第P9周：YOLOv5-Backbone模块实现

夏伊呀

于 2023-09-29 21:53:32 发布

阅读量98

点赞数

文章标签： YOLO

本文链接：https://blog.csdn.net/weixin_54533484/article/details/133420596

版权

🍨 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 | 接辅导、项目定制
🚀 文章来源：K同学的学习圈子

一、前期准备

文章目录

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")            

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

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('*'))
classNames = [str(path).split("\\")[1] for path in data_paths]
print(classNames)

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

train_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])
])

test_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("./data/",transform=train_transforms)
print(total_data)

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

print(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])
print(train_dataset)
print(test_dataset)

<torch.utils.data.dataset.Subset object at 0x000001E029242820>
<torch.utils.data.dataset.Subset object at 0x000001E029320370>

batch_size = 4

train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True)

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([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64

二、搭建包含C3模块的模型

图片1.png

由以上图可以知：YOLOv5模型主要由：Backbone、Neck、Head(Prediction)组成，这里主要是实现其中的Backbone模块。

**Backbone:**是网络的主体，通常用于提取图像的特征。由Conv模块、C3模块、SPPF模块组成。

**Conv模块：**封装了一个标准的卷积层。

**C3模块：**C3模块是YOLOv5中的一个重要组成部分，两个Conv组成Bottleneck，以减少计算量和参数量，其中,在Bottleneck类中，还提供了一个简单的残差连接。在CSP Bottleneck类中，包括两个1x1的卷积层self.cv1、self.cv2，一个瓶颈层序列self.m，一个1x1的卷积层self.cv3（用来恢复通道数）。使得在保持复杂度的同时增加网络的容量和学习能力。

**SPPF模块：**在SPPF类中，通过多次最大池化层self.m和卷积层self.cv1、self.cv2来实现多尺度特征的捕获和组合。使得网络能够在不同的尺度上理解图像特征，从而提高网络的性能。

1.搭建模型

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


'''卷积层(Conv)类'''
class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
        super().__init__()  # 初始化nn.Module的父类，这是Pytorch中所有神经网络模块的基类
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)  # 2D卷积层
        self.bn = nn.BatchNorm2d(c2)  # 批量归一化层，用于加速训练并减少过拟合
        # 激活函数，SILU是Swish的一种变体
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

    def forward(self, x):
        # 数据流过程：卷积->批量归一化->激活函数
        return self.act(self.bn(self.conv(x)))

'''瓶颈层(Bottleneck)类'''
class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortout=True, g=1, e=0.5): # .. shortcut, group. expansion
        super().__init__()
        c_ = int(c2 * e)   # 计算中间通道数，这是为了减少计算量
        self.cv1 = Conv(c1, c_, 1, 1)       # 1x1 卷积， 减少通道数
        self.cv2 = Conv(c_, c2, 3, 1, g=g)  # 3x3卷积，回复通道数
        self.add = shortout and c1 == c2    # 判断是否需要进行残差连接

    def forward(self, x):
        # 残差连接或仅卷积
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

'''CSP Bottleneck层(C3)类'''
class C3(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)  # 计算中间通道数
        self.cv1 = Conv(c1, c_, 1, 1)   # 1x1卷积
        self.cv2 = Conv(c1, c_, 1, 1)   # 1x1卷积
        self.cv3 = Conv(2 * c_, c2, 1)  # 1x1卷积，恢复通道数
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) # 瓶颈层序列

    def forward(self, x):
        # 拼接两个卷积的输出，然后通过第三个卷积层
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

'''空间金字塔池化快速层(SPPF)类'''
class SPPF(nn.Module):
    # Spatial Pyrmid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):
        super().__init__()
        c_ = c1 // 2  # 计算中间通道数
        self.cv1 = Conv(c1, c_, 1, 1)     # 1x1卷积，减少通道数
        self.cv2 = Conv(c_ * 4, c2, 1, 1) # 1x1卷积， 恢复通道数
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)  # 最大池化层

    def forward(self, x):
        x = self.cv1(x)  # 通过1x1卷积
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')
            y1 = self.m(x)  # 最大池化
            y2 = self.m(y1) # 再次最大池化
            # 拼接四个特征图并通过1x1卷积
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

'''YOLOv5 Backbone类'''


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)
print(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))

----------------------------------------------------------------
        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) 
    num_batches = len(dataloader)  

    train_loss, train_acc = 0, 0  

    for X, y in dataloader:  
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        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) 
    num_batches = len(dataloader)  
    test_loss, test_acc = 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 = 20

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))

# 保存最佳模型到文件中
PATH = './best_model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

print('Done')

None
Epoch: 1, Train_acc:54.0%, Train_loss:1.163, Test_acc:70.7%, Test_loss:0.666, Lr:1.00E-04
Epoch: 2, Train_acc:64.0%, Train_loss:0.830, Test_acc:73.3%, Test_loss:0.535, Lr:1.00E-04
Epoch: 3, Train_acc:68.0%, Train_loss:0.716, Test_acc:80.0%, Test_loss:0.472, Lr:1.00E-04
Epoch: 4, Train_acc:74.4%, Train_loss:0.607, Test_acc:81.3%, Test_loss:0.450, Lr:1.00E-04
Epoch: 5, Train_acc:78.0%, Train_loss:0.590, Test_acc:77.8%, Test_loss:0.521, Lr:1.00E-04
Epoch: 6, Train_acc:75.8%, Train_loss:0.638, Test_acc:85.3%, Test_loss:0.372, Lr:1.00E-04
Epoch: 7, Train_acc:81.7%, Train_loss:0.461, Test_acc:77.3%, Test_loss:0.526, Lr:1.00E-04
Epoch: 8, Train_acc:82.6%, Train_loss:0.460, Test_acc:88.9%, Test_loss:0.336, Lr:1.00E-04
Epoch: 9, Train_acc:86.3%, Train_loss:0.386, Test_acc:81.3%, Test_loss:0.519, Lr:1.00E-04
Epoch:10, Train_acc:84.8%, Train_loss:0.379, Test_acc:87.1%, Test_loss:0.378, Lr:1.00E-04
Epoch:11, Train_acc:83.6%, Train_loss:0.418, Test_acc:75.6%, Test_loss:0.631, Lr:1.00E-04
Epoch:12, Train_acc:88.0%, Train_loss:0.288, Test_acc:86.2%, Test_loss:0.427, Lr:1.00E-04
Epoch:13, Train_acc:89.9%, Train_loss:0.260, Test_acc:89.3%, Test_loss:0.253, Lr:1.00E-04
Epoch:14, Train_acc:89.6%, Train_loss:0.265, Test_acc:88.9%, Test_loss:0.279, Lr:1.00E-04
Epoch:15, Train_acc:91.2%, Train_loss:0.223, Test_acc:89.8%, Test_loss:0.274, Lr:1.00E-04
Epoch:16, Train_acc:91.7%, Train_loss:0.232, Test_acc:90.7%, Test_loss:0.232, Lr:1.00E-04
Epoch:17, Train_acc:93.7%, Train_loss:0.195, Test_acc:88.9%, Test_loss:0.354, Lr:1.00E-04
Epoch:18, Train_acc:92.6%, Train_loss:0.193, Test_acc:91.6%, Test_loss:0.239, Lr:1.00E-04
Epoch:19, Train_acc:92.2%, Train_loss:0.205, Test_acc:89.8%, Test_loss:0.293, Lr:1.00E-04
Epoch:20, Train_acc:94.7%, Train_loss:0.148, Test_acc:90.7%, Test_loss:0.256, Lr:1.00E-04
Epoch:21, Train_acc:94.1%, Train_loss:0.177, Test_acc:88.9%, Test_loss:0.302, Lr:1.00E-04
Epoch:22, Train_acc:95.3%, Train_loss:0.124, Test_acc:90.2%, Test_loss:0.326, Lr:1.00E-04
Epoch:23, Train_acc:95.7%, Train_loss:0.117, Test_acc:91.6%, Test_loss:0.246, Lr:1.00E-04
Epoch:24, Train_acc:94.7%, Train_loss:0.127, Test_acc:89.8%, Test_loss:0.278, Lr:1.00E-04
Epoch:25, Train_acc:95.7%, Train_loss:0.124, Test_acc:90.7%, Test_loss:0.380, Lr:1.00E-04
Epoch:26, Train_acc:96.7%, Train_loss:0.102, Test_acc:91.1%, Test_loss:0.244, Lr:1.00E-04
Epoch:27, Train_acc:96.7%, Train_loss:0.102, Test_acc:91.6%, Test_loss:0.365, Lr:1.00E-04
Epoch:28, Train_acc:95.7%, Train_loss:0.114, Test_acc:92.4%, Test_loss:0.256, Lr:1.00E-04
Epoch:29, Train_acc:97.1%, Train_loss:0.077, Test_acc:90.2%, Test_loss:0.346, Lr:1.00E-04
Epoch:30, Train_acc:95.6%, Train_loss:0.116, Test_acc:92.0%, Test_loss:0.273, Lr:1.00E-04
Epoch:31, Train_acc:98.0%, Train_loss:0.051, Test_acc:89.8%, Test_loss:0.433, Lr:1.00E-04
Epoch:32, Train_acc:96.3%, Train_loss:0.122, Test_acc:91.1%, Test_loss:0.280, Lr:1.00E-04
Epoch:33, Train_acc:97.4%, Train_loss:0.081, Test_acc:90.7%, Test_loss:0.321, Lr:1.00E-04
Epoch:34, Train_acc:97.3%, Train_loss:0.063, Test_acc:92.4%, Test_loss:0.254, Lr:1.00E-04
