search

microsoft / TAP

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption, CVPR 2021 (Oral)
MIT License
70 stars 11 forks source link

TextCaps json file missing for TextVQA #11

Closed HenryJunW closed 2 years ago

HenryJunW commented 2 years ago

Hello, I would like to train the TextVQA model with the extra data of TextCaps, however, the file 'TextCaps_0.1_train.json' is not provided in Line https://github.com/microsoft/TAP/blob/352891f93c75ac5d6b9ba141bbe831477dcdd807/pythia/datasets/vqa/m4c_textvqa/dataset.py#L36. Thanks!

HenryJunW commented 2 years ago

Is that the same from the official website https://dl.fbaipublicfiles.com/textvqa/data/textcaps/TextCaps_0.1_train.json?

zyang-ur commented 2 years ago

Hi @HenryJunW,

Thank you so much for catching this!

Yes, your understanding is correct. I also uploaded the missing files (https://tapvqacaption.blob.core.windows.net/data/original_dl/TextCaps_0.1_train.json), feel free to have a check. Thank you :)