xdeng77/relabeled_coco_val

Dataset

4

stars

9

commits

1

linked in READMEs

Apr 29, 2024

updated

Browse cluster: Visual Referential Understanding & COCO Datasets

README

How to download

  1. Set up environment
pip install datasets tqdm
wget https://raw.githubusercontent.com/bytedance/coconut_cvpr2024/main/download_coconut.py
  1. Use the download script to download the COCONut dataset splits.
python download_coconut.py # default split: relabeled_coco_val

The above command should print your download status, if you download it successfully you can see the results below:

image/png

  1. Download other COCONut dataset splits.

If you want to download the other splits, you can replace the split name to "coconut_s" or "coconut_b" NOTE: multiple splits download is not yet supported.

python download_coconut.py --split coconut_s --output_dir coconut_s
  1. The mask images are nearly black as we use continuous segment ids for each image, you can use our github visualization tutorial to create colorful masks for viewing.

Please go to our offical github repo for detailed usage instruction: https://github.com/bytedance/coconut_cvpr2024

Contributors

xdeng77

9 commits

xdeng77/relabeled_coco_val

Dataset

4

stars

9

commits

1

linked in READMEs

Apr 29, 2024

updated

Browse cluster: Visual Referential Understanding & COCO Datasets

README

How to download

  1. Set up environment
pip install datasets tqdm
wget https://raw.githubusercontent.com/bytedance/coconut_cvpr2024/main/download_coconut.py
  1. Use the download script to download the COCONut dataset splits.
python download_coconut.py # default split: relabeled_coco_val

The above command should print your download status, if you download it successfully you can see the results below:

image/png

  1. Download other COCONut dataset splits.

If you want to download the other splits, you can replace the split name to "coconut_s" or "coconut_b" NOTE: multiple splits download is not yet supported.

python download_coconut.py --split coconut_s --output_dir coconut_s
  1. The mask images are nearly black as we use continuous segment ids for each image, you can use our github visualization tutorial to create colorful masks for viewing.

Please go to our offical github repo for detailed usage instruction: https://github.com/bytedance/coconut_cvpr2024

Contributors

xdeng77

9 commits