Best-of Machine Learning with Python
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
This curated list contains 920 awesome open-source projects with a total of 4.3M stars grouped into 34 categories. All projects are ranked by a project-quality score, which is calculated based on various metrics automatically collected from GitHub and different package managers. If you like to add or update projects, feel free to open an issue, submit a pull request, or directly edit the projects.yaml. Contributions are very welcome!
🧙♂️ Discover other best-of lists or create your own.
📫 Subscribe to our newsletter for updates and trending projects.
Contents
- Machine Learning Frameworks 61 projects
- Data Visualization 54 projects
- Text Data & NLP 102 projects
- Image Data 64 projects
- Graph Data 36 projects
- Audio Data 29 projects
- Geospatial Data 22 projects
- Financial Data 25 projects
- Time Series Data 30 projects
- Medical Data 19 projects
- Tabular Data 5 projects
- Optical Character Recognition 12 projects
- Data Containers & Structures 1 projects
- Data Loading & Extraction 1 projects
- Web Scraping & Crawling 1 projects
- Data Pipelines & Streaming 1 projects
- Distributed Machine Learning 36 projects
- Hyperparameter Optimization & AutoML 52 projects
- Reinforcement Learning 23 projects
- Recommender Systems 17 projects
- Privacy Machine Learning 7 projects
- Workflow & Experiment Tracking 40 projects
- Model Serialization & Deployment 20 projects
- Model Interpretability 53 projects
- Vector Similarity Search (ANN) 13 projects
- Probabilistics & Statistics 23 projects
- Adversarial Robustness 9 projects
- GPU & Accelerator Utilities 20 projects
- Tensorflow Utilities 16 projects
- Jax Utilities 3 projects
- Sklearn Utilities 19 projects
- Pytorch Utilities 32 projects
- Database Clients 1 projects
- Others 66 projects
Explanation
- 🥇🥈🥉 Combined project-quality score
- ⭐️ Star count from GitHub
- 🐣 New project (less than 6 months old)
- 💤 Inactive project (6 months no activity)
- 💀 Dead project (12 months no activity)
- 📈📉 Project is trending up or down
- ➕ Project was recently added
- ❗️ Warning (e.g. missing/risky license)
- 👨💻 Contributors count from GitHub
- 🔀 Fork count from GitHub
- 📋 Issue count from GitHub
- ⏱️ Last update timestamp on package manager
- 📥 Download count from package manager
- 📦 Number of dependent projects
Tensorflow related project
Sklearn related project
PyTorch related project
MxNet related project
Apache Spark related project
Jupyter related project
PaddlePaddle related project
Pandas related project
Jax related project
Machine Learning Frameworks
General-purpose machine learning and deep learning frameworks.
Tensorflow (🥇54 · ⭐ 180K) - An Open Source Machine Learning Framework for Everyone. Apache-2
-
GitHub (👨💻 4.5K · 🔀 72K · 📦 330K · 📋 39K - 4% open · ⏱️ 04.01.2024):
git clone https://github.com/tensorflow/tensorflow -
PyPi (📥 16M / month):
pip install tensorflow -
Conda (📥 4.4M · ⏱️ 22.12.2023):
conda install -c conda-forge tensorflow -
Docker Hub (📥 76M · ⭐ 2.2K · ⏱️ 04.01.2024):
docker pull tensorflow/tensorflow
scikit-learn (🥇52 · ⭐ 57K) - scikit-learn: machine learning in Python. BSD-3
pytorch-lightning (🥇45 · ⭐ 26K) - Pretrain, finetune and deploy AI models on multiple.. Apache-2
StatsModels (🥇45 · ⭐ 9.2K) - Statsmodels: statistical modeling and econometrics in Python. BSD-3
XGBoost (🥈44 · ⭐ 25K) - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or.. Apache-2
PaddlePaddle (🥈44 · ⭐ 21K) - PArallel Distributed Deep LEarning: Machine Learning.. Apache-2
LightGBM (🥈43 · ⭐ 16K) - A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT,.. MIT
