image dataset to .npy

[virginie-do]

How did you transform the vqa dataset to a .npy file available for download?

[meetps]

The documentation about converting VQA dataset to the npy files provided is described here

Kindly close the issue if you feel your query has been answered.

[apsdehal]

In simple terms, you put metadata as dict on first line and each question and its related data's dict on a separate line.

For saving, push all these dicts in an array and save using np.save.

[virginie-do]

Thank you.

The documentation about converting VQA dataset to the npy files provided is described here

Are these scripts mentioned in the Readme available somewhere?
data_prep/vqa_v2.0/build_vqa_2.0_imdb.py
data_prep/vqa_v2.0/extract_word_glove_embedding.py
data_prep/vqa_v2.0/download_vqa_2.0.sh

[apsdehal]

Yup, they are in this folder: https://github.com/facebookresearch/pythia/tree/master/pythia/legacy/data_prep/vqa_v2.0

[apsdehal]

Closing as resolved. @virginie-do if you have any other questions please open up a new issue.