Epoch:35, Train_acc:99.1%, Train_loss:0.030, Test_acc:93.8%, Test_loss:0.208, Lr:1.00E-04
Epoch:36, Train_acc:98.4%, Train_loss:0.060, Test_acc:91.6%, Test_loss:0.272, Lr:1.00E-04
Epoch:37, Train_acc:98.1%, Train_loss:0.067, Test_acc:92.0%, Test_loss:0.322, Lr:1.00E-04
Epoch:38, Train_acc:96.3%, Train_loss:0.121, Test_acc:86.7%, Test_loss:0.476, Lr:1.00E-04
Epoch:39, Train_acc:98.7%, Train_loss:0.058, Test_acc:92.4%, Test_loss:0.257, Lr:1.00E-04
Epoch:40, Train_acc:97.0%, Train_loss:0.083, Test_acc:89.8%, Test_loss:0.350, Lr:1.00E-04
Epoch:41, Train_acc:97.9%, Train_loss:0.085, Test_acc:92.0%, Test_loss:0.283, Lr:1.00E-04
Epoch:42, Train_acc:98.8%, Train_loss:0.033, Test_acc:91.6%, Test_loss:0.264, Lr:1.00E-04
Epoch:43, Train_acc:98.9%, Train_loss:0.036, Test_acc:89.3%, Test_loss:0.429, Lr:1.00E-04
Epoch:44, Train_acc:99.0%, Train_loss:0.033, Test_acc:88.0%, Test_loss:0.422, Lr:1.00E-04
Epoch:45, Train_acc:98.0%, Train_loss:0.066, Test_acc:92.4%, Test_loss:0.169, Lr:1.00E-04
Epoch:46, Train_acc:99.3%, Train_loss:0.020, Test_acc:92.0%, Test_loss:0.262, Lr:1.00E-04
Epoch:47, Train_acc:99.6%, Train_loss:0.014, Test_acc:93.3%, Test_loss:0.198, Lr:1.00E-04
Epoch:48, Train_acc:99.9%, Train_loss:0.007, Test_acc:92.4%, Test_loss:0.257, Lr:1.00E-04
Epoch:49, Train_acc:99.6%, Train_loss:0.012, Test_acc:92.0%, Test_loss:0.310, Lr:1.00E-04
Epoch:50, Train_acc:97.3%, Train_loss:0.071, Test_acc:89.3%, Test_loss:0.406, Lr:1.00E-04
Epoch:51, Train_acc:98.7%, Train_loss:0.052, Test_acc:85.3%, Test_loss:0.593, Lr:1.00E-04
Epoch:52, Train_acc:97.3%, Train_loss:0.063, Test_acc:92.4%, Test_loss:0.275, Lr:1.00E-04
Epoch:53, Train_acc:98.9%, Train_loss:0.037, Test_acc:92.0%, Test_loss:0.332, Lr:1.00E-04
Epoch:54, Train_acc:99.2%, Train_loss:0.029, Test_acc:90.7%, Test_loss:0.401, Lr:1.00E-04
Epoch:55, Train_acc:97.7%, Train_loss:0.072, Test_acc:90.7%, Test_loss:0.369, Lr:1.00E-04
Epoch:56, Train_acc:99.6%, Train_loss:0.013, Test_acc:93.3%, Test_loss:0.292, Lr:1.00E-04
Epoch:57, Train_acc:98.7%, Train_loss:0.032, Test_acc:92.0%, Test_loss:0.334, Lr:1.00E-04
Epoch:58, Train_acc:99.1%, Train_loss:0.034, Test_acc:86.2%, Test_loss:0.494, Lr:1.00E-04
Epoch:59, Train_acc:98.2%, Train_loss:0.044, Test_acc:93.3%, Test_loss:0.265, Lr:1.00E-04
Epoch:60, Train_acc:99.6%, Train_loss:0.020, Test_acc:90.2%, Test_loss:0.315, 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")
plt.rcParams['font.sans-serif']    = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
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()

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)

0.9377777777777778 0.20752016281970923

夏伊呀

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
1
评论
第P9周：YOLOv5-Backbone模块实现

*C3模块：**C3模块是YOLOv5中的一个重要组成部分，两个Conv组成Bottleneck，以减少计算量和参数量，其中,在Bottleneck类中，还提供了一个简单的残差连接。在CSP Bottleneck类中，包括两个1x1的卷积层self.cv1、self.cv2，一个瓶颈层序列self.m，一个1x1的卷积层self.cv3（用来恢复通道数）。**SPPF模块：**在SPPF类中，通过多次最大池化层self.m和卷积层self.cv1、self.cv2来实现多尺度特征的捕获和组合。
复制链接

扫一扫