ALiPy provides a module based implementation of active learning framework, which allows users to conveniently evaluate, compare and analyze the performance of active learning methods. It implementations more than 20 algorithms and also supports users to easily implement their own approaches under different settings.
Get startedTang, Y.-P.; Li, G.-X.; and Huang, S.-J. ALiPy: Active learning in python. https://arxiv.org/abs/1901.03802 . 2019.
There is no limitation to the classification model. One can use SVM in sklearn or deep model in tensorflow as you need.
One can freely modify one or more modules of the toolbox without affection to the others.
There are few limitations of the user-defined functions, such as the parameters or names.
Noisy oracles, Multi-label, Cost effective, Feature querying, etc.
Intermediate results saving & loading; multi-threading; experiement result analysing, etc.
You can get alipy simply by:
pip install alipy
For detailed installation instruction, please refer to installation guide .
ALiPy provides several optional usages for different users.
For the users who are less familiar with active learning and want to simply apply a method to a dataset , Please refer to AlExperiment to run the active learning process in a few lines of codes without knowing about any background knowledge.
For the users who want to experimentally evaluate the performance of existing active learning methods , We recommend you to the ALiPy overview to learn the usage of more than 20 state-of-the-art algorithms in 7 different settings.
For the users who want to implement their own idea and perform active learning experiments , We recommend you to the 10 minutes to alipy to learn how to easily perform active learning experiment with ALiPy.
ALiPy provide several commonly used strategies in different active learning settings for now, and new algorithms will be added in subsequent updates.
Copyright © 2018, alipy developers (BSD 3 License).