Python unsupervised-learning

Open-source Python projects categorized as unsupervised-learning | Edit details

Top 23 Python unsupervised-learning Projects

  • anomaly-detection-resources

    Anomaly detection related books, papers, videos, and toolboxes

    Project mention: anomaly-detection-resources: NEW Extended Research - star count:5415.0 | | 2022-01-21
  • pyod

    (JMLR' 19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

    Project mention: [D] Unsupervised Outlier Detection - Advise Requested | | 2021-12-03

    The source code and documentaion of PyOD is the best survey about OOD. Besides, the normalized flow and VQVAE are also feasible.

  • SonarQube

    Static code analysis for 29 languages.. Your projects are multi-language. So is SonarQube analysis. Find Bugs, Vulnerabilities, Security Hotspots, and Code Smells so you can release quality code every time. Get started analyzing your projects today for free.

  • cleanlab

    The standard package for machine learning with label errors, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.

    Project mention: Has anyone used unsupervised anomaly detection to improve data quality? | | 2021-12-18
  • mmselfsup

    OpenMMLab Self-Supervised Learning Toolbox and Benchmark

    Project mention: Rebirth! OpenSelfSup is upgraded to MMSelfSup | | 2021-12-16
  • karateclub

    Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

  • HyperGAN

    Composable GAN framework with api and user interface

    Project mention: Machine learning software that generates images? | | 2021-11-15

    And then there's software already prebaked that can do it, but its really taxing on a pc, its called hyperGAN.

  • alibi-detect

    Algorithms for outlier, adversarial and drift detection

    Project mention: Ask HN: Who is hiring? (January 2022) | | 2022-01-03

    Seldon | Multiple positions | London/Cambridge UK | Onsite/Remote | Full time |

    At Seldon we are building industry leading solutions for deploying, monitoring, and explaining machine learning models. We are an open-core company with several successful open source projects like:






    We are hiring for a range of positions, including software engineers(go, k8s), ml engineers (python, go), frontend engineers (js), UX designer, and product managers. All open positions can be found at

  • Scout APM

    Less time debugging, more time building. Scout APM allows you to find and fix performance issues with no hassle. Now with error monitoring and external services monitoring, Scout is a developer's best friend when it comes to application development.

  • minisom

    :red_circle: MiniSom is a minimalistic implementation of the Self Organizing Maps

    Project mention: [P][D] Self Organizing Maps | | 2021-07-15
  • Unsupervised-Classification

    SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]

    Project mention: Any reference or idea about how to train unsupervised CNN model ? | | 2021-04-13
  • athena

    an open-source implementation of sequence-to-sequence based speech processing engine (by athena-team)

  • autovc

    AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

    Project mention: Use deep fake tech to say stuff with your favorite characters | | 2021-12-25
  • corex_topic

    Hierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx

    Project mention: Are topic models reliable or useful? | | 2021-09-27

    We started off by trying LDA and NMF, but the topics were too messy so we wound up switching to CorEx (, which is a semi-supervised algo that lets you "nudge" the model in the right direction using anchor terms. By the time our topics started looking coherent, it turned out that a regex with the anchor terms we'd picked outperformed the model itself. This case study was on a relatively small sample of relatively short documents (~4k survey open-ends) but for what it's worth, we also tried to use topic models to classify congressional Facebook posts (much larger corpus and longer documents) and the results were the same.

    Overfitting is certainly part of the problem - in one of my earlier posts I talk about "conceptually spurious words," which are essentially the product of overfitting - but the more difficult problem is polysemy. I'm sure there are ways to mitigate that - expanding the feature space with POS tagging, etc. - but ultimately I think the solution is to simply avoid using a dimensionality reduction method for text classification. Supervised models are clearly the way to go - even if those "models" are just keyword dictionaries curated based on domain knowledge.

  • Lifting-from-the-Deep-release

    Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"

    Project mention: How do I install deeplearning package from github and apply transfer learning on it? | | 2021-07-17

    You should try reading the source code of the bash script and the other source files to get a sense of what they do and how you can incorporate it into your project. Here's some tips to get started (assuming you're looking at this repo:

  • Unsupervised-Semantic-Segmentation

    Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021]

    Project mention: Unsupervised semantic segmentation | | 2021-09-09

    Check out these unsupervised masks created in exactly such way in this paper. They are nearly perfect

  • DETReg

    Official implementation of the paper "DETReg: Unsupervised Pretraining with Region Priors for Object Detection".

