109            [-1, 512, 8, 8]         524,288
     BatchNorm2d-110            [-1, 512, 8, 8]           1,024
            SiLU-111            [-1, 512, 8, 8]               0
            Conv-112            [-1, 512, 8, 8]               0
       MaxPool2d-113            [-1, 512, 8, 8]               0
       MaxPool2d-114            [-1, 512, 8, 8]               0
       MaxPool2d-115            [-1, 512, 8, 8]               0
          Conv2d-116           [-1, 1024, 8, 8]       2,097,152
     BatchNorm2d-117           [-1, 1024, 8, 8]           2,048
            SiLU-118           [-1, 1024, 8, 8]               0
            Conv-119           [-1, 1024, 8, 8]               0
            SPPF-120           [-1, 1024, 8, 8]               0
          Linear-121                  [-1, 100]       6,553,700
            ReLU-122                  [-1, 100]               0
          Linear-123                    [-1, 4]             404
================================================================
Total params: 21,729,592
Trainable params: 21,729,592
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 137.59
Params size (MB): 82.89
Estimated Total Size (MB): 221.06
----------------------------------------------------------------

三、训练模型

1.编写训练函数

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
    
    train_loss, train_acc = 0, 0
    
    for X, y in dataloader:
        X, y = X.to(device), y.to(device)
        
        
        ## 计算误差
        pred = model(X)
        loss = loss_fn(pred, y)
        
        ## 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

2.编写测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)   ## 训练集的大小
    num_batches = len(dataloader)      ## 批次数目
    test_acc, test_loss = 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

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

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.pth'          ## 保存的参数文件名
torch.save(best_model.state_dict(), PATH)

print('Done')

