[NeurIPS2024] SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
- PyTorch >= version 1.4
- tqdm == 4.65.0
- timm == 0.6.5
We follow RanPAC setting to use the same data index_list for training.
$ python main.py -d cifar224
- for -d choose from 'cifar224', 'imageneta'
Our project references the codes in the following repos.