Could the trained dual model be available?

[Tang Ruixue]

Thanks for your work on VQG.
I want to generate new questions given the answers in my project and I have learned that it takes 124G memory, which is not convenient for me. So, it is very grateful if you could provide the trained dual model.
Thanks again.

[goonmeet]

The vqa2.0 dataset did not automatically download for me.

Any other place we can access the data this work used?

[Tang Ruixue]

@goonmeet https://visualqa.org/download.html

[goonmeet]

Thanks!