Image category frequency for the case of LVIS dataset

tztztztztz / eql.detectron2

The official implementation of Equalization Loss for Long-Tailed Object Recognition (CVPR 2020) based on Detectron2. https://arxiv.org/abs/2003.05176

Apache License 2.0

202 stars 17 forks source link

Image category frequency for the case of LVIS dataset #7

Closed aniket-agarwal1999 closed 4 years ago

aniket-agarwal1999 commented 4 years ago

Hi, Can you point out how did you get the LVIS_CATEGORIES from the LVIS dataset(present in the file lvis_v0_5_categories.py). I am trying to implement this loss for long-tail relationship detection using GQA and VG dataset.