Sahand

Yes, exactly the same error.

There is [another script](https://github.com/rowanz/neural-motifs/blob/master/scripts/refine_for_detection.sh) which fine-tunes the model trained in sgcl, given the object detector's output. That would give the results for SGdet setting.

No. But maybe it's possible to make it work with the [pretrained OPT weights](https://github.com/facebookresearch/metaseq/tree/main/projects/OPT) recently released by facebook and the [pretrained CLIP weights](https://github.com/openai/CLIP).

> Its actually not a good idea since CLIP is not task agnostic, as explained in CLIP's paper tasks with non natural images like EuroSAT perform poorly. So you would...

You might be able to use Flamingo for your use case by prompting (I'm not sure if it works but its worth a try). By prompting I mean that u...

Now I understand that your reported numbers are in fact not comparable to Neural Motifs. I consider this some sort of [unintended?] mistake in reporting the results. In NM (and...

@bknyaz I avoided using this repository for my research. No one responded to my complaint for a year. The mentioned evaluation issue affects the heart of this paper's contribution and...