search

facebookresearch / connect-caption-and-trace

A unified framework to jointly model images, text, and human attention traces.
78 stars 7 forks source link

Detectron2 Preprocessing #4

Open dondongwon opened 3 years ago

dondongwon commented 3 years ago

Hi, I'm having trouble following the steps for (5) Image features (with bounding boxes) extracted by a Mask-RCNN pretrained on Visual Genome. The step: Prepare COCO-style annotations for Visual Genome.

Could you elaborate on these steps? I think this is due to the depreciation of the repository that was linked, with the newer installation not allowing for the same steps.

I would really appreciate detailed preprocessing instructions, or if you could provide the preprocessed features directly, so it would be possible to recreate the results, that would be amazing as well.

Thank you for the amazing work!

zihangm commented 3 years ago

Hi, are you using Detectron2 branch named "genome_obj+attr" (instead of the master branch)? Let me know if you are getting error when using that (share the error message if possible).