MILVLG_admin

Currently, we do not support attribute prediction, as the original implementation in Caffe is not that straightforward to migrate to the d2 backend. They need another forward pass with the...

@adrelino @airsplay Hi guys, We have a parallel work to reimplement the bottom-up-attention in PyTorch, and we also use Detectron2 as our backend coincidently :) We have converted the Caffe...

> Great to know that. I have added the link to your project to the Readme file. > > BTW, I noticed that the attribute head is closed [here](https://github.com/MILVLG/bottom-up-attention.pytorch/blob/57e66ef2cc3732c2403aa78ef68579e57064c41e/configs/bua-caffe/extract-bua-caffe-r101.yaml#L11). It...

感谢反馈，我们也在持续优化中

Thanks for your wonderful work. Looking forward to the training scripts on downstream textvqa datasets!