DeepAL: Deep Active Learning in Python

Kuan-Hao Huang

Last update: Jan 3, 2023

Overview

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]
Core-Set 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 0.13.9

You 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 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

Comments

Error with coreset strategy

Tried coreset strategy with various initializations: NUM_INIT_LB and NUM_QUERY. All of them produce errors as shown below. Looks like 'sols{}.pkl' is not being generated.

(pytorch_p36) [ec2-user@ip-172-31-38-51 deep-active-learning]$ python run.py /home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/externals/joblib/externals/cloudpickle/cloudpickle.py:47: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses import imp number of labeled pool: 1000 number of unlabeled pool: 39000 number of testing pool: 10000 MNIST SEED 1 CoreSet Round 0 testing accuracy 0.7458 Round 1 calculate distance matrix /home/ec2-user/src/deep-active-learning/query_strategies/core_set.py:24: RuntimeWarning: invalid value encountered in sqrt dist_mat = np.sqrt(dist_mat) 0:00:22.086067 calculate greedy solution greedy solution 0/50 greedy solution 10/50 greedy solution 20/50 greedy solution 30/50 greedy solution 40/50 0:00:13.353899

/home/ec2-user/src/deep-active-learning/query_strategies/core_set.py(64)query() 63 ---> 64 sols = pickle.load(open('sols{}.pkl'.format(SEED), 'rb')) 65

ipdb>

Exiting Debugger.

opened by kaushikpavani 4
Mapping between paper names to python class

Hey, Thanks for this awesome repository. A quick question, is there a mapping between the paper names to the python code classes? Specifically I'm interested in ''ACTIVE LEARNING FOR CONVOLUTIONAL NEURAL NETWORKS: A CORE-SET APPROACH`` which supposes to be one of these: "RandomSampling", "LeastConfidence", "MarginSampling", "EntropySampling", "LeastConfidenceDropout", "MarginSamplingDropout", "EntropySamplingDropout", "KMeansSampling", "KCenterGreedy", "BALDDropout", "AdversarialBIM", "AdversarialDeepFool",

opened by kobybibas 2
Confusion about network constructor
It seems that each time I call the function Net.train(self, data), a new network with new initial parameters will be constructed.（As the code shown in https://github.com/ej0cl6/deep-active-learning/blob/563723356421bc7d82e3496700265992cf7fcb06/nets.py#L17） As I know, the network's parameters are trained continuously after each query in Active Learning settings, instead of constructing a new network and training from scratch. So the constructor of class Net maybe like:

class Net: def __init__(self, net, params, device): self.net = net self.params = params self.device = device self.clf = self.net().to(self.device) # add def train(self, data): n_epoch = self.params['n_epoch'] # self.clf = self.net().to(self.device) # remove self.clf.train() optimizer = optim.SGD(self.clf.parameters(), **self.params['optimizer_args'])

I'm a beginner in Deep Active Learning, so the content above maybe just my misunderstanding about Deep Active Learning. Looking forward to your reply. Thank you.
opened by UnpureRationalist 2
TypeError: missing arguments with ALBL strategy

There is a bug in deep-active-learning/query_strategies/active_learning_by_learning.py line 9.

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, args))

I got the error: TypeError: init() missing 2 required positional arguments: 'handler' and 'args'

The fix should be:

self.strategy_list.append(RandomSampling(X, Y, idxs_lb, net, handler, args))

opened by kaushikpavani 2
Is there a mistake in Deepfool implementation?

I believe there is a mistake in this line in adversarial_deepfool.py if value_i < value_l: ri = value_i/np.linalg.norm(wi.numpy().flatten()) * wi value_l = value_i # <--- this line should be added here since otherwise,t value_i is just always the last value in the for loop?

opened by saifullah3396 1
How can I add my own data set for active learning?

Hello, thank you for implementing a code base that integrates multiple active learning methods! It's a great job! I was wondering how can I add my own data sets and use this code to do active learning?

opened by Djn-swjtu 1
Can this pipeline be applied to any deep learning model?
Hey there,

I'm looking to explore deep learning with active learning semi automated labels for a video classification project i have. I currently use a Bidirectional LSTM and may look to explore transformers, gradient boosted decision trees and SVMs as well. For LSTMs and transformers, is it possible for me to use my LSTM model with the current framework?

Tony
opened by Tony363 1
TensorFlow Support

HI there, thanks for your great job. I'm wondering if you know any TensorFlow Supporting implementation or do you have any plan to implement it as well?

Thanks.

opened by hadisaadat 1
Custom dataset for image classification

Firstly I would like to thank you for the library Is there a way to use this framework on custom image datasets for image classification with active learning?

opened by JosianeUwineza 1
CoreSet AL algorithm

Hi, thanks for your excellent codes. I have a question regarding to the CoreSet AL algorithm. In your previews version, there is this algorithm but now it is gone. May I know the reason? Thanks a lot in advance!!

opened by luuyin 1
Gurobi License

Thanks for your incredible lines of code. There are no problems until I run model.optimize() in file full_solver_gurobi.py, it raises error: 'GurobiError: Model too large for size-limited license; visit https://www.gurobi.com/free-trial for a full license'. Gurobi seem not to be free with large size models (because I ran 35000 vectors size of 512) I just want to quickly reproduce the reported results of the paper but not any commercial purposes. Is there any other way to reproduce the results of Core-Set [3] paper or to get the free Gurobi license?

opened by vietth-bka 1

Owner

Kuan-Hao Huang

GitHub

Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

Active Learning with the Nvidia TLT Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT). In this tutorial, we will show you ho

25 Dec 3, 2022

A modular active learning framework for Python

Modular Active Learning framework for Python3 Page contents Introduction Active learning from bird's-eye view modAL in action From zero to one in a fe

1.9k Dec 31, 2022

An Active Automata Learning Library Written in Python

AALpy An Active Automata Learning Library AALpy is a light-weight active automata learning library written in pure Python. You can start learning auto

TU Graz - SAL Dependable Embedded Systems Lab (DES Lab)

78 Dec 30, 2022

Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection, CVPR 2021. Installation A Linux pla

269 Dec 21, 2022

Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

MI-AOD Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection (The PDF is not available tem

269 Dec 21, 2022

gym-anm is a framework for designing reinforcement learning (RL) environments that model Active Network Management (ANM) tasks in electricity distribution networks.

gym-anm is a framework for designing reinforcement learning (RL) environments that model Active Network Management (ANM) tasks in electricity distribution networks. It is built on top of the OpenAI Gym toolkit.

99 Dec 12, 2022

PyTorch implementation of "A Simple Baseline for Low-Budget Active Learning".

A Simple Baseline for Low-Budget Active Learning This repository is the implementation of A Simple Baseline for Low-Budget Active Learning. In this pa

10 Nov 14, 2022

Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks (MAPDN)

Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks (MAPDN) This is the implementation of the paper Multi-Age

83 Jan 6, 2023

Code for Active Learning at The ImageNet Scale.

Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training with torch's DDP.

47 Dec 12, 2022

The pyrelational package offers a flexible workflow to enable active learning with as little change to the models and datasets as possible

pyrelational is a python active learning library developed by Relation Therapeutics for rapidly implementing active learning pipelines from data management, model development (and Bayesian approximation), to creating novel active learning strategies.