A Simple Long-Tailed Rocognition Baseline via Vision-Language Model
This is the official code repository for A Simple Long-Tailed Rocognition Baseline via Vision-Language Model.
Requirements
- Python3
- Pytorch(1.7.1 recommended)
- yaml
- other necessary packages
Datasets
- 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.
Training
Phase A
python main.py --cfg ./config/ImageNet_LT/clip_A_rn50.yaml
Phase B
python main.py --cfg ./config/ImageNet_LT/clip_B_rn50.yaml