This is the official code repository for A Simple Long-Tailed Rocognition Baseline via Vision-Language Model.

• Python3
• Pytorch(1.7.1 recommended)
• yaml
• other necessary packages

• ImageNet_LT
• Places_LT

Download the ImageNet_2014 and Places_365.

Modify the data_root in main.py to refer to your own dataset path.

python main.py --cfg ./config/ImageNet_LT/clip_A_rn50.yaml

python main.py --cfg ./config/ImageNet_LT/clip_B_rn50.yaml

python main.py --cfg ./config/ImageNet_LT/test.yaml --test

The codes is based on https://github.com/zhmiao/OpenLongTailRecognition-OLTR and motivated by https://github.com/facebookresearch/classifier-balancing.