deep-active-learning:深度主动学习

  • I7_734290
    了解作者
  • 16KB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • VIP专享
    资源类型
  • 0
    下载次数
  • 2022-05-26 03:57
    上传日期
深度主动学习 以下主动学习算法的Python实现: 随机抽样 最不信任[1] 保证金抽样[1] 熵采样[1] 具有辍学估计的不确定性采样[2] 贝叶斯主动学习分歧[2] K均值采样[3] K中心贪婪[3] 核心套装[3] 对抗-基本的迭代方法 对抗性-DeepFool [4] 先决条件 numpy的1.14.3 scipy 1.1.0 火炬0.4.0 火炬视觉0.2.1 scikit学习0.19.1 ipdb 0.11 用法 $ python run.py 参考 [1]一种新的深度学习主动标记方法,IJCNN,2014年 [2]使用图像数据进行深度贝叶斯主动学习,ICML,2017年 [3]卷积神经网络的主动学习:核心集方法,ICLR,2018年 [4]深度网络的对抗式主动学习:基于边际的方法,arXiv,2018年
deep-active-learning-master.zip
  • deep-active-learning-master
  • model.py
    2.4KB
  • run.py
    4.8KB
  • dataset.py
    3.2KB
  • README.md
    928B
  • .gitignore
    6B
  • query_strategies
  • margin_sampling.py
    505B
  • random_sampling.py
    294B
  • entropy_sampling.py
    486B
  • entropy_sampling_dropout.py
    555B
  • strategy.py
    4.4KB
  • bayesian_active_learning_disagreement_dropout.py
    618B
  • adversarial_bim.py
    1.2KB
  • kmeans_sampling.py
    837B
  • least_confidence.py
    433B
  • __init__.py
    711B
  • kcenter_greedy.py
    1.1KB
  • margin_sampling_dropout.py
    587B
  • active_learning_by_learning.py
    1.7KB
  • least_confidence_dropout.py
    515B
  • adversarial_deepfool.py
    2KB
  • core_set.py
    2KB
  • core_set_solve.py
    3.9KB
内容介绍
## Deep Active Learning Python implementations of the following active learning algorithms: - Random Sampling - Least Confidence [1] - Margin Sampling [1] - Entropy Sampling [1] - Uncertainty Sampling with Dropout Estimation [2] - Bayesian Active Learning Disagreement [2] - K-Means Sampling [3] - K-Centers Greedy [3] - Core-Set [3] - Adversarial - Basic Iterative Method - Adversarial - DeepFool [4] ### Prerequisites - numpy 1.14.3 - scipy 1.1.0 - pytorch 0.4.0 - torchvision 0.2.1 - scikit-learn 0.19.1 - ipdb 0.11 ### Usage $ python run.py ### Reference [1] A New Active Labeling Method for Deep Learning, IJCNN, 2014 [2] Deep Bayesian Active Learning with Image Data, ICML, 2017 [3] Active Learning for Convolutional Neural Networks: A Core-Set Approach, ICLR, 2018 [4] Adversarial Active Learning for Deep Networks: a Margin Based Approach, arXiv, 2018
评论
    相关推荐