>- **🍨 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]
目录
一、前期准备
1.设置GPU
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms,datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings('ignore')
device = torch.device("cuda" if torch.cuda.is_available else 'cpu')
device
device(type='cuda')
2. 导入数据
def LocalData(root):
data_dir = pathlib.Path(root)
data_path = list(data_dir.glob('*'))
ClassNames = [str(path).split('\\')[-1] for path in data_path]
train_transforms = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(
mean=[0.486,0.456,0.406],
std=[0.229,0.224,0.225]),
transforms.Resize([224,224])
])
total_dataset = torchvision.datasets.ImageFolder(data_dir,transform=train_transforms)
print(total_dataset)
print(total_dataset.class_to_idx)
train_size = int(len(total_dataset)*0.8)
test_size = len(total_dataset)-train_size
train_dataset,test_dataset = torch.utils.data.random_split(total_dataset,(train_size,test_size))
return ClassNames,train_dataset,test_dataset
root = r"..\Netural_work_Data\P3_data"
output = r"..\model_param\p_9_model"
ClassNames,train_dataset,test_dataset = LocalData(root)
print(ClassNames)
Dataset ImageFolder Number of datapoints: 1125 Root location: ..\Netural_work_Data\P3_data StandardTransform Transform: Compose( ToTensor() Normalize(mean=[0.486, 0.456, 0.406], std=[0.229, 0.224, 0.225]) Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=warn) ) {'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3} ['cloudy', 'rain', 'shine', 'sunrise']
3.数据可视化
from matplotlib import pyplot as plt
from PIL import Image
def DisplayImage(root):
img_files = [f for f in os.listdir(root) if f.endswith(('.jpeg','.png','.jpg'))]
img_paths=[os.path.join(root,img_file) for img_file in img_files]
fig,axes = plt.subplots(3,8,figsize=(16,6))
for ax,i in zip(axes.flat,range(len(img_paths)-1)):
img_path = os.path.join(root,img_paths[i])
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
plt.show()
root = r"F:\Netural_work_Data\P3_data\cloudy"
DisplayImage(root)
4.加载数据
def DataLoader(train_dataset,test_dataset,batch_size):
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size = batch_size,
shuffle=True,
num_workers=2)
test_dl = torch.utils.data.DataLoader(train_dataset,
batch_size = batch_size,
shuffle=False,
num_workers=2)
for X,y in train_dl:
print('shape of X[N,C,H,W]:',X.shape)
print('shape of y:',y.shape,y.dtype)
break
return (train_dl,test_dl)
batch_size = 32
train_dl,test_dl = DataLoader(train_dataset,train_dataset,batch_size)
shape of X[N,C,H,W]: torch.Size([32, 3, 224, 224]) shape of y: torch.Size([32]) torch.int64
二、搭建包含Backbone模块的模型
1.Backbone骨干网络
参考文章:【YOLOv5】Backbone、Neck、Head各模块详解_yolov5 backbone-CSDN博客
骨干网络是指用来提取图像特征的网络,它的主要作用是将原始的输入图像转化为多层特征图,以便后续的目标检测任务使用。在Yolov5中,使用的是CSPDarknet53或ResNet骨干网络,这两个网络都是相对轻量级的,能够在保证较高检测精度的同时,尽可能地减少计算量和内存占用。
Backbone中的主要结构有Conv模块、C3模块、SPPF模块。
2.Conv模块
Conv模块是卷积神经网络中常用的一种基础模块,它主要由卷积层、BN层和激活函数组成。下面对这些组成部分进行详细解析。