Catboost (🥈41 · ⭐ 7.5K) - A fast, scalable, high performance Gradient Boosting on Decision.. Apache-2
Jina (🥈40 · ⭐ 20K) - Build multimodal AI applications with cloud-native stack. Apache-2
-
GitHub (👨💻 180 · 🔀 2.2K · 📦 1.4K · 📋 1.9K - 0% open · ⏱️ 14.12.2023):
git clone https://github.com/jina-ai/jina -
PyPi (📥 110K / month):
pip install jina -
Conda (📥 59K · ⏱️ 16.06.2023):
conda install -c conda-forge jina-core -
Docker Hub (📥 1.3M · ⭐ 8 · ⏱️ 14.12.2023):
docker pull jinaai/jina
einops (🥈35 · ⭐ 7.5K) - Flexible and powerful tensor operations for readable and reliable code.. MIT
Thinc (🥈35 · ⭐ 2.8K) - A refreshing functional take on deep learning, compatible with your favorite.. MIT
Vowpal Wabbit (🥉31 · ⭐ 8.3K) - Vowpal Wabbit is a machine learning system which pushes the.. BSD-3
tensorpack (🥉31 · ⭐ 6.3K) - A Neural Net Training Interface on TensorFlow, with focus.. Apache-2
tensorflow-upstream (🥉31 · ⭐ 670) - TensorFlow ROCm port. Apache-2
Determined (🥉29 · ⭐ 2.7K) - Determined is an open-source machine learning platform.. Apache-2
Neural Network Libraries (🥉27 · ⭐ 2.7K) - Neural Network Libraries. Apache-2
SHOGUN (🥉26 · ⭐ 3K) - Unified and efficient Machine Learning. BSD-3
-
GitHub (👨💻 250 · 🔀 1K · 📋 1.5K - 27% open · ⏱️ 19.12.2023):
git clone https://github.com/shogun-toolbox/shogun -
Conda (📥 130K · ⏱️ 16.06.2023):
conda install -c conda-forge shogun -
Docker Hub (📥 1.5K · ⭐ 1 · ⏱️ 31.01.2019):
docker pull shogun/shogun
Neural Tangents (🥉26 · ⭐ 2.2K) - Fast and Easy Infinite Neural Networks in Python. Apache-2
NeuPy (🥉24 · ⭐ 740 · 💤) - NeuPy is a Tensorflow based python library for prototyping and building.. MIT
Torchbearer (🥉24 · ⭐ 630) - torchbearer: A model fitting library for PyTorch. MIT
chefboost (🥉22 · ⭐ 430) - A Lightweight Decision Tree Framework supporting regular algorithms:.. MIT
ThunderSVM (🥉21 · ⭐ 1.5K) - ThunderSVM: A Fast SVM Library on GPUs and CPUs. Apache-2
ThunderGBM (🥉16 · ⭐ 680) - ThunderGBM: Fast GBDTs and Random Forests on GPUs. Apache-2
Show 16 hidden projects...
- dlib (🥈38 · ⭐ 13K) - A toolkit for making real world machine learning and data analysis..
❗️BSL-1.0 - Theano (🥈38 · ⭐ 9.8K · 💀) - Theano was a Python library that allows you to define, optimize, and..
BSD-3 - MindsDB (🥈33 · ⭐ 19K) - Build AI using SQL.
❗Unlicensed - Chainer (🥈33 · ⭐ 5.8K · 💀) - A flexible framework of neural networks for deep learning.
MIT - TFlearn (🥉32 · ⭐ 9.6K · 💀) - Deep learning library featuring a higher-level API for TensorFlow.
MIT - Turi Create (🥉31 · ⭐ 11K · 💀) - Turi Create simplifies the development of custom machine..
BSD-3 - mlpack (🥉31 · ⭐ 4.6K) - mlpack: a fast, header-only C++ machine learning library.
❗Unlicensed - ivy (🥉30 · ⭐ 14K) - The Unified AI Framework.
❗Unlicensed - Lasagne (🥉28 · ⭐ 3.8K · 💀) - Lightweight library to build and train neural networks in Theano.
MIT - NuPIC (🥉27 · ⭐ 6.3K) - Numenta Platform for Intelligent Computing is an implementation of..
❗️AGPL-3.0 - CNTK (🥉26 · ⭐ 17K · 💀) - Microsoft Cognitive Toolkit (CNTK), an open source deep-learning..
❗Unlicensed - xLearn (🥉25 · ⭐ 3.1K · 💀) - High performance, easy-to-use, and scalable machine learning (ML)..
Apache-2 - mace (🥉22 · ⭐ 4.8K · 💀) - MACE is a deep learning inference framework optimized for mobile..
Apache-2 - neon (🥉22 · ⭐ 3.9K · 💀) - Intel Nervana reference deep learning framework committed to best..
Apache-2 - elegy (🥉18 · ⭐ 460 · 💀) - A High Level API for Deep Learning in JAX.
MIT - StarSpace (🥉16 · ⭐ 3.9K · 💀) - Learning embeddings for classification, retrieval and ranking.
MIT
Data Visualization
General-purpose and task-specific data visualization libraries.
