VinVL can model the relation prediction?

[alice-cool]

I found VinVL 'S object and attribute lable is so bigger. So How to use the VinVL in predicate classification. At Now the project only provides 150 object. But visual genome +faster rcnn can detect 1370 object class. It is so big difference.

[alice-cool]

sgcls maybe not right. The code running failed

out_dists_sampled[is_overlap[box_ind, :, cls_ind], cls_ind] = 0.0 IndexError: index 61 is out of bounds for axis 2 with size 1 Killing subprocess 24877

[alice-cool]

if we don't provide relations we will get the following "exception"
AttributeError: 'SceneParser' object has no attribute 'relation_head'

[alice-cool]

So the flexible label provides whether it only can constrained to the predifined 151 object label?

[alice-cool]

Dear scholar,
Could the VinVL model can produce specific features for my designated or the grounding truth coordinate?

[hanxiaotian]

For releation predictions, you need to run our pretrained relation prediction models. You can refer to this #16 (comment)