卷积层是卷积神经网络中最基础的层之一,用于提取输入特征中的局部空间信息。卷积操作可以看作是一个滑动窗口,窗口在输入特征上滑动,并将窗口内的特征值与卷积核进行卷积操作,从而得到输出特征。卷积层通常由多个卷积核组成,每个卷积核对应一个输出通道。卷积核的大小、步长、填充方式等超参数决定了卷积层的输出大小和感受野大小。卷积神经网络中,卷积层通常被用来构建特征提取器。
BN层是在卷积层之后加入的一种归一化层,用于规范化神经网络中的特征值分布。它可以加速训练过程,提高模型泛化能力,减轻模型对初始化的依赖性。BN层的输入为一个batch的特征图,它将每个通道上的特征进行均值和方差的计算,并对每个通道上的特征进行标准化处理。标准化后的特征再通过一个可学习的仿射变换(拉伸和偏移)进行还原,从而得到BN层的输出
激活函数是一种非线性函数,用于给神经网络引入非线性变换能力。常用的激活函数包括sigmoid、ReLU、LeakyReLU、ELU等。它们在输入值的不同范围内都有不同的输出表现,可以更好地适应不同类型的数据分布。
3.C3模块
C3模块是YOLOv5网络中的一个重要组成部分,其主要作用是增加网络的深度和感受野,提高特征提取的能力。
C3模块是由三个Conv块构成的,其中第一个Conv块的步幅为2,可以将特征图的尺寸减半,第二个Conv块和第三个Conv块的步幅为1。C3模块中的Conv块采用的都是3x3的卷积核。在每个Conv块之间,还加入了BN层和LeakyReLU激活函数,以提高模型的稳定性和泛化性能。
C3模块中的第一个Conv块的步幅为2,红色方框内两个Conv组成Bottleneck,这意味着它会将特征图的尺寸减半。这样做的目的是为了增加网络的感受野,同时减少计算量。通过将特征图的尺寸减半,可以使网络更加关注物体的全局信息,从而提高特征提取的效果。
C3模块中的第二个Conv块和第三个Conv块的步幅为1,这意味着它们不会改变特征图的尺寸。这样做的目的是为了保持特征图的空间分辨率,从而更好地保留物体的局部信息。同时,这两个Conv块的主要作用是进一步提取特征,增加网络的深度和感受野。
总的来说,C3模块通过增加网络的深度和感受野,提高了特征提取的能力。这对于目标检测等计算机视觉任务来说非常重要,因为这些任务需要对物体进行准确的识别和定位,而准确的识别和定位需要良好的特征提取能力。
4.SPP
SPP模块是一种池化模块,通常应用于卷积神经网络中,旨在实现输入数据的空间不变性和位置不变性,以便于提高神经网络的识别能力。其主要思想是将不同大小的感受野应用于同一张图像,从而能够捕捉到不同尺度的特征信息。在SPP模块中,首先对输入特征图进行不同大小的池化操作,以得到一组不同大小的特征图。然后将这些特征图连接在一起,并通过全连接层进行降维,最终得到固定大小的特征向量。
SPP模块通常由三个步骤组成:
- 池化:将输入特征图分别进行不同大小的池化操作,以获得一组不同大小的特征图。
- 连接:将不同大小的特征图连接在一起。
- 全连接:通过全连接层将连接后的特征向量降维,得到固定大小的特征向量。
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 deviceOut[7]:
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) ) )
# 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
def train(dataloader,model,optimizer,loss_fn):
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)
#计算误差
pred = model(X)
loss = loss_fn(pred,y)
#反向传播
optimizer.zero_grad()
loss.backward()
optimizer.step()
#记录loss与acc
train_loss += loss.item()
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss /= num_batches
train_acc /= size
return train_acc,train_loss
2.测试函数
def train(dataloader,model,optimizer,loss_fn):
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)
#计算误差
pred = model(X)
loss = loss_fn(pred,y)
#反向传播
optimizer.zero_grad()
loss.backward()
optimizer.step()
#记录loss与acc
train_loss += loss.item()
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss /= num_batches
train_acc /= size
return train_acc,train_loss
3. 正式训练&设置超参数&保存最近模型
import time
import copy
'''设置超参数'''
start_epoch = 0
epochs = 30
learn_rate = 1e-4
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),lr=learn_rate)
type(optimizer)
lambda1 = lambda epoch:0.92**(epoch//4)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=lambda1)
train_loss = []
train_acc = []
test_loss = []
test_acc = []
epoch_best_acc = 0
'''加载之前的模型'''
if not os.path.exists(output) or not os.path.isdir(output):
os.makedirs(output)
if start_epoch > 0:
resumeFile = os.path.join(output, 'epoch'+str(start_epoch)+'.pkl')
if not os.path.exists(resumeFile) or not os.path.isfile(resumeFile):
start_epoch = 0
else:
model.load_state_dict(torch.load(resumeFile))
'''开始训练'''
print('\nStarting Training...')