Matplotlib (🥇48 · ⭐ 19K) - matplotlib: plotting with Python. ❗Unlicensed
pandas-profiling (🥈37 · ⭐ 12K) - 1 Line of code data quality profiling & exploratory.. MIT
datashader (🥈33 · ⭐ 3.1K) - Quickly and accurately render even the largest data. BSD-3
mpld3 (🥈33 · ⭐ 2.3K) - D3 Renderings of Matplotlib Graphics. BSD-3
-
GitHub (👨💻 52 · 🔀 360 · 📦 5.4K · 📋 360 - 59% open · ⏱️ 23.12.2023):
git clone https://github.com/mpld3/mpld3 -
PyPi (📥 440K / month · 📦 410 · ⏱️ 23.12.2023):
pip install mpld3 -
Conda (📥 190K · ⏱️ 23.12.2023):
conda install -c conda-forge mpld3 -
npm (📥 570 / month · 📦 8 · ⏱️ 23.12.2023):
npm install mpld3
Perspective (🥈31 · ⭐ 7.1K) - A data visualization and analytics component, especially.. Apache-2
-
GitHub (👨💻 93 · 🔀 900 · 📥 1.9K · 📦 110 · 📋 700 - 11% open · ⏱️ 03.01.2024):
git clone https://github.com/finos/perspective -
PyPi (📥 3.8K / month):
pip install perspective-python -
Conda (📥 500K · ⏱️ 04.12.2023):
conda install -c conda-forge perspective -
npm (📥 160 / month):
npm install @finos/perspective-jupyterlab
D-Tale (🥈31 · ⭐ 4.4K) - Visualizer for pandas data structures. ❗️LGPL-2.1
hvPlot (🥈31 · ⭐ 860) - A high-level plotting API for pandas, dask, xarray, and networkx built on.. BSD-3
bqplot (🥉30 · ⭐ 3.5K) - Plotting library for IPython/Jupyter notebooks. Apache-2
-
GitHub (👨💻 64 · 🔀 470 · 📦 53 · 📋 620 - 40% open · ⏱️ 04.10.2023):
git clone https://github.com/bqplot/bqplot -
PyPi (📥 110K / month · 📦 100 · ⏱️ 17.10.2023):
pip install bqplot -
Conda (📥 1.2M · ⏱️ 06.11.2023):
conda install -c conda-forge bqplot -
npm (📥 2.9K / month · 📦 17 · ⏱️ 17.10.2023):
npm install bqplot
data-validation (🥉29 · ⭐ 740) - Library for exploring and validating machine learning.. Apache-2
Facets Overview (🥉28 · ⭐ 7.3K · 💤) - Visualizations for machine learning datasets. Apache-2
Sweetviz (🥉27 · ⭐ 2.7K) - Visualize and compare datasets, target values and associations, with one.. MIT
AutoViz (🥉27 · ⭐ 1.5K) - Automatically Visualize any dataset, any size with a single line of.. Apache-2
Plotly-Resampler (🥉25 · ⭐ 870) - Visualize large time series data with plotly.py. MIT
Chartify (🥉24 · ⭐ 3.4K) - Python library that makes it easy for data scientists to create.. Apache-2
Multicore-TSNE (🥉23 · ⭐ 1.8K · 💤) - Parallel t-SNE implementation with Python and Torch.. BSD-3
Pandas-Bokeh (🥉23 · ⭐ 870 · 💤) - Bokeh Plotting Backend for Pandas and GeoPandas. MIT
python-ternary (🥉23 · ⭐ 660) - Ternary plotting library for python with matplotlib. MIT
Show 16 hidden projects...
- VisPy (🥈34 · ⭐ 3.2K) - High-performance interactive 2D/3D data visualization library.
❗Unlicensed - cartopy (🥈34 · ⭐ 1.3K) - Cartopy - a cartographic python library with matplotlib support.
❗️LGPL-3.0 - PyQtGraph (🥈33 · ⭐ 3.5K) - Fast data visualization and GUI tools for scientific /..
❗Unlicensed - Cufflinks (🥉29 · ⭐ 2.9K · 💀) - Productivity Tools for Plotly + Pandas.
MIT - HyperTools (🥉25 · ⭐ 1.8K · 💀) - A Python toolbox for gaining geometric insights into high-..
MIT - PandasGUI (🥉23 · ⭐ 3.1K) - A GUI for Pandas DataFrames.
❗️MIT-0 - pythreejs (🥉23 · ⭐ 910 · 💤) - A Jupyter - Three.js bridge.
❗Unlicensed - pivottablejs (🥉21 · ⭐ 640 · 💀) - Dragndrop Pivot Tables and Charts for Jupyter/IPython..
❗Unlicensed - joypy (🥉20 · ⭐ 510 · 💀) - Joyplots in Python with matplotlib & pandas.
