vmurahari3/visdial-bert
Implementation for "Large-scale Pretraining for Visual Dialog" https://arxiv.org/abs/1912.02379
PythonBSD-3-Clause
Issues
- 1
Could you please report the result pretrained on only vqa weight, in your paper, the rusults of pretrained on cc and cc+vqa are reported, but on vqa is missing. And in your provided checkpoints the weight of cc+vqa is missing
#12 opened by easonfudan - 0
- 1
Bus error (core dumped)
#13 opened by Xiao-wen-Sun - 9
Validation-only option
#9 opened by idansc - 3
no running on batch_size=80
#11 opened by linxi1158 - 1
Question about the rcnn boxes
#10 opened by AmeenAli - 2
Performance check in EvalAI
#8 opened by gicheonkang - 3
The length of train and val.
#4 opened by simpleshinobu - 1
Version of Faster RCNN
#7 opened by xiaoleihuang - 0
- 3
The question about training base model
#5 opened by simpleshinobu - 5
Error when train the base model
#3 opened by yangzhch6 - 1