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

Microsoft OCR data could not be found #17

Closed zhousheng97 closed 2 years ago

zhousheng97 commented 2 years ago

Hello, I would like to know whether there are IMBD files and extracted features corresponding to Microsoft OCR in the data provided? I did not find the corresponding file, could you please clearly point out the corresponding path of each data? The IMDB files in the figure all seem to correspond to Rosetta OCR. a00359b0ff0f0505e510b488b4c3a90

zyang-ur commented 2 years ago

Hi @zhousheng97 ,

For the downstream task datasets (e.g., TextVQA, STVQA), we do not create new imdb files for MS-OCR. Instead, we load (overwrite) the OCR directly from the MS-OCR's info.npy file in the data loader, e.g., here: https://github.com/microsoft/TAP/blob/352891f93c75ac5d6b9ba141bbe831477dcdd807/pythia/datasets/vqa/m4c_textvqa/dataset.py#L185

zhousheng97 commented 2 years ago

Hi @zhousheng97 ,

For the downstream task datasets (e.g., TextVQA, STVQA), we do not create new imdb files for MS-OCR. Instead, we load (overwrite) the OCR directly from the MS-OCR's info.npy file in the data loader, e.g., here:

https://github.com/microsoft/TAP/blob/352891f93c75ac5d6b9ba141bbe831477dcdd807/pythia/datasets/vqa/m4c_textvqa/dataset.py#L185

Thanks.