MIT - vegafusion (🥉20 · ⭐ 280) - Serverside scaling for Vega and Altair visualizations.
BSD-3 - PyWaffle (🥉19 · ⭐ 560 · 💀) - Make Waffle Charts in Python.
MIT - animatplot (🥉18 · ⭐ 400 · 💀) - A python package for animating plots build on matplotlib.
MIT - pdvega (🥉16 · ⭐ 340 · 💀) - Interactive plotting for Pandas using Vega-Lite.
MIT - data-describe (🥉16 · ⭐ 290 · 💀) - datadescribe: Pythonic EDA Accelerator for Data Science.
Apache-2 - nx-altair (🥉12 · ⭐ 220 · 💀) - Draw interactive NetworkX graphs with Altair.
MIT - nptsne (🥉9 · ⭐ 31 · 💀) - nptsne is a numpy compatible python binary package that offers a..
Apache-2
Text Data & NLP
Libraries for processing, cleaning, manipulating, and analyzing text data as well as libraries for NLP tasks such as language detection, fuzzy matching, classification, seq2seq learning, conversational AI, keyword extraction, and translation.
transformers (🥇50 · ⭐ 120K) - Transformers: State-of-the-art Machine Learning for.. Apache-2
nltk (🥇42 · ⭐ 13K) - Suite of libraries and programs for symbolic and statistical natural.. Apache-2
gensim (🥇40 · ⭐ 15K) - Topic Modelling for Humans. ❗️LGPL-2.1
sentence-transformers (🥇38 · ⭐ 13K) - Multilingual Sentence & Image Embeddings with BERT. Apache-2
Tokenizers (🥇37 · ⭐ 8K) - Fast State-of-the-Art Tokenizers optimized for Research and.. Apache-2
sentencepiece (🥇36 · ⭐ 8.8K) - Unsupervised text tokenizer for Neural Network-based text.. Apache-2
haystack (🥇35 · ⭐ 12K) - LLM orchestration framework to build customizable, production-ready.. Apache-2
stanza (🥈34 · ⭐ 6.9K) - Stanford NLP Python library for tokenization, sentence segmentation,.. Apache-2
TensorFlow Text (🥈34 · ⭐ 1.2K) - Making text a first-class citizen in TensorFlow. Apache-2
DeepPavlov (🥈33 · ⭐ 6.4K) - An open source library for deep learning end-to-end dialog.. Apache-2
ftfy (🥈32 · ⭐ 3.6K · 📈) - Fixes mojibake and other glitches in Unicode text, after the fact. Apache-2
jellyfish (🥈31 · ⭐ 1.9K) - a python library for doing approximate and phonetic matching of strings. MIT
spacy-transformers (🥈30 · ⭐ 1.3K) - Use pretrained transformers like BERT, XLNet and GPT-2.. MIT spacy
TextDistance (🥈29 · ⭐ 3.2K) - Compute distance between sequences. 30+ algorithms, pure python.. MIT
qdrant (🥈28 · ⭐ 15K) - Qdrant - High-performance, massive-scale Vector Database for the next.. Apache-2
-
GitHub (👨💻 78 · 🔀 850 · 📥 7.5K · 📋 860 - 14% open · ⏱️ 19.12.2023):
git clone https://github.com/qdrant/qdrant
PyTextRank (🥈27 · ⭐ 2.1K) - Python implementation of TextRank algorithms (textgraphs) for phrase.. MIT
SciSpacy (🥈27 · ⭐ 1.5K) - A full spaCy pipeline and models for scientific/biomedical documents. Apache-2
OpenPrompt (🥉26 · ⭐ 4K · 💤) - An Open-Source Framework for Prompt-Learning. Apache-2
snowballstemmer (🥉26 · ⭐ 700 · 📉) - Snowball compiler and stemming algorithms. BSD-3
Ciphey (🥉25 · ⭐ 15K) - Automatically decrypt encryptions without knowing the key or cipher, decode.. MIT
-
GitHub (👨💻 48 · 🔀 880 · 📋 320 - 17% open · ⏱️ 12.10.2023):
git clone https://github.com/Ciphey/Ciphey -
PyPi (📥 35K / month · ⏱️ 06.06.2021):
pip install ciphey -
Docker Hub (📥 22K · ⭐ 14 · ⏱️ 14.10.2023):
docker pull remnux/ciphey
pytorch-nlp (🥉24 · ⭐ 2.2K) - Basic Utilities for PyTorch Natural Language Processing (NLP). BSD-3
scattertext (🥉24 · ⭐ 2.2K) - Beautiful visualizations of how language differs among document.. Apache-2
promptsource (🥉23 · ⭐ 2.3K) - Toolkit for creating, sharing and using natural language.. Apache-2
happy-transformer (🥉23 · ⭐ 480) - Happy Transformer makes it easy to fine-tune and.. Apache-2 huggingface
Texthero (🥉22 · ⭐ 2.8K) - Text preprocessing, representation and visualization from zero to hero. MIT
YouTokenToMe (🥉22 · ⭐ 930 · 💤) - Unsupervised text tokenizer focused on computational efficiency. MIT
small-text (🥉22 · ⭐ 510) - Active Learning for Text Classification in Python. MIT
textaugment (🥉20 · ⭐ 350) - TextAugment: Text Augmentation Library. MIT
OpenNRE (🥉16 · ⭐ 4.2K) - An Open-Source Package for Neural Relation Extraction (NRE). MIT
-
GitHub (👨💻 13 · 🔀 980 · 📋 360 - 3% open · ⏱️ 04.01.2024):
git clone https://github.com/thunlp/OpenNRE
Show 48 hidden projects...