best_model= None
for epoch in range(start_epoch, epochs):
model.train()
epoch_train_acc,epoch_train_loss = train(train_dl,model,optimizer,loss_fn)
scheduler.step()
model.eval()
epoch_test_acc,epoch_test_loss = test(test_dl,model,loss_fn)
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(time.strftime('[%Y-%m-%d %H:%M:%S]'), 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
if epoch_test_acc>epoch_best_acc:
''' 保存最优模型参数 '''
epoch_best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
print(('acc = {:.1f}%, saving model to best.pkl').format(epoch_best_acc*100))
saveFile = os.path.join(output, 'best.pkl')
torch.save(best_model.state_dict(), saveFile)
print('Done\n')
''' 保存最新模型参数 '''
saveFile = os.path.join(output, 'epoch'+str(epochs)+'.pkl')
torch.save(model.state_dict(), saveFile)
Starting Training... [2023-12-15 10:29:21] Epoch: 1, Train_acc:87.1%, Train_loss:0.466, Test_acc:91.9%, Test_loss:0.224, Lr:1.00E-04 acc = 91.9%, saving model to best.pkl [2023-12-15 10:30:05] Epoch: 2, Train_acc:89.8%, Train_loss:0.276, Test_acc:94.3%, Test_loss:0.157, Lr:1.00E-04 acc = 94.3%, saving model to best.pkl [2023-12-15 10:30:48] Epoch: 3, Train_acc:91.7%, Train_loss:0.260, Test_acc:95.7%, Test_loss:0.122, Lr:1.00E-04 acc = 95.7%, saving model to best.pkl [2023-12-15 10:31:25] Epoch: 4, Train_acc:95.6%, Train_loss:0.130, Test_acc:96.7%, Test_loss:0.124, Lr:9.20E-05 acc = 96.7%, saving model to best.pkl [2023-12-15 10:32:00] Epoch: 5, Train_acc:94.6%, Train_loss:0.151, Test_acc:98.3%, Test_loss:0.063, Lr:9.20E-05 acc = 98.3%, saving model to best.pkl [2023-12-15 10:32:30] Epoch: 6, Train_acc:96.9%, Train_loss:0.107, Test_acc:98.3%, Test_loss:0.050, Lr:9.20E-05 [2023-12-15 10:33:02] Epoch: 7, Train_acc:96.8%, Train_loss:0.108, Test_acc:95.7%, Test_loss:0.119, Lr:9.20E-05 [2023-12-15 10:33:32] Epoch: 8, Train_acc:92.7%, Train_loss:0.446, Test_acc:96.7%, Test_loss:0.078, Lr:8.46E-05 [2023-12-15 10:34:03] Epoch: 9, Train_acc:93.7%, Train_loss:0.230, Test_acc:98.1%, Test_loss:0.050, Lr:8.46E-05 [2023-12-15 10:34:32] Epoch:10, Train_acc:94.8%, Train_loss:0.163, Test_acc:98.4%, Test_loss:0.050, Lr:8.46E-05 acc = 98.4%, saving model to best.pkl [2023-12-15 10:35:04] Epoch:11, Train_acc:94.7%, Train_loss:0.272, Test_acc:97.9%, Test_loss:0.051, Lr:8.46E-05 [2023-12-15 10:35:34] Epoch:12, Train_acc:93.4%, Train_loss:0.266, Test_acc:97.6%, Test_loss:0.086, Lr:7.79E-05 [2023-12-15 10:36:05] Epoch:13, Train_acc:95.2%, Train_loss:0.130, Test_acc:99.2%, Test_loss:0.038, Lr:7.79E-05 acc = 99.2%, saving model to best.pkl [2023-12-15 10:36:35] Epoch:14, Train_acc:98.4%, Train_loss:0.199, Test_acc:99.4%, Test_loss:0.019, Lr:7.79E-05 acc = 99.4%, saving model to best.pkl [2023-12-15 10:37:06] Epoch:15, Train_acc:94.1%, Train_loss:0.169, Test_acc:98.2%, Test_loss:0.058, Lr:7.79E-05 [2023-12-15 10:37:38] Epoch:16, Train_acc:97.2%, Train_loss:0.139, Test_acc:99.2%, Test_loss:0.025, Lr:7.16E-05 [2023-12-15 10:38:10] Epoch:17, Train_acc:98.1%, Train_loss:0.061, Test_acc:99.8%, Test_loss:0.009, Lr:7.16E-05 acc = 99.8%, saving model to best.pkl [2023-12-15 