输出：

Epoch: 1, Train_acc:53.8%, Train_loss:1.126, Test_acc:66.7%, Test_loss:0.705, Lr:1.00E-04
Epoch: 2, Train_acc:67.0%, Train_loss:0.814, Test_acc:75.6%, Test_loss:0.619, Lr:1.00E-04
Epoch: 3, Train_acc:74.0%, Train_loss:0.688, Test_acc:76.9%, Test_loss:0.445, Lr:1.00E-04
Epoch: 4, Train_acc:74.9%, Train_loss:0.616, Test_acc:81.3%, Test_loss:0.489, Lr:1.00E-04
Epoch: 5, Train_acc:79.4%, Train_loss:0.542, Test_acc:82.2%, Test_loss:0.494, Lr:1.00E-04
Epoch: 6, Train_acc:83.7%, Train_loss:0.430, Test_acc:85.8%, Test_loss:0.404, Lr:1.00E-04
Epoch: 7, Train_acc:83.0%, Train_loss:0.463, Test_acc:71.1%, Test_loss:0.867, Lr:1.00E-04
Epoch: 8, Train_acc:85.3%, Train_loss:0.349, Test_acc:87.6%, Test_loss:0.304, Lr:1.00E-04
Epoch: 9, Train_acc:87.7%, Train_loss:0.297, Test_acc:87.6%, Test_loss:0.337, Lr:1.00E-04
Epoch:10, Train_acc:89.1%, Train_loss:0.328, Test_acc:88.9%, Test_loss:0.343, Lr:1.00E-04
Epoch:11, Train_acc:90.2%, Train_loss:0.260, Test_acc:82.2%, Test_loss:0.657, Lr:1.00E-04
Epoch:12, Train_acc:90.0%, Train_loss:0.306, Test_acc:91.1%, Test_loss:0.259, Lr:1.00E-04
Epoch:13, Train_acc:90.7%, Train_loss:0.256, Test_acc:85.3%, Test_loss:0.351, Lr:1.00E-04
Epoch:14, Train_acc:92.7%, Train_loss:0.193, Test_acc:88.9%, Test_loss:0.267, Lr:1.00E-04
Epoch:15, Train_acc:90.8%, Train_loss:0.239, Test_acc:92.9%, Test_loss:0.250, Lr:1.00E-04
Epoch:16, Train_acc:92.4%, Train_loss:0.180, Test_acc:84.4%, Test_loss:0.488, Lr:1.00E-04
Epoch:17, Train_acc:94.8%, Train_loss:0.133, Test_acc:93.8%, Test_loss:0.258, Lr:1.00E-04
Epoch:18, Train_acc:93.6%, Train_loss:0.186, Test_acc:91.1%, Test_loss:0.217, Lr:1.00E-04
Epoch:19, Train_acc:98.1%, Train_loss:0.075, Test_acc:92.0%, Test_loss:0.240, Lr:1.00E-04
Epoch:20, Train_acc:92.1%, Train_loss:0.238, Test_acc:85.3%, Test_loss:0.485, Lr:1.00E-04
Epoch:21, Train_acc:90.6%, Train_loss:0.297, Test_acc:89.8%, Test_loss:0.335, Lr:1.00E-04
Epoch:22, Train_acc:96.9%, Train_loss:0.101, Test_acc:90.2%, Test_loss:0.354, Lr:1.00E-04
Epoch:23, Train_acc:94.8%, Train_loss:0.152, Test_acc:88.9%, Test_loss:0.277, Lr:1.00E-04
Epoch:24, Train_acc:96.9%, Train_loss:0.106, Test_acc:92.9%, Test_loss:0.299, Lr:1.00E-04
Epoch:25, Train_acc:97.3%, Train_loss:0.074, Test_acc:94.2%, Test_loss:0.217, Lr:1.00E-04
Epoch:26, Train_acc:97.9%, Train_loss:0.069, Test_acc:92.0%, Test_loss:0.235, Lr:1.00E-04
Epoch:27, Train_acc:99.0%, Train_loss:0.025, Test_acc:92.4%, Test_loss:0.264, Lr:1.00E-04
Epoch:28, Train_acc:97.1%, Train_loss:0.074, Test_acc:90.2%, Test_loss:0.467, Lr:1.00E-04
Epoch:29, Train_acc:93.6%, Train_loss:0.186, Test_acc:91.6%, Test_loss:0.287, Lr:1.00E-04
Epoch:30, Train_acc:94.8%, Train_loss:0.131, Test_acc:90.7%, Test_loss:0.347, Lr:1.00E-04
Epoch:31, Train_acc:98.4%, Train_loss:0.060, Test_acc:94.2%, Test_loss:0.267, Lr:1.00E-04
Epoch:32, Train_acc:98.0%, Train_loss:0.062, Test_acc:92.0%, Test_loss:0.264, Lr:1.00E-04
Epoch:33, Train_acc:98.3%, Train_loss:0.046, Test_acc:92.4%, Test_loss:0.261, Lr:1.00E-04
Epoch:34, Train_acc:98.8%, Train_loss:0.044, Test_acc:95.1%, Test_loss:0.215, Lr:1.00E-04
Epoch:35, Train_acc:96.6%, Train_loss:0.101, Test_acc:94.2%, Test_loss:0.203, Lr:1.00E-04
Epoch:36, Train_acc:97.7%, Train_loss:0.082, Test_acc:91.6%, Test_loss:0.313, Lr:1.00E-04
Epoch:37, Train_acc:97.1%, Train_loss:0.091, Test_acc:89.8%, Test_loss:0.334, Lr:1.00E-04
Epoch:38, Train_acc:98.6%, Train_loss:0.052, Test_acc:93.3%, Test_loss:0.261, Lr:1.00E-04
Epoch:39, Train_acc:97.1%, Train_loss:0.086, Test_acc:92.0%, Test_loss:0.291, Lr:1.00E-04
Epoch:40, Train_acc:97.0%, Train_loss:0.076, Test_acc:84.4%, Test_loss:0.540, Lr:1.00E-04
Epoch:41, Train_acc:97.0%, Train_loss:0.094, Test_acc:88.0%, Test_loss:0.390, Lr:1.00E-04
Epoch:42, Train_acc:99.0%, Train_loss:0.024, Test_acc:92.9%, Test_loss:0.223, Lr:1.00E-04
Epoch:43, Train_acc:99.6%, Train_loss:0.011, Test_acc:93.3%, Test_loss:0.218, Lr:1.00E-04
Epoch:44, Train_acc:99.6%, Train_loss:0.019, Test_acc:89.3%, Test_loss:0.342, Lr:1.00E-04
Epoch:45, Train_acc:98.6%, Train_loss:0.055, Test_acc:93.3%, Test_loss:0.273, Lr:1.00E-04
Epoch:46, Train_acc:99.6%, Train_loss:0.019, Test_acc:94.2%, Test_loss:0.238, Lr:1.00E-04
Epoch:47, Train_acc:99.9%, Train_loss:0.008, Test_acc:93.8%, Test_loss:0.193, Lr:1.00E-04
Epoch:48, Train_acc:99.8%, Train_loss:0.008, Test_acc:93.8%, Test_loss:0.298, Lr:1.00E-04
Epoch:49, Train_acc:99.8%, Train_loss:0.016, Test_acc:88.4%, Test_loss:0.376, Lr:1.00E-04
Epoch:50, Train_acc:96.7%, Train_loss:0.128, Test_acc:88.4%, Test_loss:0.345, Lr:1.00E-04
Epoch:51, Train_acc:95.7%, Train_loss:0.134, Test_acc:90.7%, Test_loss:0.387, Lr:1.00E-04
Epoch:52, Train_acc:98.9%, Train_loss:0.032, Test_acc:92.0%, Test_loss:0.282, Lr:1.00E-04
Epoch:53, Train_acc:99.9%, Train_loss:0.007, Test_acc:94.2%, Test_loss:0.261, Lr:1.00E-04
Epoch:54, Train_acc:99.8%, Train_loss:0.009, Test_acc:95.1%, Test_loss:0.261, Lr:1.00E-04
Epoch:55, Train_acc:98.3%, Train_loss:0.045, Test_acc:93.3%, Test_loss:0.338, Lr:1.00E-04
Epoch:56, Train_acc:97.7%, Train_loss:0.095, Test_acc:92.4%, Test_loss:0.285, Lr:1.00E-04
Epoch:57, Train_acc:97.6%, Train_loss:0.083, Test_acc:91.1%, Test_loss:0.325, Lr:1.00E-04
Epoch:58, Train_acc:99.1%, Train_loss:0.026, Test_acc:92.4%, Test_loss:0.295, Lr:1.00E-04
Epoch:59, Train_acc:99.2%, Train_loss:0.033, Test_acc:94.2%, Test_loss:0.257, Lr:1.00E-04
Epoch:60, Train_acc:99.3%, Train_loss:0.019, Test_acc:93.3%, Test_loss:0.278, Lr:1.00E-04
Done

四、结果可视化

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
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()

输出：
在这里插入图片描述

2.模型评估

## 将参数加载到model当中
best_model.load_state_dict(torch.load(PATH, map_location=device))
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)

epoch_test_acc, epoch_test_loss

输出：

(0.9511111111111111, 0.214860527808387)

五、总结：

本周主要通过代码学习了解了YOLOv5中Backbone模块的结构。
其中学习到了一个新的模块——SPPF(Spatial Pyramid Pooling)，一种用于图像识别和目标检测的技术，其作用是在不同尺度下对图像进行特征提取和编码，它可以将任意大小的输入图像重新缩放到固定大小，并生成固定长度的特征向量。这种方法可以提高模型对目标位置和大小变化的鲁棒性。