资源分类
》 资源 》算法》MAML-Pytorch-Multi-GPUs

MAML-Pytorch-Multi-GPUs

2020-02-25 | |  39 |   0 |   0

MAML-Pytorch-Multi-GPUs

It is a reproduced version of maml, which is implemented with PyTorch 1.2.0 and support Multi-GPUs both in Meta-training phase and Meta-testing phase.

All the hyper-parameters and tricks, e.g. gradient clip, are strictly consistent with the original paper Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks HERE and its Tensorflow Implementation HERE.

Platform

  • python: 3.7

  • Pytorch: 1.2.0

Howto

  1. Downloading MiniImagenet dataset

  2. Changing the Param.root in train_mini_adam.py with your own root of the MiniImagenet dataset

  3. python train_mini_adam.py

Comparison to original MAML implementation for miniImageNet


5-way 1-shot5-way 5-shot
MAML48.7%63.1%
Ours48.9%#TODO#

图片.png

reference

https://github.com/cbfinn/maml

https://github.com/dragen1860/MAML-Pytorch

https://github.com/jik0730/MAML-in-pytorch

https://arxiv.org/abs/1703.03400


上一篇：mnist_maml

下一篇：Maml_Reptile_PyTorch

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • 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 ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

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