深度学习 09 — YOLOv5 Backbone模块实现

TOMWilliamLIN

已于 2024-05-07 14:43:43 修改

阅读量869

点赞数 16

分类专栏：深度学习文章标签：深度学习 YOLO 人工智能

于 2024-05-07 14:42:45 首次发布

本文链接：https://blog.csdn.net/TOMWilliamLIN/article/details/138507856

版权

深度学习专栏收录该内容

11 篇文章 1 订阅

订阅专栏

🍨 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

1. 设置GPU

import torch
import torchvision
import torch.nn as nn
import os,PIL,pathlib,warnings
import torchvision.transforms as transforms
from torchvision import transforms,datasets

warnings.filterwarnings("ignore")

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

2. 导入数据

data_dir = '/content/drive/MyDrive/Colab Notebooks/data'

data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))

classeName = [str(path).split('/')[-1] for path in data_paths]

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_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('/content/drive/MyDrive/Colab Notebooks/data',transform=train_transforms)

total_data

3. 划分数据集

train_size = int(len(total_data)*0.8)
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

batch_size = 4

train_dl = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True,num_workers=1)

test_dl = torch.utils.data.DataLoader(test_dataset,batch_size=batch_size,shuffle=True,num_workers=1)

for X, y in test_dl:
    print("Shape of X [N,C,H,W]: ", X.shape)
    print("Shape of y: ",y.shape,y.dtype)
    break

二、搭建包含Backbone模块的模型

1. 搭建模型

import torch.nn.functional as F
def autopad(k,p=None):
    if p is None:
        p = k // 2 if  isinstance(k,int) else [x // 2 for x in k]
    return p

class Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
        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):
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)
        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):
        out = self.cv2(self.cv1(x))
        return x + out if self.add else out

class C3(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 *c_, c2, 1)
        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):
    def __init__(self, c1, c2, k=5):
        super().__init__()
        c_ = c1 // 2
        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")
            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)
        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)

        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.查看模型详细

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.编写训练模型

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    num_batchsize = len(dataloader)
    train_acc, train_loss = 0,0

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

        pred = model(X)
        loss = loss_fn(pred,y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc /= size
    train_loss /= num_batchsize

    return train_acc, train_loss

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)
            
            
            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()

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)
    
    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)
    
   
    lr = optimizer.state_dict()['param_groups'][0]['lr']
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, 
                          epoch_test_acc*100, epoch_test_loss, lr))
    

PATH = './best_model.pth'  
torch.save(best_model.state_dict(), PATH)

print('Done')


