search

LinWeizheDragon / Retrieval-Augmented-Visual-Question-Answering

This is the official repository for Retrieval Augmented Visual Question Answering
GNU General Public License v3.0
184 stars 15 forks source link

Some bug when processing img_key #5

Closed yao-jz closed 1 year ago

yao-jz commented 1 year ago

When generating VinVL features, in file: prepare_data_for_okvqa.py

Theimg_key is ''.

img_key = img_p.split('.')[0].split('_')[-1] should be img_key = str(imgId).zfill(12)

The same for ocr.py

LinWeizheDragon commented 1 year ago

Thanks for pointing this out. I may forgot to update some of the codes. Just do whatever it works ^_^