Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ej0cl6/deep-active-learning
Deep Active Learning
https://github.com/ej0cl6/deep-active-learning
active-learning deep-active-learning
Last synced: 3 months ago
JSON representation
Deep Active Learning
- Host: GitHub
- URL: https://github.com/ej0cl6/deep-active-learning
- Owner: ej0cl6
- License: mit
- Created: 2018-05-03T05:51:17.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2022-10-03T20:23:38.000Z (about 2 years ago)
- Last Synced: 2024-04-17T00:19:08.525Z (7 months ago)
- Topics: active-learning, deep-active-learning
- Language: Python
- Homepage:
- Size: 40 KB
- Stars: 760
- Watchers: 16
- Forks: 179
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-machine-learning-resources - **[Code Collection - active-learning?style=social) (Table of Contents)
- awesome-active-learning - DeepAL - learn, pytorch) | Kuan-Hao Huang | Keep updating & deep neural networks | (3.3 AL in AI Fields - 人工智能背景中的主动学习 / **Tutorials - 教程**)
README
# DeepAL: Deep Active Learning in Python
Python implementations of the following active learning algorithms:
- Random Sampling
- Least Confidence [1]
- Margin Sampling [2]
- Entropy Sampling [3]
- Uncertainty Sampling with Dropout Estimation [4]
- Bayesian Active Learning Disagreement [4]
- Cluster-Based Selection [5]
- Adversarial margin [6]## Prerequisites
- numpy 1.21.2
- scipy 1.7.1
- pytorch 1.10.0
- torchvision 0.11.1
- scikit-learn 1.0.1
- tqdm 4.62.3
- ipdb 0.13.9You can also use the following command to install conda environment
```
conda env create -f environment.yml
```## Demo
```
python demo.py \
--n_round 10 \
--n_query 1000 \
--n_init_labeled 10000 \
--dataset_name MNIST \
--strategy_name RandomSampling \
--seed 1
```Please refer [here](https://arxiv.org/abs/2111.15258) for more details.
## Citing
If you use our code in your research or applications, please consider citing our paper.
```
@article{Huang2021deepal,
author = {Kuan-Hao Huang},
title = {DeepAL: Deep Active Learning in Python},
journal = {arXiv preprint arXiv:2111.15258},
year = {2021},
}
```## Reference
[1] A Sequential Algorithm for Training Text Classifiers, SIGIR, 1994
[2] Active Hidden Markov Models for Information Extraction, IDA, 2001
[3] Active learning literature survey. University of Wisconsin-Madison Department of Computer Sciences, 2009
[4] Deep Bayesian Active Learning with Image Data, ICML, 2017
[5] Active Learning for Convolutional Neural Networks: A Core-Set Approach, ICLR, 2018
[6] Adversarial Active Learning for Deep Networks: a Margin Based Approach, arXiv, 2018