import copy

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

epochs     = 60

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

Epoch: 1, Train_acc:56.3%, Train_loss:1.146, Test_acc:64.0%, Test_loss:0.842, Lr:1.00E-04
Epoch: 2, Train_acc:64.6%, Train_loss:0.864, Test_acc:72.9%, Test_loss:0.637, Lr:1.00E-04
Epoch: 3, Train_acc:70.7%, Train_loss:0.687, Test_acc:79.6%, Test_loss:0.496, Lr:1.00E-04
Epoch: 4, Train_acc:73.9%, Train_loss:0.669, Test_acc:77.3%, Test_loss:0.508, Lr:1.00E-04
Epoch: 5, Train_acc:74.9%, Train_loss:0.587, Test_acc:68.4%, Test_loss:0.615, Lr:1.00E-04
Epoch: 6, Train_acc:79.9%, Train_loss:0.484, Test_acc:80.0%, Test_loss:0.558, Lr:1.00E-04
Epoch: 7, Train_acc:80.3%, Train_loss:0.473, Test_acc:83.1%, Test_loss:0.396, Lr:1.00E-04
Epoch: 8, Train_acc:83.3%, Train_loss:0.420, Test_acc:84.4%, Test_loss:0.349, Lr:1.00E-04
Epoch: 9, Train_acc:83.9%, Train_loss:0.433, Test_acc:85.3%, Test_loss:0.352, Lr:1.00E-04
Epoch:10, Train_acc:85.3%, Train_loss:0.363, Test_acc:84.0%, Test_loss:0.513, Lr:1.00E-04
Epoch:11, Train_acc:89.3%, Train_loss:0.302, Test_acc:85.3%, Test_loss:0.403, Lr:1.00E-04
Epoch:12, Train_acc:87.0%, Train_loss:0.344, Test_acc:84.4%, Test_loss:0.440, Lr:1.00E-04
Epoch:13, Train_acc:87.7%, Train_loss:0.361, Test_acc:89.8%, Test_loss:0.317, Lr:1.00E-04
Epoch:14, Train_acc:88.7%, Train_loss:0.299, Test_acc:88.4%, Test_loss:0.314, Lr:1.00E-04
Epoch:15, Train_acc:91.6%, Train_loss:0.211, Test_acc:82.7%, Test_loss:0.763, Lr:1.00E-04
Epoch:16, Train_acc:92.8%, Train_loss:0.226, Test_acc:87.6%, Test_loss:0.382, Lr:1.00E-04
Epoch:17, Train_acc:91.4%, Train_loss:0.214, Test_acc:90.2%, Test_loss:0.327, Lr:1.00E-04
Epoch:18, Train_acc:94.1%, Train_loss:0.181, Test_acc:89.8%, Test_loss:0.273, Lr:1.00E-04
Epoch:19, Train_acc:93.9%, Train_loss:0.203, Test_acc:89.3%, Test_loss:0.377, Lr:1.00E-04
Epoch:20, Train_acc:95.7%, Train_loss:0.121, Test_acc:92.0%, Test_loss:0.249, Lr:1.00E-04
Epoch:21, Train_acc:96.4%, Train_loss:0.099, Test_acc:91.1%, Test_loss:0.285, Lr:1.00E-04
Epoch:22, Train_acc:97.7%, Train_loss:0.078, Test_acc:89.8%, Test_loss:0.290, Lr:1.00E-04
Epoch:23, Train_acc:95.7%, Train_loss:0.142, Test_acc:91.6%, Test_loss:0.296, Lr:1.00E-04
Epoch:24, Train_acc:97.0%, Train_loss:0.086, Test_acc:90.7%, Test_loss:0.311, Lr:1.00E-04
Epoch:25, Train_acc:95.3%, Train_loss:0.141, Test_acc:88.9%, Test_loss:0.458, Lr:1.00E-04
Epoch:26, Train_acc:97.6%, Train_loss:0.069, Test_acc:92.4%, Test_loss:0.234, Lr:1.00E-04
Epoch:27, Train_acc:96.9%, Train_loss:0.075, Test_acc:90.2%, Test_loss:0.322, Lr:1.00E-04
Epoch:28, Train_acc:96.2%, Train_loss:0.103, Test_acc:87.1%, Test_loss:0.428, Lr:1.00E-04
Epoch:29, Train_acc:96.4%, Train_loss:0.107, Test_acc:89.8%, Test_loss:0.381, Lr:1.00E-04
