sshkhr / imaml

Reproduction of the IMAML paper

implicit MAML

Meta-Learning with Implicit Gradients [report]

Code for ENGG 6500: Introduction to Machine Learning Project. For this project I reimplemented the NeurIPS 2019 paper Meta-Learning with Implicit Gradients and verified the results on the Omniglot few-shot image recognition dataset.

• Project web page: https://sites.google.com/view/imaml
• Original author's code: https://github.com/aravindr93/imaml_dev

Requirements

• PyTorch 1.4.0
• CUDA 10.1
• cuDNN 7.6

License

The code is realeased under MIT License