torchvision.datasets¶
All datasets are subclasses of torch.utils.data.Dataset
i.e, they have __getitem__
and __len__
methods implemented.
Hence, they can all be passed to a torch.utils.data.DataLoader
which can load multiple samples parallelly using torch.multiprocessing
workers.
For example:
imagenet_data = torchvision.datasets.ImageFolder('path/to/imagenet_root/')
data_loader = torch.utils.data.DataLoader(imagenet_data,
batch_size=4,
shuffle=True,
num_workers=args.nThreads)
The following datasets are available:
All the datasets have almost similar API. They all have two common arguments:
transform
and target_transform
to transform the input and target respectively.
Imagenet-12¶
This should simply be implemented with an ImageFolder
dataset.
The data is preprocessed as described
here