Epoch:30, Train_acc:96.1%, Train_loss:0.116, Test_acc:90.2%, Test_loss:0.380, Lr:1.00E-04
Epoch:31, Train_acc:96.0%, Train_loss:0.125, Test_acc:86.7%, Test_loss:0.425, Lr:1.00E-04
Epoch:32, Train_acc:98.4%, Train_loss:0.047, Test_acc:81.3%, Test_loss:0.978, Lr:1.00E-04
Epoch:33, Train_acc:96.6%, Train_loss:0.098, Test_acc:90.2%, Test_loss:0.504, Lr:1.00E-04
Epoch:34, Train_acc:98.1%, Train_loss:0.059, Test_acc:91.1%, Test_loss:0.307, Lr:1.00E-04
Epoch:35, Train_acc:98.1%, Train_loss:0.053, Test_acc:88.4%, Test_loss:0.429, Lr:1.00E-04
Epoch:36, Train_acc:99.1%, Train_loss:0.035, Test_acc:87.6%, Test_loss:0.442, Lr:1.00E-04
Epoch:37, Train_acc:99.4%, Train_loss:0.015, Test_acc:88.4%, Test_loss:0.445, Lr:1.00E-04
Epoch:38, Train_acc:99.1%, Train_loss:0.027, Test_acc:88.4%, Test_loss:0.446, Lr:1.00E-04
Epoch:39, Train_acc:98.2%, Train_loss:0.048, Test_acc:86.2%, Test_loss:0.644, Lr:1.00E-04
Epoch:40, Train_acc:97.3%, Train_loss:0.072, Test_acc:84.9%, Test_loss:0.743, Lr:1.00E-04
Epoch:41, Train_acc:94.8%, Train_loss:0.159, Test_acc:88.9%, Test_loss:0.446, Lr:1.00E-04
Epoch:42, Train_acc:96.8%, Train_loss:0.096, Test_acc:87.1%, Test_loss:0.573, Lr:1.00E-04
Epoch:43, Train_acc:99.4%, Train_loss:0.025, Test_acc:88.4%, Test_loss:0.370, Lr:1.00E-04
Epoch:44, Train_acc:99.7%, Train_loss:0.010, Test_acc:90.2%, Test_loss:0.490, Lr:1.00E-04
Epoch:45, Train_acc:99.4%, Train_loss:0.015, Test_acc:87.1%, Test_loss:0.599, Lr:1.00E-04
Epoch:46, Train_acc:99.1%, Train_loss:0.035, Test_acc:86.2%, Test_loss:0.602, Lr:1.00E-04
Epoch:47, Train_acc:98.2%, Train_loss:0.057, Test_acc:89.3%, Test_loss:0.431, Lr:1.00E-04
Epoch:48, Train_acc:98.7%, Train_loss:0.043, Test_acc:89.3%, Test_loss:0.431, Lr:1.00E-04
Epoch:49, Train_acc:98.1%, Train_loss:0.081, Test_acc:91.1%, Test_loss:0.351, Lr:1.00E-04
Epoch:50, Train_acc:97.4%, Train_loss:0.084, Test_acc:84.0%, Test_loss:0.625, Lr:1.00E-04
Epoch:51, Train_acc:97.8%, Train_loss:0.055, Test_acc:92.4%, Test_loss:0.308, Lr:1.00E-04
Epoch:52, Train_acc:98.8%, Train_loss:0.042, Test_acc:91.1%, Test_loss:0.324, Lr:1.00E-04
Epoch:53, Train_acc:99.3%, Train_loss:0.025, Test_acc:91.1%, Test_loss:0.327, Lr:1.00E-04
Epoch:54, Train_acc:98.9%, Train_loss:0.041, Test_acc:89.8%, Test_loss:0.419, Lr:1.00E-04
Epoch:55, Train_acc:98.8%, Train_loss:0.036, Test_acc:89.3%, Test_loss:0.422, Lr:1.00E-04
Epoch:56, Train_acc:99.4%, Train_loss:0.013, Test_acc:92.4%, Test_loss:0.351, Lr:1.00E-04
Epoch:57, Train_acc:99.7%, Train_loss:0.012, Test_acc:89.8%, Test_loss:0.417, Lr:1.00E-04
Epoch:58, Train_acc:99.9%, Train_loss:0.007, Test_acc:88.9%, Test_loss:0.366, Lr:1.00E-04
Epoch:59, Train_acc:99.9%, Train_loss:0.005, Test_acc:89.8%, Test_loss:0.545, Lr:1.00E-04
Epoch:60, Train_acc:98.4%, Train_loss:0.053, Test_acc:92.9%, Test_loss:0.378, Lr:1.00E-04
Done

