Skip to content

Latest commit

 

History

History
23 lines (22 loc) · 666 Bytes

prepare_dataset.md

File metadata and controls

23 lines (22 loc) · 666 Bytes

Dataset preparation

Please follow LAVT for dataset preparation.

After downloading the dataset, the directory should look like this:

├── ref_dataset/data
│   │
│   ├── train2014
│   │   ├── COCO_train2014_000000193977.jpg
│   │   ├── COCO_train2014_000000387678.jpg
│   │   └── ...
│   │
│   ├── refcoco
│   │   ├── instances.json
│   │   ├── refs(google).p
│   │   └── refs(unc).p
│   │
│   ├── refcoco+
│   │   └── ...
│   │
│   ├── refcocog
│       └── ...