五、模型训练
# 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
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
# 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_loss
''' 自定义设置动态学习率 '''
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
# 设置初始学习率
learn_rate = 1e-4
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
# 定义学习率调整函数
lambda1 = lambda epoch: 0.92 ** (epoch // 4)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) # 选定调整方法
# 定义损失函数
loss_fn = nn.CrossEntropyLoss()
# 定义训练参数
epochs = 40
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 用于保存最佳模型的准确率
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）
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))
# 保存最佳模型到文件中
PATH = './best_model.pth' # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)
print('Done')在非实时编译器中运行出现Python 脚本中使用多进程相关问题报错，问题通常发生在没有正确使用 if __name__ == '__main__': 块的情况下。为了解决这个问题，我将完整代码修改如下：
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os, PIL, random, pathlib, warnings
import copy
warnings.filterwarnings("ignore")
def main():
# 您的现有代码放在这里
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
import os, PIL, random, pathlib
data_dir = 'D:/P6/48-data/'
data_dir = pathlib.Path(data_dir)
data_path = list(data_dir.glob('*'))
print(data_path)
classname = [str(path).split("\\")[3] for path in data_path]
print(classname)
train_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.39354826, 0.41713402, 0.48036146],
std=[0.25076334, 0.25809455, 0.28359835]
)
])
total_data = datasets.ImageFolder("D:/P6/48-data/", transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)
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])
print(train_dataset, test_dataset)
batch_size = 32
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)
from torchvision.models import vgg16
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using {} device\n".format(device))
''' 调用官方的VGG-16模型 '''
# 加载预训练模型，并且对模型进行微调
model = vgg16(pretrained=True).to(device) # 加载预训练的vgg16模型
for param in model.parameters():
param.requires_grad = False # 冻结模型的参数，这样子在训练的时候只训练最后一层的参数
# 修改classifier模块的第6层（即：(6): Linear(in_features=4096, out_features=2, bias=True)）
# 注意查看我们下方打印出来的模型
model.classifier._modules['6'] = nn.Linear(4096, 17) # 修改vgg16模型中最后一层全连接层，输出目标类别个数
model.to(device)
print(model)
# 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
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
# 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_loss
''' 自定义设置动态学习率 '''
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
# 设置初始学习率
learn_rate = 1e-4
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
# 定义学习率调整函数
lambda1 = lambda epoch: 0.92 ** (epoch // 4)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) # 选定调整方法
# 定义损失函数
loss_fn = nn.CrossEntropyLoss()
# 定义训练参数
epochs = 40
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 用于保存最佳模型的准确率
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）
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))
# 保存最佳模型到文件中
PATH = './best_model.pth' # 保存的参数文件名
torch.save(best_model.state_dict(), PATH)
print('Done')
if __name__ == '__main__':
main()
