Rowan Zellers

Not sure what you mean here. I believe I got the RoIAlign implementation from other implementations of the same idea, though the paper is a bit vague on details so...

Not sure, if you investigate more and find an easy fix I’d love it if you submit a PR :) On Wed, Oct 3, 2018 at 8:46 AM Zhang Yidong...

You should be able to! Just change the dataloader to load from your own dataset. You’ll need to provide bounding boxes if using SGCls mode, boxes and labels if Predcls,...

> I'm still facing some issues. For example, in SGDet mode, there should be no Ground Truth right? (I just want to produce scene graphs from images, and I don't...

hi there, sorry for taking so long to respond. the visualization code isn't supported with the current version of the code. if you managed to get it to work i'd...

I think the problem is that you have a checkpoint for the sgcls model that you're treating like a detector checkpoint. If you download the provided detector checkpoint that should...

sorry I'm not sure how to use google colab. My guess is that you have a newer version of pytorch than what I used, so you would need to find...

I'm not entirely sure what's going on here, but it seems like you're using Python 2, which I don't support with this repo. have you tried using Python 3?

my guess is that you have a newer version of cuda than I did last year. Possibly you’d need to compile it with -arch=sm_61 ? Sorry for the difficulty anyways,...

sorry, I don't support training the relationship model with multiple GPUs right now (it's not what I used for these experiments). I found it actually doesn't help too much in...