Question

我正在尝试加载我的自定义数据集以执行本文中的“单像素攻击”： https://arxiv.org/pdf/1710.08864v7.pdf

我正在使用 pytorch，所以我尝试修改此代码： https://github.com/DebangLi/one-pixel-attack-pytorch

但它失败可能是因为我的文件排列方式不同并且与原始使用的文件不同（我使用的是 imagenet 的一部分，称为 imagenette，而它是在 CIFAR10 上设计的）

这是我加载数据的方式：

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'drive/MyDrive/Datasets/imagenette2'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

如 pytorch 迁移学习教程中所述： https://colab.research.google.com/github/pytorch/tutorials/blob/gh-pages/_downloads/62840b1eece760d5e42593187847261f/transfer_learning_tutorial.ipynb

这里是如何在“单像素攻击”代码中加载数据：

def main():

    print "==> Loading data and model..."
    tranfrom_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
        ])
    test_set = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=tranfrom_test)
    testloader = torch.utils.data.DataLoader(test_set, batch_size=1, shuffle=True, num_workers=2)

    class_names = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
    assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
    checkpoint = torch.load('./checkpoint/%s.t7'%args.model)
    net = checkpoint['net']
    net.cuda()
    cudnn.benchmark = True

    print "==> Starting attck..."

    results = attack_all(net, testloader, pixels=args.pixels, targeted=args.targeted, maxiter=args.maxiter, popsize=args.popsize, verbose=args.verbose)
    print "Final success rate: %.4f"%results

当然，我还需要将那里的预测类更改为适合我的数据集的类。

感谢您的帮助！

加载自定义数据集而不是 CIFAR10

0 个答案: