P8打卡——YOLOv5-C3模块实现天气识别
- 🍨 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
1.检查GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
2.查看数据
import random
data_dir='data/weather_photos'
data_dir=pathlib.Path(data_dir)
data_paths=list(data_dir.glob('*'))
classNames=[str(path).split('\\')[2] for path in data_paths]
classNames
3.划分数据集
train_transforms=transforms.Compose([transforms.Resize([224,224]),transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize(mean=[0.482,0.456,0.406],std=[0.229,0.224,0.225])
])
test_transforms=transforms.Compose([transforms.Resize([224,224]),transforms.ToTensor(),transforms.Normalize(mean=[0.482,0.456,0.406],std=[0.229,0.224,0.225])
])
total_data=datasets.ImageFolder("data/weather_photos/",transform=train_transforms)
total_datatotal_data.class_to_idxtrain_size=int(0.8*len(total_data))
test_size=len(total_data)-train_size
train_data,test_data=torch.utils.data.random_split(total_data,[train_size,test_size])
train_data,test_databatch_size=4
train_dl=torch.utils.data.DataLoader(train_data,batch_size,shuffle=True,num_workers=1)
test_dl=torch.utils.data.DataLoader(test_data,batch_size,shuffle=True,num_workers=1)for X,y in train_dl:print(X.shape)print(y.shape)break
4.创建模型
import torch.nn.functional as Fdef 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-padreturn pclass Conv(nn.Module):# Standard convolutiondef __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groupssuper().__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 bottleneckdef __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e) # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_, c2, 3, 1, g=g)self.add = shortcut and c1 == c2def 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 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e) # hidden channelsself.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1self.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 xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = model_K().to(device)
modelimport torchsummary as summary
summary.summary(model,(3,224,224))
5.编译及训练模型
def train(dataloader,model,loss_fn,optimizer):size=len(dataloader.dataset)num_batches=len(dataloader)train_loss,train_acc=0,0for X,y in dataloader:X,y =X.to(device),y.to(device)pred=model(X)loss=loss_fn(pred,y)#反向传播optimizer.zero_grad()loss.backward()optimizer.step()train_loss+=loss.item()train_acc+=(pred.argmax(1)==y).type(torch.float).sum().item()train_acc/=sizetrain_loss/=num_batchesreturn train_acc,train_lossdef test(dataloader,model,loss_fn):size=len(dataloader.dataset)num_batches=len(dataloader)test_loss,test_acc=0,0with 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/=sizetest_loss/=num_batchesreturn test_acc,test_lossimport copy
optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn = nn.CrossEntropyLoss()
epochs = 20
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)# 保存最佳模型到 best_modelif epoch_test_acc > best_acc:best_acc = epoch_test_accbest_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))
# 保存最佳模型到文件中
PATH = './best_model.pth'
torch.save(model.state_dict(), PATH)
print('Done')
6.结果可视化
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.rcParams['figure.dpi']=100epochs_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()
7.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_lossepoch_test_acc
总结：
1.C3模块
import torch.nn.functional as Fdef 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-padreturn pclass Conv(nn.Module):# Standard convolutiondef __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groupssuper().__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 bottleneckdef __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e) # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_, c2, 3, 1, g=g)self.add = shortcut and c1 == c2def 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 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e) # hidden channelsself.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1self.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 xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = model_K().to(device)
model