ImageNet32 dataloader returning weird images

[varungupta31]

Hi, I was referring to the dataloader code for imagenet32. Upon visualizing the validation set, I am getting weird images.

Visualizing Code

transform = transforms.Compose([
    transforms.ToTensor()
])

d = ImageNet32(root = '.', train=False, transform = transform)
val_loader = torch.utils.data.DataLoader(d, batch_size=16, shuffle=False)

def imshow(img):
  npimg = img.numpy()
  plt.figure(figsize = (10, 10))
  plt.imshow(np.transpose(npimg, (1, 2, 0)))
  plt.show()

dataiter = iter(val_loader)
images, labels = next(dataiter)

imshow(torchvision.utils.make_grid(images))

Either i'm mistaking somewhere in the visualization, or the dataloader is not reading the npz correctly.
Can you please help resolve this?