Downloads the Caltech101 training dataset or fetches it locally.

Returns a tuple of format:

{{images_binary, images_type, images_shape},
 {labels_binary, labels_type, labels_shape}}

If you want to one-hot encode the labels, you can:

labels_binary
|> Nx.from_binary(labels_type)
|> Nx.new_axis(-1)
|> Nx.equal(Nx.tensor(Enum.to_list(1..102)))

options

Options.

• :base_url - Dataset base URL.

  Defaults to "https://s3.amazonaws.com/fast-ai-imageclas/"

• :dataset_file - Dataset filename.

  Defaults to "caltech_101.tgz"

• :cache_dir - Cache directory.

  Defaults to System.tmp_dir!()