- flair (🥇37 · ⭐ 13K) - A very simple framework for state-of-the-art Natural Language..
❗Unlicensed - ChatterBot (🥇35 · ⭐ 14K · 💀) - ChatterBot is a machine learning, conversational dialog engine..
BSD-3 - AllenNLP (🥇35 · ⭐ 12K · 💀) - An open-source NLP research library, built on PyTorch.
Apache-2 - fuzzywuzzy (🥈33 · ⭐ 9K · 💀) - Fuzzy String Matching in Python.
❗️GPL-2.0 - nlpaug (🥈29 · ⭐ 4.2K · 💀) - Data augmentation for NLP.
MIT - GluonNLP (🥈29 · ⭐ 2.5K · 💀) - Toolkit that enables easy text preprocessing, datasets..
Apache-2 - vaderSentiment (🥈27 · ⭐ 4.2K · 💀) - VADER Sentiment Analysis. VADER (Valence Aware Dictionary..
MIT - fastNLP (🥈27 · ⭐ 3K · 💀) - fastNLP: A Modularized and Extensible NLP Framework. Currently..
Apache-2 - textacy (🥈27 · ⭐ 2.1K · 💤) - NLP, before and after spaCy.
❗Unlicensed - underthesea (🥈27 · ⭐ 1.3K) - Underthesea - Vietnamese NLP Toolkit.
❗️GPL-3.0 - flashtext (🥉25 · ⭐ 5.5K · 💀) - Extract Keywords from sentence or Replace keywords in sentences.
MIT - neuralcoref (🥉25 · ⭐ 2.8K · 💀) - Fast Coreference Resolution in spaCy with Neural Networks.
MIT - english-words (🥉24 · ⭐ 9.7K · 💀) - A text file containing 479k English words for all your..
Unlicense - textgenrnn (🥉24 · ⭐ 4.9K · 💀) - Easily train your own text-generating neural network of any..
MIT - MatchZoo (🥉24 · ⭐ 3.8K · 💀) - Facilitating the design, comparison and sharing of deep..
Apache-2 - polyglot (🥉24 · ⭐ 2.2K · 💀) - Multilingual text (NLP) processing toolkit.
❗Unlicensed - langid (🥉24 · ⭐ 2.2K · 💀) - Stand-alone language identification system.
❗Unlicensed - pySBD (🥉24 · ⭐ 680 · 💀) - pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence..
MIT - Snips NLU (🥉23 · ⭐ 3.8K · 💀) - Snips Python library to extract meaning from text.
Apache-2 - Kashgari (🥉23 · ⭐ 2.4K · 💀) - Kashgari is a production-level NLP Transfer learning..
Apache-2 - FARM (🥉23 · ⭐ 1.7K · 💀) - Fast & easy transfer learning for NLP. Harvesting language..
Apache-2 - PyText (🥉22 · ⭐ 6.4K · 💀) - A natural language modeling framework based on PyTorch.
❗Unlicensed - DeepMatcher (🥉22 · ⭐ 4.9K · 💀) - Python package for performing Entity and Text Matching using..
BSD-3 - gpt-2-simple (🥉22 · ⭐ 3.4K · 💀) - Python package to easily retrain OpenAIs GPT-2 text-..
MIT - Texar (🥉22 · ⭐ 2.4K · 💀) - Toolkit for Machine Learning, Natural Language Processing, and..
Apache-2 - jiant (🥉22 · ⭐ 1.6K · 💀) - jiant is an nlp toolkit.
MIT - stop-words (🥉22 · ⭐ 150 · 💀) - Get list of common stop words in various languages in Python.
