资源分类
》 资源 》算法》MAML_simple

MAML_simple

2020-02-25 | |  33 |   0 |   0

MAML_simple

DESCRIPTION

It is a vanilla python based example following idea of Finn et al Model-Agnostic Meta Learning. In this task, the MAML algorithm is implemented on MNIST dataset. And it aims to achieve better performance on binary classification of two particular digits with knowledge of other digits.

Notice: meta update is achieved by first-order approximation, which essentially reflects gradient according to paper.

REQUIREMENT

python 3

jupyter notebook

USAGE

  1. Unzip all files in "/data" folder

  2. Run python file "src/runner.py" or notebook "src/runner.ipynb"


上一篇：Few-Shot-MAML

下一篇：maml-cifar-fs

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...