>- **🍨 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]**
本次我将利用YOLOv5算法中的C3模块搭建网络
🏡 我的环境:
- 语言环境:Python3.8
- 编译器:Jupyter Notebook
- 数据集:天气识别数据集
- 深度学习环境:Pytorch
-
- torch==2.3.1+cu188
-
- torchvision==0.18.1+cu118
一、 前期准备
1. 设置GPU
如果设备上支持GPU就使用GPU,否则使用CPU
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
import torch
device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
运行结果:
device(type='cuda')
2. 导入数据
import pathlib
data_dir='D:\THE MNIST DATABASE\weather_photos'
data_dir=pathlib.Path(data_dir)
data_paths=list(data_dir.glob('*'))
classNames=[str(path).split("\\")[3] for path in data_paths]
classNames
运行结果:
['cloudy', 'rain', 'shine', 'sunrise']
3. 随机查看图片
import matplotlib.pyplot as plt
import random,PIL
from PIL import Image
data_path2=list(data_dir.glob('*/*'))
plt.figure(figsize=(20,4))
for i in range(20):
plt.subplot(2,10,i+1)
plt.axis('off')
image=random.choice(data_path2)
plt.title(image.parts[-2])
plt.imshow(Image.open(str(image)))
运行结果:
4. 图片预处理
total_dir='D:\THE MNIST DATABASE\weather_photos'
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms,datasets
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])
])
total_data=datasets.ImageFolder(total_dir,transform=train_transforms)
total_data
运行结果:
Dataset ImageFolder
Number of datapoints: 1125
Root location: D:\THE MNIST DATABASE\weather_photos
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
RandomHorizontalFlip(p=0.5)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
映射输出:
total_data.class_to_idx
运行结果:
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
5. 划分数据集
train_size=int(0.8*len(total_data))
test_size=len(total_data)-train_size
train_dataset,test_dataset=torch.utils.data.random_split(total_data,[train_size,test_size])
train_dataset,test_dataset
运行结果:
(<torch.utils.data.dataset.Subset at 0x231a814ad50>,
<torch.utils.data.dataset.Subset at 0x231abf18450>)
显示训练集和测试集的数据数量:
train_size,test_size
运行结果:
(900, 225)
6. 加载数据集
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)
显示测试集的情况:
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
运行结果:
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
1. 搭建模型
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 model_K(nn.Module):
def __init__(self):
super(model_K, self).__init__()
# 卷积模块
self.Conv = Conv(3, 32, 3, 2)
# C3模块1
self.C3_1 = C3(32, 64, 3, 2)
# 全连接网络层,用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=802816, out_features=100),
nn.ReLU(),
nn.Linear(in_features=100, out_features=4)
)
def forward(self, x):
x = self.Conv(x)
x = self.C3_1(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 = model_K().to(device)
model
运行结果:
Using cuda device
model_K(
(Conv): Conv(
(conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_1): C3(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): 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()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(classifier): Sequential(