10:38:39] Epoch:18, Train_acc:99.1%, Train_loss:0.080, Test_acc:99.9%, Test_loss:0.007, Lr:7.16E-05 acc = 99.9%, saving model to best.pkl [2023-12-15 10:39:10] Epoch:19, Train_acc:97.3%, Train_loss:0.215, Test_acc:99.6%, Test_loss:0.013, Lr:7.16E-05 [2023-12-15 10:39:41] Epoch:20, Train_acc:95.7%, Train_loss:0.120, Test_acc:99.3%, Test_loss:0.027, Lr:6.59E-05 [2023-12-15 10:40:13] Epoch:21, Train_acc:99.0%, Train_loss:0.030, Test_acc:99.7%, Test_loss:0.014, Lr:6.59E-05 [2023-12-15 10:40:45] Epoch:22, Train_acc:98.7%, Train_loss:0.044, Test_acc:100.0%, Test_loss:0.007, Lr:6.59E-05 acc = 100.0%, saving model to best.pkl [2023-12-15 10:41:18] Epoch:23, Train_acc:99.4%, Train_loss:0.043, Test_acc:100.0%, Test_loss:0.002, Lr:6.59E-05 [2023-12-15 10:41:49] Epoch:24, Train_acc:98.6%, Train_loss:0.048, Test_acc:100.0%, Test_loss:0.005, Lr:6.06E-05 [2023-12-15 10:42:20] Epoch:25, Train_acc:98.4%, Train_loss:0.063, Test_acc:99.9%, Test_loss:0.005, Lr:6.06E-05 [2023-12-15 10:42:52] Epoch:26, Train_acc:98.4%, Train_loss:0.046, Test_acc:99.6%, Test_loss:0.012, Lr:6.06E-05 [2023-12-15 10:43:25] Epoch:27, Train_acc:99.0%, Train_loss:0.030, Test_acc:99.9%, Test_loss:0.004, Lr:6.06E-05 [2023-12-15 10:43:57] Epoch:28, Train_acc:98.7%, Train_loss:0.047, Test_acc:99.9%, Test_loss:0.008, Lr:5.58E-05 [2023-12-15 10:44:27] Epoch:29, Train_acc:99.3%, Train_loss:0.028, Test_acc:100.0%, Test_loss:0.003, Lr:5.58E-05 [2023-12-15 10:45:01] Epoch:30, Train_acc:99.7%, Train_loss:0.015, Test_acc:100.0%, Test_loss:0.001, Lr:5.58E-05 Dones
四、结果可视化
''' 结果可视化 '''
def displayResult(train_acc, test_acc, train_loss, test_loss, start_epoch, epochs, output=''):
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(start_ epoch, epochs)
plt.figure('Result Visualization', 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.savefig(os.path.join(output, 'AccuracyLoss.png'))
plt.show()
''' 绘制准确率&损失率曲线图 '''
displayResult(train_acc, test_acc, train_loss, test_loss, start_epoch, epochs, output)
五、加载指定图片并进行预测
''' 预测函数 '''
import PIL
from PIL import Image
def predict(model, img_path):
img = Image.open(img_path)
test_transforms = torchvision.transforms.Compose([
torchvision.transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
torchvision.transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
torchvision.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。
])
img = test_transforms(img)
img = img.to(device).unsqueeze(0)
output = model(img)
#print(output.argmax(1))
_, indices = torch.max(output, 1)
percentage = torch.nn.functional.softmax(output, dim=1)[0] * 100
perc = percentage[int(indices)].item()
result = classeNames[indices]
print('predicted:', result, perc)
if __name__=='__main__':
classeNames = list({'Cloudy': 0, 'Rain': 1, 'Shine': 2, 'Sunrise': 3})
num_classes = len(classeNames)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using {} device\n".format(device))
model = YOLOv5_backbone().to(device)
model.load_state_dict(torch.load(r'F:\model_param\p_9_model\best.pkl'))
model.eval()
img_path = r'F:\Netural_work_Data\P3_data\cloudy\cloudy1.jpg'
predict(model, img_path)
Using cuda device predicted: Cloudy 99.98368072509766