Open Songinpyo opened 4 months ago
Hi @Songinpyo, Thanks for your query and sorry for the late response. We followed the step-by-step data pre-processing steps as described in the EgoTaskQA repository: https://github.com/Buzz-Beater/EgoTaskQA/tree/main/baselines#preprocessing
To use EgoVLPv2 (specifically EgoTaskQA) on custom VQA dataset, it is essential to preprocess the metadata about questions ans answers.
Specifically the "answer_encode" is needed. How can I encode other datasets to EgotaskQA form.
Have you used the official EgoTaskQA's preprocess code?