Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fine-tune VilBERT on a different VQA dataset #40

Open
claudiogreco opened this issue Dec 17, 2019 · 2 comments
Open

Fine-tune VilBERT on a different VQA dataset #40

claudiogreco opened this issue Dec 17, 2019 · 2 comments

Comments

@claudiogreco
Copy link

claudiogreco commented Dec 17, 2019

Hello,

I am trying to fine-tune and evaluate the pre-trained VilBERT model on a different VQA dataset, but I am finding it a bit difficult to quickly do it. Could you please briefly describe the steps needed to fine-tune the model on a different VQA dataset?

Thank you!

Best,
Claudio

@johntiger1
Copy link

Also have this question, I believe the current pre-trained VilBERT on VQA only works if you follow their paper exactly, i.e. you VQA must be a classification from 1 of 10 possible answers

@alice-cool
Copy link

Also have this question, I believe the current pre-trained VilBERT on VQA only works if you follow their paper exactly, i.e. you VQA must be a classification from 1 of 10 possible answers

What about the result, I run the evaluate_tasks.py Only got the score is 0.0

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants