Keras - MAML

Part 1. Introduction

This is an experimental code base

The biggest difference between MAML and pre-training weights：Pre-training weights minimize only for original task loss. MAML can minimize all task loss with a few steps of training.

Part 2. Quick Start

1. Pull repository.

git clone https://github.com/verages/MAML.git

2. You need to install some dependency package.

cd MAML
pip installl -r requirements.txt

3. Download the Omiglot dataset and maml weights.

wget https://github.com/verages/MAML/releases/download/v0.1/Omniglot.tar
wget https://github.com/verages/MAML/releases/download/v0.1/maml.h5
tar -xvf Omniglot.tar

4. Run evaluate.py, you'll see the difference between MAML and random initialization weights.

python evaluate.py

Part 3. Train your own dataset

1. You should set same parameters in config.py.

n_way = "number of classes"
k_shot = "number of support set"
q_query = "number of query set"

2. Start training.

python train.py

3. Running tensorboard to monitor the training process.

tensorboard --logdir=./summary

Part 4. Paper and other implement

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• cbfinn/maml
• dragen1860/MAML-Pytorch