    Project mention: Researchers From Tel Aviv University, UC Berkeley and NVIDIA Introduce ‘DETReg’, A Novel Unsupervised AI For Object Detection | | 2021-08-01


  • ContraD

    Code for the paper "Training GANs with Stronger Augmentations via Contrastive Discriminator" (ICLR 2021)

    Project mention: [D] What is the smallest dataset you styleGAN2 trained? | | 2021-06-04

    Well, I've been trying to train a 1024 GAN from scratch on stylegan2-ada-pytorch with a small dataset 300 samples of not so diversity in images of painting faces. Fact is that on first try FID went as low as 71 and started deteriorating. Now I x-flip augmented the dataset (700 images) and at 900kimg FID went 64 but I doubt it will get lower. I lowered the learning rate to 0.0001 as they say it might help... Recently found this way of dataset augmentation... probably will use this

  • unsupervised-depth-completion-visual-inertial-odometry

    Tensorflow implementation of Unsupervised Depth Completion from Visual Inertial Odometry (in RA-L January 2020 & ICRA 2020)

    Project mention: Unsupervised Depth Completion from Visual Inertial Odometry | | 2021-08-30

    Hey there, interested in camera and range sensor fusion for point cloud (depth) completion?

    Here is an extended version of our [talk]( at ICRA 2020 where we do a step by step walkthrough of our paper Unsupervised Depth Completion from Visual Inertial Odometry (joint work with Fei Xiaohan, Stephanie Tsuei, and Stefano Soatto).

    In this talk, we present an unsupervised method (no need for human supervision/annotations) for learning to recover dense point clouds from images, captured by cameras, and sparse point clouds, produced by lidar or tracked by visual inertial odometry (VIO) systems. To illustrate what I mean, here is an [example]( of the point clouds produced by our method.

    Our method is light-weight (so you can run it on your computer!) and is built on top of [XIVO] ( our VIO system.

    For those interested here are links to the [paper](, [code]( and the [dataset]( we collected.

  • pyRDF2Vec

    🐍 Python Implementation and Extension of RDF2Vec

    Project mention: [P] pyRDF2Vec 0.2.0 is out! | | 2021-03-22

    This release is packed with many new features and optimizations under the hood. An entire overview of what's new can be found in our CHANGELOG ( An overview of some major updates:

  • Insta-DM

    Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)

    Project mention: Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency | | 2021-02-09

    The official PyTorch code is available here:

  • student-teacher-anomaly-detection

    Student–Teacher Anomaly Detection with Discriminative Latent Embeddings

    Project mention: [R] Introduction to Fast Dense Feature Extraction -- A fast way to extract visual features for many patches from an image | | 2021-07-31

    Code for found:

  • Revisiting-Contrastive-SSL

    Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]

    Project mention: [R] Contrastive Visual Representation Learning Is More Robust Than You Might Think (Paper + Analysis) | | 2021-06-17
  • acoustic-keylogger

    Pipeline of a keylogging attack using just an audio signal and unsupervised learning.

  • susi

    SuSi: Python package for unsupervised, supervised and semi-supervised self-organizing maps (SOM)

    Project mention: [P][D] Self Organizing Maps | | 2021-07-15


NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020). The latest post mention was on 2022-01-21.

Python unsupervised-learning related posts


What are some of the best open-source unsupervised-learning projects in Python? This list will help you:

Project Stars
1 anomaly-detection-resources 5,425
2 pyod 5,181
3 cleanlab 2,604
4 mmselfsup 1,782
5 karateclub 1,494
6 HyperGAN 1,157
7 alibi-detect 1,097
8 minisom 991
9 Unsupervised-Classification 900
10 athena 728
11 autovc 648
12 corex_topic 520
13 Lifting-from-the-Deep-release 437
14 Unsupervised-Semantic-Segmentation 235
15 DETReg 178
16 ContraD 155
17 unsupervised-depth-completion-visual-inertial-odometry 139
18 pyRDF2Vec 138
19 Insta-DM 132
20 student-teacher-anomaly-detection 91
21 Revisiting-Contrastive-SSL 69
22 acoustic-keylogger 68
23 susi 63
Find remote jobs at our new job board There are 29 new remote jobs listed recently.
Are you hiring? Post a new remote job listing for free.
OPS - Build and Run Open Source Unikernels
Quickly and easily build and deploy open source unikernels in tens of seconds. Deploy in any language to any cloud.