>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/Z9yL_wt7L8aPOr9Lqb1K3w) 中的学习记录博客**
>- **🍖 原作者:[K同学啊](https://mtyjkh.blog.csdn.net/)**
本次我们将继续学习YOLOv5-Backbone模块,Backbone 是 YOLOv5 网络的核心模块之一,它主要用于从输入图像中提取底层特征。这些特征在后续网络层中被进一步处理,以识别图像中的物体。YOLOv5 使用了 CSPDarknet53 作为其 Backbone,这是一种轻量级的网络架构,基于 Darknet53 进行了优化,增加了 Cross Stage Partial Networks(CSPNet)的改进,以减少计算量和模型参数。CSPNet 通过部分分支的方式减少了计算成本,同时保持了较高的特征表达能力。
与上周学习的C3模块不同,C3 模块(CSP Bottleneck with 3 convolutions)是 YOLOv5 中的一个重要组件,用于提升网络的特征表达能力。它属于 YOLOv5 Backbone 结构的一部分,但有别于整个 Backbone 的作用。C3 模块的主要功能是增加特征层的表达能力,同时控制计算量的增加。Backbone模块可以包含多个C3模块。
一、前期准备
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
二、导入数据、处理数据
这个数据集是我们之前学习中使用过的,分为四个类别:cloudy、rain、shine、sunrise,我们按照之前的步骤,导入数据,读取类别名称
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]
classeNames
对数据集进行一个预处理,首先将图片尺寸统一调整为224*224像素,再做随机翻转以提升泛化能力做数据增强处理,接着转换为 PyTorch 的张量 (tensor) 格式,并将像素值归一化到 [0,1] 之间,然后做一个标准化处理,最终创建一个 ImageFolder 数据集对象,我们照例查看了每个类别的索引。
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("./weather_photos/",transform=train_transforms)
total_data
total_data.class_to_idx
下面也是以往的操作,划分训练集和测试集,设置批组样本数目为32,设置在每次迭代中打乱数据,子进程数为1
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
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
三、搭建包含C3模块的模型
YOLOv5_backbone 模块的网络结构由多个卷积层、C3 模块和一个 SPPF 模块组成,具体分为以下几个部分:
1. 卷积层 (Conv layers)
网络开始时有四个连续的卷积层,每个卷积层通过调整通道数和特征图大小来提取不同尺度的特征。每个卷积层之后都会进行一次下采样(通过步长为 2 的卷积实现),以逐渐减少特征图的空间分辨率,同时增加通道数。
2. C3 模块
C3 模块是 YOLOv5 中的 CSP(Cross Stage Partial)结构,用于增强特征提取能力。每个 C3 模块内部包含多个 Bottleneck 层,用来进一步提取特征。整个网络包含 4 个 C3 模块,每个模块位于不同的特征提取阶段,分别处理不同尺度的特征图。
3. SPPF 模块
SPPF(Spatial Pyramid Pooling - Fast)模块位于网络的最后,用于在多尺度上提取特征。这一模块通过多次最大池化操作扩展模型的感受野,捕获来自不同尺度的上下文信息。该模块处理 1024 通道的特征图,输出同样是 1024 通道的特征图。
4. 分类头
最后的分类头部分是一个全连接网络,处理从卷积和 C3 模块中提取到的特征。这个全连接网络包含两个线性层,最终输出用于分类的 4 个类别。特征图在进入全连接层之前会被展平(flatten),将二维特征图转换为一维向量。
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
[10]:
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) ) )
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 ----------------------------------------------------------------
四、训练模型
1、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、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
我们还是使用Adam优化器,做二十个周期的迭代训练
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')
Epoch: 1, Train_acc:51.7%, Train_loss:1.184, Test_acc:66.7%, Test_loss:0.925, Lr:1.00E-04 Epoch: 2, Train_acc:64.0%, Train_loss:0.846, Test_acc:80.4%, Test_loss:0.527, Lr:1.00E-04 Epoch: 3, Train_acc:72.8%, Train_loss:0.699, Test_acc:77.3%, Test_loss:0.480, Lr:1.00E-04 Epoch: 4, Train_acc:77.0%, Train_loss:0.573, Test_acc:78.2%, Test_loss:0.464, Lr:1.00E-04 Epoch: 5, Train_acc:78.2%, Train_loss:0.527, Test_acc:84.0%, Test_loss:0.405, Lr:1.00E-04 Epoch: 6, Train_acc:79.9%, Train_loss:0.501, Test_acc:84.4%, Test_loss:0.448, Lr:1.00E-04 Epoch: 7, Train_acc:82.3%, Train_loss:0.460, Test_acc:88.0%, Test_loss:0.329, Lr:1.00E-04 Epoch: 8, Train_acc:86.0%, Train_loss:0.360, Test_acc:88.0%, Test_loss:0.338, Lr:1.00E-04 Epoch: 9, Train_acc:86.9%, Train_loss:0.349, Test_acc:87.1%, Test_loss:0.473, Lr:1.00E-04 Epoch:10, Train_acc:89.2%, Train_loss:0.275, Test_acc:90.2%, Test_loss:0.372, Lr:1.00E-04 Epoch:11, Train_acc:87.8%, Train_loss:0.289, Test_acc:87.1%, Test_loss:0.409, Lr:1.00E-04 Epoch:12, Train_acc:91.7%, Train_loss:0.232, Test_acc:89.3%, Test_loss:0.335, Lr:1.00E-04 Epoch:13, Train_acc:92.8%, Train_loss:0.208, Test_acc:91.1%, Test_loss:0.273, Lr:1.00E-04 Epoch:14, Train_acc:94.1%, Train_loss:0.161, Test_acc:92.4%, Test_loss:0.205, Lr:1.00E-04 Epoch:15, Train_acc:95.7%, Train_loss:0.137, Test_acc:93.8%, Test_loss:0.231, Lr:1.00E-04 Epoch:16, Train_acc:93.9%, Train_loss:0.184, Test_acc:94.2%, Test_loss:0.185, Lr:1.00E-04 Epoch:17, Train_acc:96.2%, Train_loss:0.095, Test_acc:92.9%, Test_loss:0.210, Lr:1.00E-04 Epoch:18, Train_acc:92.4%, Train_loss:0.204, Test_acc:84.0%, Test_loss:0.533, Lr:1.00E-04 Epoch:19, Train_acc:93.4%, Train_loss:0.175, Test_acc:91.1%, Test_loss:0.268, Lr:1.00E-04 Epoch:20, Train_acc:97.3%, Train_loss:0.088, Test_acc:95.1%, Test_loss:0.173, Lr:1.00E-04 Done
四、 结果可视化
模型训练完后,我们对训练结果进行可视化,对比上一期简单的C3模块,我们这次使用的模型明显提升了训练效果,训练准确率有了明显的提升,可以上升到90%以上,同时训练损失也在下降。
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 # 用来正常显示负号
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()
五、、总结
YOLOv5 的 Backbone模块,模型复杂度明显提升,但训练效果比上一期学习的简单的C3模块也相应提高了很多,Backbone 是 YOLOv5 的核心特征提取模块,而 C3 模块是其中的一个优化模块,Backbone中还加了一个SPDF这样一个空间金字塔池化模块,通过多次最大池化操作增强模型的感受野,能够在不同尺度上提取特征。通过我们的训练结果也可以看出这个YOLOv5主干模块在提取特征上的优势。