linjieyangsc / densecap

Dense captioning with joint inference and visual context
Other
53 stars 24 forks source link

Unable to find train.txt, val.txt, test.txt in corresponding folder #3

Open ZhiqiangZ opened 5 years ago

ZhiqiangZ commented 5 years ago

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?

linjieyangsc commented 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