BSD-3 - anaGo (🥉21 · ⭐ 1.5K · 💀) - Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition,..
MIT - NLP Architect (🥉20 · ⭐ 2.9K · 💀) - A model library for exploring state-of-the-art deep..
Apache-2 - DELTA (🥉20 · ⭐ 1.6K · 💀) - DELTA is a deep learning based natural language and speech..
Apache-2 - pyfasttext (🥉20 · ⭐ 230 · 💀) - Yet another Python binding for fastText.
❗️GPL-3.0 - numerizer (🥉20 · ⭐ 210 · 💤) - A Python module to convert natural language numerics into ints and..
MIT - textpipe (🥉19 · ⭐ 300 · 💀) - Textpipe: clean and extract metadata from text.
MIT - lightseq (🥉18 · ⭐ 3K · 💤) - LightSeq: A High Performance Library for Sequence Processing..
❗Unlicensed - Camphr (🥉18 · ⭐ 340 · 💀) - Camphr - NLP libary for creating pipeline components.
Apache-2spacy - fastT5 (🥉17 · ⭐ 510 · 💀) - boost inference speed of T5 models by 5x & reduce the model size..
Apache-2 - whoosh (🥉17 · ⭐ 490 · 💀) - Pure-Python full-text search library.
❗Unlicensed - NeuroNER (🥉16 · ⭐ 1.7K · 💀) - Named-entity recognition using neural networks. Easy-to-use and..
MIT - skift (🥉16 · ⭐ 230 · 💀) - scikit-learn wrappers for Python fastText.
MIT - BLINK (🥉15 · ⭐ 1.1K · 💀) - Entity Linker solution.
MIT - Translate (🥉15 · ⭐ 810 · 💀) - Translate - a PyTorch Language Library.
BSD-3 - nboost (🥉15 · ⭐ 670 · 💀) - NBoost is a scalable, search-api-boosting platform for deploying..
Apache-2 - Headliner (🥉14 · ⭐ 230 · 💀) - Easy training and deployment of seq2seq models.
MIT - TransferNLP (🥉13 · ⭐ 290 · 💀) - NLP library designed for reproducible experimentation..
MIT - ONNX-T5 (🥉13 · ⭐ 240 · 💀) - Summarization, translation, sentiment-analysis, text-generation..
Apache-2 - NeuralQA (🥉13 · ⭐ 230 · 💀) - NeuralQA: A Usable Library for Question Answering on Large Datasets..
MIT - textvec (🥉13 · ⭐ 190 · 💀) - Text vectorization tool to outperform TFIDF for classification..
MIT - spacy-dbpedia-spotlight (🥉12 · ⭐ 94 · 💤) - A spaCy wrapper for DBpedia Spotlight.
MITspacy
Image Data
Libraries for image & video processing, manipulation, and augmentation as well as libraries for computer vision tasks such as facial recognition, object detection, and classification.
PyTorch Image Models (🥇41 · ⭐ 28K) - PyTorch image models, scripts, pretrained weights --.. Apache-2
MMDetection (🥇39 · ⭐ 27K) - OpenMMLab Detection Toolbox and Benchmark. Apache-2
torchvision (🥇38 · ⭐ 15K · 📉) - Datasets, Transforms and Models specific to Computer Vision. BSD-3
opencv-python (🥈36 · ⭐ 3.9K) - Automated CI toolchain to produce precompiled opencv-python,.. MIT
InsightFace (🥈35 · ⭐ 20K · 📈) - State-of-the-art 2D and 3D Face Analysis Project. MIT
Albumentations (🥈35 · ⭐ 13K) - Fast image augmentation library and an easy-to-use wrapper.. MIT
detectron2 (🥈33 · ⭐ 28K) - Detectron2 is a platform for object detection, segmentation.. Apache-2
vit-pytorch (🥈30 · ⭐ 16K) - Implementation of Vision Transformer, a simple way to achieve.. MIT
imageai (🥈29 · ⭐ 8.2K) - A python library built to empower developers to build applications and.. MIT
Face Alignment (🥈29 · ⭐ 6.7K) - 2D and 3D Face alignment library build using pytorch. BSD-3
sahi (🥈29 · ⭐ 3.3K) - Framework agnostic sliced/tiled inference + interactive ui + error analysis.. MIT
PaddleDetection (🥉28 · ⭐ 12K) - Object Detection toolkit based on PaddlePaddle. It.. Apache-2
