Skip to content

Latest commit

 

History

History
35 lines (18 loc) · 666 Bytes

datasets.rst

File metadata and controls

35 lines (18 loc) · 666 Bytes
Raw

Visual Question Answering

Visual Question Answering datasets are available in multimodal. Annotations data are automatically downloaded and processed when the class is instanciated. Note that the pre-processing can take several minutes.

.. autoclass:: multimodal.datasets.VQA
    :inherited-members:


.. autoclass:: multimodal.datasets.VQA2
    :inherited-members:



.. autoclass:: multimodal.datasets.VQACP
    :inherited-members:



.. autoclass:: multimodal.datasets.VQACP2
    :inherited-members:

CLEVR

https://cs.stanford.edu/people/jcjohns/clevr/

.. autoclass:: multimodal.datasets.CLEVR
    :inherited-members: