Scidata.CIFAR10.download

You're seeing just the function download, go back to Scidata.CIFAR10 module for more information.

Downloads the CIFAR10 training dataset or fetches it locally.

Options

  • :transform_images - A function that transforms images, defaults to & &1.

    It accepts a tuple like {binary_data, tensor_type, data_shape} which can be used for converting the binary_data to a tensor with a function like:

    fn {labels_binary, type, _shape} ->
      labels_binary
      |> Nx.from_binary(type)
      |> Nx.new_axis(-1)
      |> Nx.equal(Nx.tensor(Enum.to_list(0..9)))
      |> Nx.to_batched_list(32)
    end
  • :transform_labels - similar to :transform_images but applied to dataset labels

Examples

iex> Scidata.CIFAR10.download()
{{<<59, 43, 50, 68, 98, 119, 139, 145, 149, 149, 131, 125, 142, 144, 137, 129,
137, 134, 124, 139, 139, 133, 136, 139, 152, 163, 168, 159, 158, 158, 152,
148, 16, 0, 18, 51, 88, 120, 128, 127, 126, 116, 106, 101, 105, 113, 109,
112, ...>>, {:u, 8}, {50000, 3, 32, 32}},
{<<6, 9, 9, 4, 1, 1, 2, 7, 8, 3, 4, 7, 7, 2, 9, 9, 9, 3, 2, 6, 4, 3, 6, 6, 2,
    6, 3, 5, 4, 0, 0, 9, 1, 3, 4, 0, 3, 7, 3, 3, 5, 2, 2, 7, 1, 1, 1, ...>>,
  {:u, 8}, {50000}}}