def main(opt):
if type(opt.seed) is int:
torch.manual_seed(opt.seed)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
mvtec_ad = MVTecAD()
if not os.path.isdir(opt.dataset_name) or opt.force_download:
mvtec_ad.download(opt.dataset_name)
mvtec_ad.extract(opt.dataset_name)
images = datasets.ImageFolder(f"./{opt.dataset_name}/test",
transform=transforms.Compose([
transforms.Resize([opt.img_size] * 2),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5],
[0.5, 0.5, 0.5])
]))
test_dataloader = DataLoader(images, batch_size=1, shuffle=False)
generator = Generator(opt)
discriminator = Discriminator(opt)
encoder = Encoder(opt)
test_anomaly_detection(opt, generator, discriminator, encoder,
test_dataloader, device)
def main(opt):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
_, (x_test, y_test) = load_mnist("dataset",
training_label=opt.training_label,
split_rate=opt.split_rate)
test_mnist = SimpleDataset(x_test,
y_test,
transform=transforms.Compose([
transforms.ToPILImage(),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])
]))
test_dataloader = DataLoader(test_mnist, batch_size=1, shuffle=False)
generator = Generator(opt)
discriminator = Discriminator(opt)
encoder = Encoder(opt)
test_anomaly_detection(opt, generator, discriminator, encoder,
test_dataloader, device)
def main(opt):
if type(opt.seed) is int:
torch.manual_seed(opt.seed)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
_, (x_test, y_test) = load_mnist("dataset",
training_label=opt.training_label,
split_rate=opt.split_rate)
test_mnist = SimpleDataset(x_test, y_test,
transform=transforms.Compose(
[transforms.ToPILImage(),
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5])])
)
test_dataloader = DataLoader(test_mnist, batch_size=1, shuffle=False)
img_shape = (opt.channels, opt.img_size, opt.img_size)
generator = Generator(img_shape, opt.latent_dim)
discriminator = Discriminator(img_shape)
encoder = Encoder(img_shape)
test_anomaly_detection(opt, generator, discriminator, encoder,
test_dataloader, device)
def main(opt):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
transform = transforms.Compose([
transforms.Resize([opt.img_size] * 2),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
mvtec_ad = MVTecAD(".",
opt.dataset_name,
train=False,
transform=transform,
download=True)
test_dataloader = DataLoader(mvtec_ad, batch_size=1, shuffle=False)
generator = Generator(opt)
discriminator = Discriminator(opt)
encoder = Encoder(opt)
test_anomaly_detection(opt, generator, discriminator, encoder,
test_dataloader, device)