A modular toolbox for accelerating meta-learning research

栏目: IT技术 · 发布时间: 4年前

内容简介:WARNING:Repository is under construction. Feel free to star and subscribe for updates, but the code will be unstable and might be changing under the hood until the first beta.| Coverage Badge

A modular toolbox for accelerating meta-learning research

A Modular Toolbox for Accelerating Meta-Learning Research :rocket:

WARNING:Repository is under construction. Feel free to star and subscribe for updates, but the code will be unstable and might be changing under the hood until the first beta.

| Coverage Badge

Meta-Blocksis a modular toolbox for research, experimentation, and reproducible benchmarking of learning-to-learn algorithms. The toolbox provides flexible APIs for working with MetaDatasets , TaskDistributions , and MetaLearners (see the figure below). The APIs make it easy to implement a variety of meta-learning algorithms, run them on well-established and emerging benchmarks, and add your own meta-learning problems to the suite and benchmark algorithms on them.

A modular toolbox for accelerating meta-learning research

Meta-Blockspackage comes with:

  • Flexible APIs, detailed documentation, and multiple examples.
  • Popular models and algorithms such as MAML [1], Reptile [2], Protonets [3].
  • Supervised and unsupervised meta-learning setups compatible with all algorithms.
  • Customizable modules and utility functions for quick prototyping on new meta-learning algorithms.

Links and Resources:

Installation

It is recommended to use pip for installation. Please make sure the latest version is installed, as meta-blocks is updated frequently:

$ pip install meta-blocks            # normal install
$ pip install --upgrade meta-blocks  # or update if needed
$ pip install --pre meta-blocks      # or include pre-release version for new features

Alternatively, you could clone and run setup.py file:

$ git clone https://github.com/alshedivat/meta-blocks.git
$ cd meta-blocks
$ pip install .

Required Dependencies :

  • albumentations
  • hydra-core
  • numpy
  • Pillow
  • scipy
  • scikit-learn
  • tensorflow>=2.1

Examples

TODO: We should provide a minimal example so people could run immediately. Ideally, the running time should be within a few mins.

Development

For development and contributions, please make sure to install pre-commit hooks to ensure proper code style and formatting:

$ pip install pre-commit      # install pre-commit
$ pre-commit install          # install git hooks $ pre-commit run --all-files  # run pre-commit on all the files ``` 
#### Status

**Meta-Blocks** is currently **under development** as of Apr, 2020.

**Watch & Star** to get the latest update! Also feel free to contact for suggestions and ideas.

----

### Citing Meta-Blocks

TODO: add citation information as soon as available.

----


### Reference

[1] Finn, C., Abbeel, P. and Levine, S. Model-agnostic meta-learning for fast adaptation of deep networks. ICML 2017.

[2] Nichol, A., Achiam, J. and Schulman, J. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999.

[3] Snell, J., Swersky, K. and Zemel, R. Prototypical networks for few-shot learning. NeurIPS 2017.

以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网

查看所有标签

猜你喜欢:

本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们

小群效应

小群效应

徐志斌 / 中信出版集团 / 2017-11 / 58.00元

互联网经济时代,新零售、网红经济、知识经济多受益于社群。用户的获取、留存及订单转化直接决定了一个社群的存亡。无论是“做”群还是“用”群,每个人都需要迭代常识:了解用户行为习惯,了解社群运行规律。 《社交红利》《即时引爆》作者徐志斌历时两年,挖掘腾讯、百度、豆瓣的一手后台数据,从上百个产品中深度解读社群行为,通过大量生动案例总结出利用社交网络和海量用户进行沟通的方法论。 本书将告诉你: ......一起来看看 《小群效应》 这本书的介绍吧!

图片转BASE64编码
图片转BASE64编码

在线图片转Base64编码工具

HTML 编码/解码
HTML 编码/解码

HTML 编码/解码

XML 在线格式化
XML 在线格式化

在线 XML 格式化压缩工具