vidgear (🥉28 · ⭐ 3.1K) - A High-performance cross-platform Video Processing Python framework.. Apache-2
CellProfiler (🥉28 · ⭐ 830) - An open-source application for biological image analysis. BSD-3
facenet-pytorch (🥉26 · ⭐ 3.9K) - Pretrained Pytorch face detection (MTCNN) and facial.. MIT
Image Deduplicator (🥉25 · ⭐ 4.8K · 💤) - Finding duplicate images made easy!. Apache-2
pytorchvideo (🥉25 · ⭐ 3.1K) - A deep learning library for video understanding research. Apache-2
DE⫶TR (🥉22 · ⭐ 12K · 💤) - End-to-End Object Detection with Transformers. Apache-2
-
GitHub (👨💻 26 · 🔀 2.1K · 📦 21 · 📋 520 - 45% open · ⏱️ 07.02.2023):
git clone https://github.com/facebookresearch/detr
tensorflow-graphics (🥉22 · ⭐ 2.7K) - TensorFlow Graphics: Differentiable Graphics Layers.. Apache-2
PySlowFast (🥉20 · ⭐ 6.1K) - PySlowFast: video understanding codebase from FAIR for.. Apache-2
Classy Vision (🥉20 · ⭐ 1.6K · 💤) - An end-to-end PyTorch framework for image and video.. MIT
scenic (🥉18 · ⭐ 2.7K) - Scenic: A Jax Library for Computer Vision Research and Beyond. Apache-2
-
GitHub (👨💻 74 · 🔀 360 · 📋 200 - 48% open · ⏱️ 15.11.2023):
git clone https://github.com/google-research/scenic
Caer (🥉17 · ⭐ 730 · 💤) - A lightweight Computer Vision library. Scale your models, not boilerplate. MIT
Show 21 hidden projects...
- scikit-image (🥇42 · ⭐ 5.7K) - Image processing in Python.
❗Unlicensed - glfw (🥈36 · ⭐ 12K) - A multi-platform library for OpenGL, OpenGL ES, Vulkan, window and input.
❗️Zlib - imgaug (🥈35 · ⭐ 14K · 💀) - Image augmentation for machine learning experiments.
MIT - Face Recognition (🥈33 · ⭐ 51K · 💀) - The worlds simplest facial recognition api for Python..
MIT - imutils (🥈31 · ⭐ 4.4K · 💀) - A series of convenience functions to make basic image processing..
MIT - PyTorch3D (🥈30 · ⭐ 8K) - PyTorch3D is FAIRs library of reusable components for deep..
❗Unlicensed - layout-parser (🥉28 · ⭐ 4.2K · 💀) - A Unified Toolkit for Deep Learning Based Document Image..
Apache-2 - chainercv (🥉27 · ⭐ 1.5K · 💀) - ChainerCV: a Library for Deep Learning in Computer Vision.
MIT - mtcnn (🥉26 · ⭐ 2.1K · 💀) - MTCNN face detection implementation for TensorFlow, as a PIP..
MIT - segmentation_models (🥉24 · ⭐ 4.5K · 💀) - Segmentation models with pretrained backbones. Keras..
MIT - Image Super-Resolution (🥉24 · ⭐ 4.4K · 💀) - Super-scale your images and run experiments with..
Apache-2 - Luminoth (🥉23 · ⭐ 2.4K · 💀) - Deep Learning toolkit for Computer Vision.
BSD-3 - deep-daze (🥉22 · ⭐ 4.4K · 💀) - Simple command line tool for text to image generation using..
MIT - Pillow-SIMD (🥉21 · ⭐ 2.1K · 💤) - The friendly PIL fork.
❗️PIL - icevision (🥉21 · ⭐ 840 · 💀) - An Agnostic Computer Vision Framework - Pluggable to any..
Apache-2 - image-match (🥉20 · ⭐ 2.9K · 💀) - Quickly search over billions of images.
Apache-2 - detecto (🥉20 · ⭐ 610 · 💀) - Build fully-functioning computer vision models with PyTorch.
MIT - nude.py (🥉19 · ⭐ 920 · 💀) - Nudity detection with Python.
MIT - solt (🥉18 · ⭐ 260 · 💀) - Streaming over lightweight data transformations.
MIT - Torch Points 3D (🥉14 · ⭐ 180 · 💀) - Pytorch framework for doing deep learning on point..
BSD-3 - HugsVision (🥉13 · ⭐ 180 · 💤) - HugsVision is a easy to use huggingface wrapper for state-of-..
MIThuggingface
Graph Data
Libraries for graph processing, clustering, embedding, and machine learning tasks.
