第P9周：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
• 🍖 原作者：K同学啊

• 我的环境：
  • 操作系统：CentOS7
  • 显卡：RTX3090
  • 显卡驱动：535.154.05
  • CUDA版本: 12.2
  • 语言环境：Python3.10
  • 编译器：Jupyter Lab
  • 深度学习环境：
    • torch==12.1
    • torchvision==0.18.1

一、前期准备

1. 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,warnings

warnings.filterwarnings("ignore")             #忽略警告信息

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

device(type='cuda')

2. 导入数据

import os,PIL,random,pathlib

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

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

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

# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.RandomHorizontalFlip(), # 随机水平翻转
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

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

Dataset ImageFolder
    Number of datapoints: 1125
    Root location: ./data/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
               RandomHorizontalFlip(p=0.5)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

total_data.class_to_idx

{'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

(<torch.utils.data.dataset.Subset at 0x7f04a79fdd20>,
 <torch.utils.data.dataset.Subset at 0x7f03beee5b40>)

batch_size = 12

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

Shape of X [N, C, H, W]:  torch.Size([12, 3, 224, 224])
Shape of y:  torch.Size([12]) torch.int64

二、搭建包含Backbone模块的模型

1. 模型搭建

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

Using cuda 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

# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))

----------------------------------------------------------------
        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

# 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)  # 计算网络输出和真实值之间的差距，targets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

2. 编写测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小
    num_batches = len(dataloader)          # 批次数目, (size/batch_size，向上取整)
    test_loss, test_acc = 0, 0
    
    # 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:
            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

def tran_my_model(train_dl, test_dl, model, loss_fn, optimizer, epochs = 40, out_best_model = "best_model.pth"):
        
    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
    
    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))
  
    torch.save(model.state_dict(), out_best_model)
    return [best_model, train_loss, test_loss, train_acc, test_acc]

model = YOLOv5_backbone().to(device)
optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数

adam_out = tran_my_model(train_dl, test_dl, model, loss_fn, optimizer, epochs = 20, out_best_model = "best_model.optim_Adam.pth")
adam_best_model, adam_train_loss, adam_test_loss, adam_train_acc, adam_test_acc = adam_out

Epoch: 1, Train_acc:62.1%, Train_loss:1.003, Test_acc:69.3%, Test_loss:0.507, Lr:1.00E-04
Epoch: 2, Train_acc:70.3%, Train_loss:0.690, Test_acc:80.0%, Test_loss:0.400, Lr:1.00E-04
Epoch: 3, Train_acc:78.1%, Train_loss:0.597, Test_acc:88.0%, Test_loss:0.374, Lr:1.00E-04
Epoch: 4, Train_acc:86.0%, Train_loss:0.375, Test_acc:90.7%, Test_loss:0.277, Lr:1.00E-04
Epoch: 5, Train_acc:85.6%, Train_loss:0.397, Test_acc:93.8%, Test_loss:0.212, Lr:1.00E-04
Epoch: 6, Train_acc:86.4%, Train_loss:0.360, Test_acc:91.6%, Test_loss:0.241, Lr:1.00E-04
Epoch: 7, Train_acc:89.7%, Train_loss:0.294, Test_acc:86.2%, Test_loss:0.352, Lr:1.00E-04
Epoch: 8, Train_acc:91.7%, Train_loss:0.260, Test_acc:94.7%, Test_loss:0.206, Lr:1.00E-04
Epoch: 9, Train_acc:91.3%, Train_loss:0.233, Test_acc:89.8%, Test_loss:0.306, Lr:1.00E-04
Epoch:10, Train_acc:92.3%, Train_loss:0.241, Test_acc:96.9%, Test_loss:0.169, Lr:1.00E-04
Epoch:11, Train_acc:91.0%, Train_loss:0.255, Test_acc:91.1%, Test_loss:0.241, Lr:1.00E-04
Epoch:12, Train_acc:91.9%, Train_loss:0.227, Test_acc:93.3%, Test_loss:0.226, Lr:1.00E-04
Epoch:13, Train_acc:94.0%, Train_loss:0.181, Test_acc:92.0%, Test_loss:0.306, Lr:1.00E-04
Epoch:14, Train_acc:92.4%, Train_loss:0.215, Test_acc:89.3%, Test_loss:0.267, Lr:1.00E-04
Epoch:15, Train_acc:95.4%, Train_loss:0.116, Test_acc:94.7%, Test_loss:0.209, Lr:1.00E-04
Epoch:16, Train_acc:94.3%, Train_loss:0.160, Test_acc:95.1%, Test_loss:0.206, Lr:1.00E-04
Epoch:17, Train_acc:95.9%, Train_loss:0.115, Test_acc:92.9%, Test_loss:0.237, Lr:1.00E-04
Epoch:18, Train_acc:94.0%, Train_loss:0.145, Test_acc:95.1%, Test_loss:0.166, Lr:1.00E-04
Epoch:19, Train_acc:94.7%, Train_loss:0.158, Test_acc:96.0%, Test_loss:0.143, Lr:1.00E-04
Epoch:20, Train_acc:96.6%, Train_loss:0.114, Test_acc:95.6%, Test_loss:0.176, Lr:1.00E-04

四、 结果可视化

1. Loss与Accuracy图

import matplotlib.pyplot as plt
import warnings

def plot_acc_loss(epoch_acc, epoch_loss):
    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      # 用来正常显示负号
    plt.rcParams['figure.dpi']         = 100        #分辨率

    train_acc, test_acc = epoch_acc
    train_loss, test_loss = epoch_loss

    epochs_range = range(len(train_acc))

    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()

plot_acc_loss([adam_train_acc, adam_test_acc], [adam_train_loss, adam_test_loss])

2. 模型评估

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

epoch_test_acc, epoch_test_loss

(0.96, 0.20603143105185345)

五、 总结

• 由于对于YOLO v3和v4不了解，直接上手v5，感觉有点吃力。下一阶段需要从YOLO框架最基础的地方开始学习。