Open ZhiqiangZ opened 5 years ago
@ZhiqiangZ We used the same split as the previous paper "DenseCap: Fully Convolutional Localization Networks for Dense Captioning". You can check this file for the train/val/test split: https://github.com/jcjohnson/densecap/blob/master/info/densecap_splits.json
I want to reproduce your code and want to run it on Visual Genome1.4 dataset. However, I cannot find the corresponding TXT file for train, val, and test when loading the dataset. Can you put these three files on GitHub?