四、结果可视化

1.Loss 与 Accuracy 图

import warnings
import matplotlib.pyplot as plt

warnings.filterwarnings("ignore")


epochs_range = range(epochs)

plt.figure(figsize=(12,3))
plt.subplot(121)

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(122)
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()

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

5.个人总结

Backbone 模块的作用

Backbone 模块的主要作用是从输入图像中提取丰富的语义特征信息，为后续的目标检测任务提供有价值的特征表示。在 YOLOv5 中，Backbone 模块将输入图像映射到一个高维的特征空间，捕捉图像中的低级特征（如边缘、纹理等）和高级语义特征（如物体部件等）。这些特征信息对于准确检测和识别目标物体至关重要。

Backbone 模块的内部结构

YOLOv5 的 Backbone 模块采用了广泛使用的 CSPDarknet53 网络架构，它是基于 DarkNet-53 网络演变而来。CSPDarknet53 包含以下几个主要部分：

1.卷积层(Convolutional Layers) : 一系列标准卷积层用于提取低级特征，如边缘、纹理等。这些层通过卷积操作从输入图像中学习局部图案和特征。

• Conv 模块 ：包含卷积层、BN 层和激活函数（SiLU 或 LeakyReLU）

2.残差连接(Residual Connections): 残差连接是 CSPDarknet53 的一个关键部分，它们允许梯度在训练过程中更容易地流动，从而缓解了梯度消失/爆炸问题。残差连接将低层特征与高层特征进行融合，增强了特征的表达能力。

• Bottleneck 模块： 包括两个卷积层和一个残差连接

3.CSP模块(Cross Stage Partial Connections) : CSP 模块是 CSPDarknet53 的核心创新，它将主干网络分为两个部分：一部分用于捕获富有语义信息的特征，另一部分用于捕获低级细节特征。这两部分特征在后面会进行融合，提高了特征的判别能力（Discriminative Power）。

• C3模块：是CSP模块的实习之一，包括多个Bottleneck层

4.下采样层(Downsampling Layers): 下采样层通常由最大池化或卷积 stride 完成，用于逐步减小特征图的空间尺寸，扩大感受野，捕获更大范围的上下文信息。

• 在YOLOv5 中，下采样通过卷积步长实习的

5.SPPF模块(Spatial Pyramid Pooling - Fast):

输入特征图 SPPF 模块的输入是一个来自 backbone 网络的特征图(feature map)。
空间金字塔池化(Spatial Pyramid Pooling) 特征图被分割为多个尺度的空间金字塔(spatial pyramid)。每个金字塔级别对应一个池化窗口(pooling bin),窗口大小不同。通常使用的金字塔级别有 1x1, 2x2, 3x3 和 6x6。
池化操作在每个池化窗口中,执行最大池化操作,生成一个对应尺度的特征图。因此,对于每个尺度级别,都会输出一个相应的池化特征图。
特征图拼接来自不同尺度的池化特征图被沿着通道维度拼接(concatenate)在一起,形成一个新的特征图。
通过这种方式,SPPF 模块可以从单个特征图中提取多尺度的特征信息。不同尺度的特征对应不同大小的目标物体,有助于检测不同尺寸的目标。

TOMWilliamLIN

关注

16
点赞
踩
30

收藏

觉得还不错? 一键收藏
0
评论
深度学习 09 — YOLOv5 Backbone模块实现

Backbone 模块的作用Backbone 模块的主要作用是从输入图像中提取丰富的语义特征信息，为后续的目标检测任务提供有价值的特征表示。在 YOLOv5 中，Backbone 模块将输入图像映射到一个高维的特征空间，捕捉图像中的低级特征（如边缘、纹理等）和高级语义特征（如物体部件等）。这些特征信息对于准确检测和识别目标物体至关重要。Backbone 模块的内部结构。
复制链接

扫一扫