MAML is a model-agnostic optimization-based meta learning algorithm. It meta-trains a model to learn a parameter initialization such that it can be fine-tuned to a different task in a single gradient update.

This repository implements second-order MAML on the omniglot dataset

• PyTorch
• OpenCV
• Numpy
• Tqdm

1. Download the Omniglot Dataset's images_background.zip and images_evaluation.zip splits here.
2. Unzip the files in omniglot/ directory.
3. Run the train.py script to start the training with default options. Run python train.py -h to get a description of the arguments.
4. For evaluation, run evaluate.py script.
5. To make predictions on new data, refer Test.ipynb.
6. Alternatively,

• https://github.com/oscarknagg/few-shot
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks https://arxiv.org/abs/1703.03400