PureT
PureT copied to clipboard
some questions about TEST process
@232525 Dear author, I use custom datasets. I used preprocess program, and create some files, like fisrt picture. I can get result, but there are some mistakes in "Loading and preparing results..." . Just like second picture. How can i solve it?
The error occurred in the process of computing metrics. If you do not need to validate, you can comment out #L73 of https://github.com/232525/PureT/blob/main/evaluation/evaler.py#L73. Or you have to modify the codes of loading dataset in coco_caption/ for compatibility with your own datasets, please refer to https://github.com/AIChallenger/AI_Challenger_2017/tree/master/Evaluation/caption_eval/coco_caption.