concepts.benchmark.clevr.dataset.make_custom_transfer_dataset#

make_custom_transfer_dataset(scenes_json, questions_json, image_root, query_list_key, custom_fields, *, image_transform=None, output_vocab_json=None, **kwargs)[source]#

Make a CLEVR custom transfer dataset. See CLEVRCustomTransferDataset for more details.

Parameters:

  • scenes_json (str) – the path to the scenes json file.

  • questions_json (str) – the path to the questions json file.

  • image_root (str) – the root directory of the images.

  • query_list_key (str) – the key of the query list in the questions json file (e.g., ‘questions’ or ‘questions_human’).

  • custom_fields (Sequence[str]) – the custom fields to be included in the dataset. These are fields in the scene annotations.

  • image_transform – the image transform (torchvision transform). If None, a default transform will be used.

  • output_vocab_json – the path to the output vocab json file. If None, the output vocab will be built from the dataset.

  • **kwargs – other keyword arguments for the dataset.

Returns:

a CLEVR custom transfer dataset.

Return type:

CLEVRCustomTransferDataset

On this page