一、前期工作
1.导入数据集
数据集：工作台 - Heywhale.com
import torch
import matplotlib.pyplot as plt
from torchvision import transforms, datasets
import os, PIL, random, pathlib
data_dir = r'D:\P5-data\test'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("\\")[3]for path in data_paths]
print(classNames)
2.数据集划分
在Windows上，PyTorch的多进程数据加载有一些限制和问题，所以我们使用num_workers=0：在数据加载器创建时，将num_workers参数设置为0，这会禁用多进程数据加载。这是一个简单的解决方法，但可能会降低数据加载的速度。
torchvision.transforms.Compose()详解【Pytorch入门手册】_K同学啊的博客-CSDN博客
train_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
test_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])
])
train_dataset = datasets.ImageFolder("D:/P5-data/train/",transform=train_transforms)
test_dataset = datasets.ImageFolder("D:/P5-data/test/",transform=train_transforms)
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
关于批次大小的选择
需要根据特定问题和数据集的特征进行调整。一般来说，常见的批次大小值为32、64、128等。选择批次大小时，建议进行实验并监测训练和验证性能，以找到适合特定任务的最佳值。
3.检查数据
for images, labels in test_dl:
print("Shape of images [N, C, H, W]: ", images.shape)
print("Shape of labels: ", labels.shape, labels.dtype)
break
二、构建神经网络
import torch.nn as nn
import torch.nn.functional as F
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1=nn.Sequential(
nn.Conv2d(3, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.conv2=nn.Sequential(
nn.Conv2d(12, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.pool3=nn.Sequential(
nn.MaxPool2d(2)
)
self.conv4=nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.conv5=nn.Sequential(
nn.Conv2d(24, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.pool6=nn.Sequential(
nn.MaxPool2d(2)
)
self.dropout=nn.Sequential(
nn.Dropout(0.5)
)
self.fc=nn.Sequential(
nn.Linear(24*50*50, len(classNames)),
nn.Dropout(0.3)
)
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x)
x = self.conv2(x)
x = self.pool3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool6(x)
x = self.dropout(x)
# print(x.shape)
x = x.view(batch_size, -1) # flatten 编程全连接网络需要的输入(batch, 24*50*50_4
x = self.fc(x)
x = self.dropout(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Model().to(device)
print(model)
三、训练模型
1.动态学习率
def adjust_learning_rate(optimizer, epoch, start_lr):
lr = start_lr * (0.92 ** (epoch // 2))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
learn_rate = 1e-4 # 初始学习率
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
2.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_loss3.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_loss4.正式训练
loss_fn = nn.CrossEntropyLoss() # 创建损失汉书
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
# 更新学习率（使用自定义学习率使用）
adjust_learning_rate(optimizer, epoch, learn_rate)
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)
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))
print('Done')
四、结果可视化
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、完整代码
import torch
import matplotlib.pyplot as plt
from torchvision import transforms, datasets
import os, PIL, random, pathlib
data_dir = r'D:\P5-data\test'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("\\")[3]for path in data_paths]
print(classNames)
train_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
test_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])
])
train_dataset = datasets.ImageFolder("D:/P5-data/train/",transform=train_transforms)
test_dataset = datasets.ImageFolder("D:/P5-data/test/",transform=train_transforms)
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
import torch.nn as nn
import torch.nn.functional as F
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
self.conv1=nn.Sequential(
nn.Conv2d(3, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.conv2=nn.Sequential(
nn.Conv2d(12, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.pool3=nn.Sequential(
nn.MaxPool2d(2)
)
self.conv4=nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.conv5=nn.Sequential(
nn.Conv2d(24, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.pool6=nn.Sequential(
nn.MaxPool2d(2)
)
self.dropout=nn.Sequential(
nn.Dropout(0.5)
)
self.fc=nn.Sequential(
nn.Linear(24*50*50, len(classNames)),
nn.Dropout(0.3)
)
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x)
x = self.conv2(x)
x = self.pool3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool6(x)
x = self.dropout(x)
# print(x.shape)
x = x.view(batch_size, -1) # flatten 编程全连接网络需要的输入(batch, 24*50*50_4
x = self.fc(x)
x = self.dropout(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = Model().to(device)
def adjust_learning_rate(optimizer, epoch, start_lr):
# 每2个epoch衰减到原来的0.92
lr = start_lr * (0.92 ** (epoch // 2))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
learn_rate = 1e-4 # 初始学习率
optimizer = torch.optim.Adam(model.parameters(), lr=learn_rate)
# 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
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
loss_fn = nn.CrossEntropyLoss() # 创建损失汉书
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
# 更新学习率（使用自定义学习率使用）
adjust_learning_rate(optimizer, epoch, learn_rate)
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)
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))
print('Done')
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()
