Dataset loader strange behavior

vision
1

hey,

I am using the code example from here
in my code :

dsets = datasets.ImageFolder(‘./dataset/’)
dset_loaders = torch.utils.data.DataLoader(dsets, batch_size=1, shuffle=False)

but I end up getting the following error :
TypeError : batch must contain tensors, numbers … found <class PIL …

Am I doing it wrong ?

2

You have to transform the images into Tensors.
You could use this code taken from the ImageNet example:

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

    train_dataset = datasets.ImageFolder(
        traindir,
        transforms.Compose([
            transforms.RandomResizedCrop(224),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize,
        ]))

In your case you need the transforms.ToTensor() transformation. The others are optional.