Donglearner

Dear schoa > > > Thanks for taking the time to release the pre-trained models and extracted features for all datasets you've used. However, I noticed that the `COCO 2014...

> > > Solved, it seems that Azcopy is not only recommended, but necessary. Just download and install [Azcopy](https://docs.microsoft.com/en-us/azure/storage/common/storage-use-azcopy-v10#download-azcopy) and use the command provided at the bottom of [DOWNLOAD.md](https://github.com/pzzhang/VinVL/blob/main/DOWNLOAD.md) replacing...

Dear scholar, Could you provide the google drive links for COCOdatasets. Because in china, the dropboxlink is unstable, even I bought a vpn. Sometimes it ended abruptly, but the file...

Dear scholar, Could you provide the **google drive** links for COCOdatasets. Because in china, the dropboxlink is unstable, even I bought a vpn. Sometimes it ended abruptly, but the file...

 I found the lmdb could produced by the tsv file. Did you have the tsv file? I found peterson github only have smaller file. SO I think the tsv...

But VQA2.0 features should be the same with the github features from peterson. https://github.com/peteanderson80/bottom-up-attention#demo I have all the tsv file from peterson.

 If the script can convert the peterson features tsv to the format lmdb. If that , I will produce the Imdb file . But which file to produce, by...

Dear scholar, I use the pretrained parameters to evaluate the dataset VQA2.0 . But the results is the following. I replace the author', task_util.py with your uploading task_util.py. **What is...

> Also have this question, I believe the current pre-trained VilBERT on VQA _only_ works if you follow their paper exactly, i.e. you VQA must be a classification from 1...

https://github.com/facebookresearch/grid-feats-vqa is it right?