This repository was archived by the owner on Feb 16, 2022. It is now read-only.
This repository was archived by the owner on Feb 16, 2022. It is now read-only.
test set for Visual Genome QA #97
Description
Hi! I see that the fastrcnn detector was trained on both train + val split of VG. Is there some test split that we can use for inference on the whole Multitask model?