Pytorch指定数据加载器使用子进程

torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True,num_workers=4, pin_memory=True)

num_workers 参数是 DataLoader 类的一个参数，它指定了数据加载器使用的子进程数量。通过增加 num_workers 的数量，可以并行地读取和预处理数据，从而提高数据加载的速度。

通常情况下，增加 num_workers 的数量可以提高数据加载的效率，因为它可以使数据加载和预处理工作在多个进程中同时进行。然而，当 num_workers 的数量超过一定阈值时，增加更多的进程可能不会再带来更多的性能提升，甚至可能会导致性能下降。

这是因为增加 num_workers 的数量也会增加进程间通信的开销。当 num_workers 的数量过多时，进程间通信的开销可能会超过并行化所带来的收益，从而导致性能下降。

此外，还需要考虑到计算机硬件的限制。如果你的计算机 CPU 核心数量有限，增加 num_workers 的数量也可能会导致性能下降，因为每个进程需要占用 CPU 核心资源。

因此，对于 num_workers 参数的设置，需要根据具体情况进行调整和优化。通常情况下，一个合理的 num_workers 值应该在 2 到 8 之间，具体取决于你的计算机硬件配置和数据集大小等因素。在实际应用中，可以通过尝试不同的 num_workers 值来找到最优的配置。

综上所述，当 num_workers 的值从 4 增加到 8 时，如果你的计算机硬件配置和数据集大小等因素没有发生变化，那么两者之间的性能差异可能会很小，或者甚至没有显著差异。

测试代码如下

import torch
import torchvision
import matplotlib.pyplot as plt
import torchvision.models as models
import torch.nn as nn
import torch.optim as optim
import torch.multiprocessing as mp
import time
 
if __name__ == '__main__':
    mp.freeze_support()
    train_on_gpu = torch.cuda.is_available()
    if not train_on_gpu:
        print('CUDA is not available. Training on CPU...')
    else:
        print('CUDA is available! Training on GPU...')
 
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
    batch_size = 4
    # 设置数据预处理的转换
    transform = torchvision.transforms.Compose([
        torchvision.transforms.Resize((512,512)),  # 调整图像大小为 224x224
        torchvision.transforms.ToTensor(),  # 转换为张量
        torchvision.transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 归一化
    ])
    dataset = torchvision.datasets.ImageFolder('C:\\Users\\ASUS\\PycharmProjects\\pythonProject1\\cats_and_dogs_train',
                                                     transform=transform)
 
 
    val_ratio = 0.2
    val_size = int(len(dataset) * val_ratio)
    train_size = len(dataset) - val_size
    train_dataset, val_dataset = torch.utils.data.random_split(dataset, [train_size, val_size])
 
    train_dataset = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True,num_workers=4, pin_memory=True)
    val_dataset = torch.utils.data.DataLoader(val_dataset, batch_size=batch_size, shuffle=True,num_workers=4, pin_memory=True)
 
    model = models.resnet18()
 
    num_classes = 2
    for param in model.parameters():
        param.requires_grad = False
 
    model.fc = nn.Sequential(
        nn.Dropout(),
        nn.Linear(model.fc.in_features, num_classes),
        nn.LogSoftmax(dim=1)
    )
    optimizer = optim.Adam(model.parameters(), lr=0.001)
    criterion = nn.CrossEntropyLoss().to(device)
    model.to(device)
 
    filename = "recognize_cats_and_dogs.pt"
 
    def save_checkpoint(epoch, model, optimizer, filename):
        checkpoint = {
            'epoch': epoch,
            'model_state_dict': model.state_dict(),
            'optimizer_state_dict': optimizer.state_dict(),
            'loss': loss,
        }
        torch.save(checkpoint, filename)
 
    num_epochs = 3
    train_loss = []
    for epoch in range(num_epochs):
        running_loss = 0
        correct = 0
        total = 0
        epoch_start_time = time.time()
        for i, (inputs, labels) in enumerate(train_dataset):
            # 将数据放到设备上
            inputs, labels = inputs.to(device), labels.to(device)
            # 前向计算
            outputs = model(inputs)
            # 计算损失和梯度
            loss = criterion(outputs, labels)
            optimizer.zero_grad()
            loss.backward()
            # 更新模型参数
            optimizer.step()
            # 记录损失和准确率
            running_loss += loss.item()
            train_loss.append(loss.item())
            _, predicted = torch.max(outputs.data, 1)
            correct += (predicted == labels).sum().item()
            total += labels.size(0)
        accuracy_train = 100 * correct / total
        # 在测试集上计算准确率
        with torch.no_grad():
            running_loss_test = 0
            correct_test = 0
            total_test = 0
            for inputs, labels in val_dataset:
                inputs, labels = inputs.to(device), labels.to(device)
                outputs = model(inputs)
                loss = criterion(outputs, labels)
                running_loss_test += loss.item()
 
                _, predicted = torch.max(outputs.data, 1)
                correct_test += (predicted == labels).sum().item()
                total_test += labels.size(0)
            accuracy_test = 100 * correct_test / total_test
            # 输出每个 epoch 的损失和准确率
        epoch_end_time = time.time()
        epoch_time = epoch_end_time - epoch_start_time
        print("Epoch [{}/{}], Time: {:.4f}s, Loss: {:.4f}, Train Accuracy: {:.2f}%, Loss: {:.4f}, Test Accuracy: {:.2f}%"
              .format(epoch + 1, num_epochs,epoch_time,running_loss / len(val_dataset),
                      accuracy_train, running_loss_test / len(val_dataset), accuracy_test))
        save_checkpoint(epoch, model, optimizer, filename)
 
    plt.plot(train_loss, label='Train Loss')
    # 添加图例和标签
    plt.legend()
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.title('Training Loss')
 
    # 显示图形
    plt.show()

不同num_workers的结果如下