(0): Linear(in_features=802816, out_features=100, bias=True)
(1): ReLU()
(2): Linear(in_features=100, out_features=4, bias=True)
)
)
2. 查看模型详情
import torchsummary as summary
summary.summary(model,(3,224,224))
运行结果:
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 32, 112, 112] 864
BatchNorm2d-2 [-1, 32, 112, 112] 64
SiLU-3 [-1, 32, 112, 112] 0
Conv-4 [-1, 32, 112, 112] 0
Conv2d-5 [-1, 32, 112, 112] 1,024
BatchNorm2d-6 [-1, 32, 112, 112] 64
SiLU-7 [-1, 32, 112, 112] 0
Conv-8 [-1, 32, 112, 112] 0
Conv2d-9 [-1, 32, 112, 112] 1,024
BatchNorm2d-10 [-1, 32, 112, 112] 64
SiLU-11 [-1, 32, 112, 112] 0
Conv-12 [-1, 32, 112, 112] 0
Conv2d-13 [-1, 32, 112, 112] 9,216
BatchNorm2d-14 [-1, 32, 112, 112] 64
SiLU-15 [-1, 32, 112, 112] 0
Conv-16 [-1, 32, 112, 112] 0
Bottleneck-17 [-1, 32, 112, 112] 0
Conv2d-18 [-1, 32, 112, 112] 1,024
BatchNorm2d-19 [-1, 32, 112, 112] 64
SiLU-20 [-1, 32, 112, 112] 0
Conv-21 [-1, 32, 112, 112] 0
Conv2d-22 [-1, 32, 112, 112] 9,216
BatchNorm2d-23 [-1, 32, 112, 112] 64
SiLU-24 [-1, 32, 112, 112] 0
Conv-25 [-1, 32, 112, 112] 0
Bottleneck-26 [-1, 32, 112, 112] 0
Conv2d-27 [-1, 32, 112, 112] 1,024
BatchNorm2d-28 [-1, 32, 112, 112] 64
SiLU-29 [-1, 32, 112, 112] 0
Conv-30 [-1, 32, 112, 112] 0
Conv2d-31 [-1, 32, 112, 112] 9,216
BatchNorm2d-32 [-1, 32, 112, 112] 64
SiLU-33 [-1, 32, 112, 112] 0
Conv-34 [-1, 32, 112, 112] 0
Bottleneck-35 [-1, 32, 112, 112] 0
Conv2d-36 [-1, 32, 112, 112] 1,024
BatchNorm2d-37 [-1, 32, 112, 112] 64
SiLU-38 [-1, 32, 112, 112] 0
Conv-39 [-1, 32, 112, 112] 0
Conv2d-40 [-1, 64, 112, 112] 4,096
BatchNorm2d-41 [-1, 64, 112, 112] 128
SiLU-42 [-1, 64, 112, 112] 0
Conv-43 [-1, 64, 112, 112] 0
C3-44 [-1, 64, 112, 112] 0
Linear-45 [-1, 100] 80,281,700
ReLU-46 [-1, 100] 0
Linear-47 [-1, 4] 404
================================================================
Total params: 80,320,536
Trainable params: 80,320,536
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 150.06
Params size (MB): 306.40
Estimated Total Size (MB): 457.04
----------------------------------------------------------------
三、 训练模型
1. 编写训练函数
def train(dataloader,model,loss_fn,optimizer):
size=len(dataloader.dataset) #训练集大小
num_batches=len(dataloader) #批次数目
train_loss,train_acc=0,0 #初始化损失和正确率
for x,y in dataloader: #获取图片和标签
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
#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_size/=size
train_loss/=num_batches
return train_acc,train_loss
2. 编写测试函数
测试函数和训练函数大致相同,但是由于不进行梯度下降对网络权重进行更新,所以不需要传入优化器
def test(dataloader,model,loss_fn):
size=len(dataloader.dataset) #测试集的大小
num_batches=len(dataloader) #批次数目
test_loss,test_acc=0,0
#当不进行训练时,停止梯度更新,节省计算内存消耗
with torch.no_grad():
for imgs,target in dataloader:
imgs,target=imgs.to(device),target.to(device)
#计算loss
target_pred=model(imgs)
loss=loss_fn(target_pred,target)
test_loss+=loss.item()
test_acc+=(target_pred.argmax(1)==target).type(torch.float).sum().item()
test_acc/=size
test_loss/=num_batches
