search

salesforce / ALBEF

Code for ALBEF: a new vision-language pre-training method
BSD 3-Clause "New" or "Revised" License
1.46k stars 193 forks source link

test in VQA dataset #48

Closed haoshuai714 closed 2 years ago

haoshuai714 commented 2 years ago

when I test in VQA task, I run : python -m torch.distributed.launch --nproc_per_node=8 --use_env VQA.py \ --config ./configs/VQA.yaml \ --output_dir output/vqa \ --checkpoint ./ALBEF.pth But, when I run one epoch, I get the result flood is empty? How to get the result? when all epoch training end?

LiJunnan1992 commented 2 years ago

Yes the result will be generated after all epochs.

LiJunnan1992 commented 2 years ago

You can also set --evaluate to directly use a finetuned model to generate result.

haoshuai714 commented 2 years ago

Thanks!

haoshuai714 commented 2 years ago

Hi: I get the file: vqa_result_epoch7.json. how to get the paper result?

LiJunnan1992 commented 2 years ago

Please go to the official evaluation server by the VQA team

haoshuai714 commented 2 years ago

Could you give me a link? Thanks!

LiJunnan1992 commented 2 years ago

https://eval.ai/web/challenges/challenge-page/830/submission