🏡 我的环境:
语言环境:Python3.8.7
编译器:Jupyter notebook
深度学习环境:Pytorch
torch == 2.0.1+cu117
torchvision == 0.15.2+cu117
1 前期准备
1.1 设置GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import datasets
import os,PIL,pathlib
device = 'cuda' if torch.cuda.is_available() else 'cpu'
device
1.2 导入数据
import os,PIL,random,pathlib
data_dir = './9-data/'
data_dir = pathlib.Path(data_dir)
data_paths=list(data_dir.glob('*'))
classNames = [str(path).split('\\')[1] for path in data_paths]
data_transform = 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('./9-data/', transform=data_transform)
total_data
1.3 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])
batch_size = 5
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)
2 搭建包含Backbone模块的模型
2.1 搭建模型
import torch.nn.functional as F
import warnings
def autopad(k, p=None):
# pad to 'same'
if p is None:
p = k//2 if isinstance(k, int) else [x//2 for x in k]
return p
class Conv(nn.Module):
# 标准卷积
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=1, 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):
return x+self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
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(4*c_, 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, 5)
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
model = YOLOv5_backbone().to(device)
model```
## 2.2 查看模型详情
import torchsummary as summary
summary.summary(model, (3,224,224))
``‘’
3 训练模型
3.1 编写训练函数
def train(dataloader, model, loss_fun, optimizer):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 每个batch的数目(size/batch_size)
train_acc, train_loss = 0, 0
for x,y in dataloader:
x, y = x.to(device), y.to(device)
pred_y = model(x)
# 计算误差
loss = loss_fun(pred_y, y)
# 反向传播
optimizer.zero_grad() # grad属性归零
loss.backward() # 反向传播
optimizer.step() # 自动更新梯度
# 记录acc与loss
train_acc += (pred_y.argmax(1)==y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
3.2 编写测试函数
def test(dataloader, model, loss_fun):
size = len(dataloader.dataset)
num_batches = len(dataloader)
test_acc, test_loss = 0, 0
# 不进行梯度更新
with torch.no_grad():
for x,y in dataloader:
x, y = x.to(device), y.to(device)
pred = model(x)
loss = loss_fun(pred, y)
test_loss += loss.item()
test_acc += (pred.argmax(1)==y).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
3.3 正式训练
import copy
# 创建损失函数
loss_fun = nn.CrossEntropyLoss()
# 创建优化器
optimizer = torch.optim.Adam(model.parameters(),lr=1e-4)
epochs = 50
train_acc = []
train_loss = []
test_acc = []
test_loss = []
best_acc = 0
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fun, optim)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fun)
# 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)
# 获得当前学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, train_acc:{:.2f}, train_loss:{:.2f}, test_acc:{:.2f}, test_loss:{:.2f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
# 保存最佳模型到文件中
Path = './best_model.pth'
torch.save(best_model.state_dict(), Path)
print('Done!')
4 结果可视化
4.1 Loss 与 Accuracy
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正确显示负号
plt.figure(figsize=(12,3)) #设置画布大小
# 子图1
plt.subplot(1,2,1)
plt.plot(range(epochs), train_acc, label='Training Accuracy')
plt.plot(range(epochs), test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1,2,2)
plt.plot(range(epochs), train_loss, label='Training loss')
plt.plot(range(epochs), test_loss, label='Test loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
4.2 模型评估
# 将参数加载到model中
best_model.load_state_dict(torch.load(Path, map_location=device))
test_acc, test_loss = test(test_dl, best_model, loss_fun)