return test_acc,test_loss
3. 正式训练
import copy
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=r'C:\Users\Administrator\PycharmProjects\pytorchProject1\第P8周:YOLOv5-C3模块实现\p8_model.pth' #保存的参数文件名
torch.save(model.state_dict,PATH)
print('Done')
运行结果:
Epoch: 1,Train_acc:86.1%,Train_loss:0.478,Test_acc:79.6%,Test_loss:0.977,Lr:1.00E-04
Epoch: 2,Train_acc:90.4%,Train_loss:0.360,Test_acc:88.9%,Test_loss:0.324,Lr:1.00E-04
Epoch: 3,Train_acc:91.3%,Train_loss:0.285,Test_acc:84.4%,Test_loss:0.789,Lr:1.00E-04
Epoch: 4,Train_acc:91.7%,Train_loss:0.296,Test_acc:83.6%,Test_loss:0.525,Lr:1.00E-04
Epoch: 5,Train_acc:93.9%,Train_loss:0.188,Test_acc:87.6%,Test_loss:0.548,Lr:1.00E-04
Epoch: 6,Train_acc:95.7%,Train_loss:0.178,Test_acc:89.8%,Test_loss:0.383,Lr:1.00E-04
Epoch: 7,Train_acc:96.1%,Train_loss:0.111,Test_acc:88.4%,Test_loss:0.461,Lr:1.00E-04
Epoch: 8,Train_acc:97.6%,Train_loss:0.083,Test_acc:88.4%,Test_loss:0.595,Lr:1.00E-04
Epoch: 9,Train_acc:96.4%,Train_loss:0.139,Test_acc:89.3%,Test_loss:0.343,Lr:1.00E-04
Epoch:10,Train_acc:97.9%,Train_loss:0.061,Test_acc:88.0%,Test_loss:0.396,Lr:1.00E-04
Epoch:11,Train_acc:98.6%,Train_loss:0.061,Test_acc:92.0%,Test_loss:0.361,Lr:1.00E-04
Epoch:12,Train_acc:97.6%,Train_loss:0.079,Test_acc:91.1%,Test_loss:0.410,Lr:1.00E-04
Epoch:13,Train_acc:97.0%,Train_loss:0.093,Test_acc:90.7%,Test_loss:0.562,Lr:1.00E-04
Epoch:14,Train_acc:96.2%,Train_loss:0.201,Test_acc:89.3%,Test_loss:0.398,Lr:1.00E-04
Epoch:15,Train_acc:98.1%,Train_loss:0.078,Test_acc:88.0%,Test_loss:0.639,Lr:1.00E-04
Epoch:16,Train_acc:98.7%,Train_loss:0.080,Test_acc:91.1%,Test_loss:0.394,Lr:1.00E-04
Epoch:17,Train_acc:99.1%,Train_loss:0.033,Test_acc:89.8%,Test_loss:0.459,Lr:1.00E-04
Epoch:18,Train_acc:98.3%,Train_loss:0.053,Test_acc:91.1%,Test_loss:0.442,Lr:1.00E-04
Epoch:19,Train_acc:98.3%,Train_loss:0.053,Test_acc:89.3%,Test_loss:0.509,Lr:1.00E-04
Epoch:20,Train_acc:99.0%,Train_loss:0.020,Test_acc:89.8%,Test_loss:0.481,Lr:1.00E-04
Done
四、 结果可视化
1. Loss与Accuracy图
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.rcParams['figure.dpi']=300
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()
运行结果:
2. 模型评估
best_model.eval()
epoch_test_acc,epoch_test_loss=test(test_dl,best_model,loss_fn)
epoch_test_acc,epoch_test_loss
运行结果:
(0.9155555555555556, 0.37511309209529703)
3. 指定图片进行预测
建立预测模型:
from PIL import Image
classes=list(total_data.class_to_idx)
def predict_one_image(image_path,model,transform,classes):
test_img=Image.open(image_path).convert('RGB')
plt.imshow(test_img) #展示预测的图片
test_img=transform(test_img)
img=test_img.to(device).unsqueeze(0)
model.eval()
output=model(img)
_,pred=torch.max(output,1)
pred_class=classes[pred]
print(f'预测结果是:{pred_class}')
预测图片:
predict_one_image(image_path=r'D:\THE MNIST DATABASE\weather_photos\cloudy\cloudy1.jpg',
model=model,transform=train_transforms,classes=classes)
运行结果:
预测结果是:cloudy
五、心得体会
加入C3模块后,模型的准确率提升比较明显,仅仅20轮的情况下已经达到原来模型40轮的准确率。