Jeffrey Zhang

I am having this issue as well.

Ok, what other code did you try? Edit: After training overnight, it seems to be working fine.

Sorry seems I need to flip the mask I was inputting. However, my problem now is no matter what prompt I give, the generated image ignores the text and tries...

Hi Seth, thanks for the response! However, I am using the pretrained VQA model, so I did not generate adict.json or vdict.json files (as specified in the instructions). What is...

Oh ok, so I should create a new `exp_vdict.json` if I'm training from pretrained VQA? The command I'm running is: `python generate_explanation.py --ques_file ../VQA-X/Questions/v2_OpenEnded_mscoco_val2014_questions.json --ann_file ../VQA-X/Annotations/v2_mscoco_val2014_annotations.json --exp_file ../VQA-X/Annotations/val_exp_anno.json --gpu 1...

Hey Seth, so I recreated my `exp_vdict.json` when training from pretrained VQA, but I'm still getting the same issues :\. The models from my training end up in `"./snapshots/VQA-X/release".` These...