About the dataset

[Kenneth-Wong]

Is the relational_captions.json your final data for training the model? Could you provide the codes for preprocessing the raw VG dataset and explain how to get the relational_captions.json file? Thanks.

[Kenneth-Wong]

Oh I see that in preprocess.py, you use the relational_caption.json as input. It seems that the json file is from the raw VG dataset. However, on the VG website, I can only find the region_descriptions.json or region_graphs.json. Are they the same or do you change something on these raw json files to obtain the relational_caption.json ?

[Dong-JinKim]

Hello. The VG website doesn't contain our ''relational_caption.json'' file. This file can only be downloaded from our link https://drive.google.com/file/d/1cCN36poslxe7cCMkLnhYK0a-Y3vO4Rfn/view