DeepAL: Deep Active Learning in Python

Abstract

We present DeepAL, a Python library that implements several common strategies for active learning, with a particular emphasis on deep active learning. DeepAL provides a simple and unified framework based on PyTorch that allows users to easily load custom datasets, build custom data handlers, and design custom strategies without much modification of codes. DeepAL is open-source on Github and welcome any contribution.

project url: https://github.com/ej0cl6/deep-active-learning

References in corpus (1)

• libact: Pool-based Active Learning in Python

Cited by in corpus (3)

• Disambiguation of Company names via Deep Recurrent Networks
• Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
• ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP