动手学习深度学习 P24 AlexNet 运行jupyter notebook代码出现错误

1. 出现错误1：DataLoader worker (pid(s) 8500, 7876, 30128, 1760) exited unexpectedly
2. 出现错误2：CUDA out of memory. Tried to allocate 100.00 MiB (GPU 0; 2.00 GiB total capacity; 829.83 MiB already allocated; 457.25 MiB free; 846.00 MiB reserved in total by PyTorch) (malloc at ..\c10\cuda\CUDACachingAllocator.cpp:289) (no backtrace available)

3. 解决：修改了load_data_fashion_mnist里的num_workers = 0就能跑了，就是把训练前加载数据那修改一下（因为我不知道如何在这个函数外面修改num_workers，所以只能把那个函数给复制过来修改一下）

import torchvision
from torch.utils import data
from torchvision import transforms
batch_size = 128

def load_data_fashion_mnist_temp(batch_size, resize=None):
    trans = [transforms.ToTensor()]
    if resize:
        trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(
        root="../data", train=True, transform=trans, download=True)
    mnist_test = torchvision.datasets.FashionMNIST(
        root="../data", train=False, transform=trans, download=True)
    return (data.DataLoader(mnist_train, batch_size, shuffle=True,
                            num_workers=0),
            data.DataLoader(mnist_test, batch_size, shuffle=False,
                            num_workers=0))

train_iter, test_iter = load_data_fashion_mnist_temp(batch_size, resize=224)

题外话：好家伙，跑了40min，但效果确实比LeNet好