Adaptive Regularized Warped Gradient Descent Enhances Model Generalization and Meta-learning for Few-shot learning
This repository provides the code for our paper "Adaptive Regularized Warped Gradient Descent Enhances Model Generalization and Meta-learning for Few-shot learning" submitted to Neurocomputing.
The main structure of this code is based on [WarpGrad] (https://github.com/flennerhag/warpgrad). We sincerely thank the authors for sharing the codes for their great works.
- Python >= 3.7
- Pytorch >= 1.7.0 and torchvision (https://pytorch.org/)
- Gpu Memory >= 11 GB
Refers to WarpGard (https://openreview.net/forum?id=rkeiQlBFPB).
cd src/omniglot
python main.py
The settings of hyperparameters can be changed in options.py.
Please cite our paper if you find the code or dataset useful for your research.
This library is licensed under the Apache 2.0 License.