PyTorch Geometric (🥇38 · ⭐ 19K) - Graph Neural Network Library for PyTorch. MIT
dgl (🥇38 · ⭐ 13K) - Python package built to ease deep learning on graph, on top of existing DL.. Apache-2
pygraphistry (🥈30 · ⭐ 2K) - PyGraphistry is a Python library to quickly load, shape,.. BSD-3
ogb (🥈28 · ⭐ 1.8K) - Benchmark datasets, data loaders, and evaluators for graph machine learning. MIT
pytorch_geometric_temporal (🥈25 · ⭐ 2.4K) - PyTorch Geometric Temporal: Spatiotemporal Signal.. MIT
Paddle Graph Learning (🥈25 · ⭐ 1.6K) - Paddle Graph Learning (PGL) is an efficient and.. Apache-2
PyTorch-BigGraph (🥈24 · ⭐ 3.3K) - Generate embeddings from large-scale graph-structured.. BSD-3
AmpliGraph (🥈24 · ⭐ 2K) - Python library for Representation Learning on Knowledge.. Apache-2
PyKEEN (🥈24 · ⭐ 1.4K) - A Python library for learning and evaluating knowledge graph embeddings. MIT
torch-cluster (🥉20 · ⭐ 720) - PyTorch Extension Library of Optimized Graph Cluster.. MIT
GraphGym (🥉19 · ⭐ 1.5K · 💤) - Platform for designing and evaluating Graph Neural Networks (GNN). MIT
OpenKE (🥉17 · ⭐ 3.6K) - An Open-Source Package for Knowledge Embedding (KE). MIT
-
GitHub (👨💻 14 · 🔀 960 · 📋 380 - 5% open · ⏱️ 04.01.2024):
git clone https://github.com/thunlp/OpenKE
OpenNE (🥉14 · ⭐ 1.7K) - An Open-Source Package for Network Embedding (NE). MIT
-
GitHub (👨💻 13 · 🔀 480 · 📋 100 - 4% open · ⏱️ 04.01.2024):
git clone https://github.com/thunlp/OpenNE
Show 17 hidden projects...
- networkx (🥇42 · ⭐ 14K) - Network Analysis in Python.
❗Unlicensed - igraph (🥇34 · ⭐ 1.2K) - Python interface for igraph.
❗️GPL-2.0 - pygal (🥈30 · ⭐ 2.6K) - PYthon svg GrAph plotting Library.
❗️LGPL-3.0 - StellarGraph (🥈27 · ⭐ 2.8K · 💀) - StellarGraph - Machine Learning on Graphs.
Apache-2 - Karate Club (🥈24 · ⭐ 2K) - Karate Club: An API Oriented Open-source Python Framework for..
❗️GPL-3.0 - DIG (🥉22 · ⭐ 1.7K) - A library for graph deep learning research.
❗️GPL-3.0 - graph4nlp (🥉21 · ⭐ 1.6K · 💀) - Graph4nlp is the library for the easy use of Graph..
Apache-2 - DeepWalk (🥉20 · ⭐ 2.6K · 💀) - DeepWalk - Deep Learning for Graphs.
❗️GPL-3.0 - jraph (🥉20 · ⭐ 1.3K · 💀) - A Graph Neural Network Library in Jax.
Apache-2 - pyRDF2Vec (🥉20 · ⭐ 230) - Python Implementation and Extension of RDF2Vec.
MIT - graph-nets (🥉19 · ⭐ 5.3K · 💀) - Build Graph Nets in Tensorflow.
Apache-2 - GraphEmbedding (🥉16 · ⭐ 3.5K · 💀) - Implementation and experiments of graph embedding..
MIT - DeepGraph (🥉16 · ⭐ 280) - Analyze Data with Pandas-based Networks. Documentation:.
BSD-3 - GraphSAGE (🥉14 · ⭐ 3.2K · 💀) - Representation learning on large graphs using stochastic..
MIT - Euler (🥉14 · ⭐ 2.9K · 💀) - A distributed graph deep learning framework.
Apache-2 - GraphVite (🥉14 · ⭐ 1.2K · 💀) - GraphVite: A General and High-performance Graph Embedding..
Apache-2 - ptgnn (🥉14 · ⭐ 370 · 💀) - A PyTorch Graph Neural Network Library.
MIT
Audio Data
Libraries for audio analysis, manipulation, transformation, and extraction, as well as speech recognition and music generation tasks.
speechbrain (🥇37 · ⭐ 7.1K) - A PyTorch-based Speech Toolkit. Apache-2
SpeechRecognition (🥈32 · ⭐ 7.8K) - Speech recognition module for Python, supporting several.. BSD-3
audioread (🥈31 · ⭐ 460) - cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding.. MIT
torchaudio (🥈30 · ⭐ 2.3K) - Data manipulation and transformation for audio signal.. BSD-2
audiomentations (🥈30 · ⭐ 1.6K) - A Python library for audio data augmentation. Inspired by.. MIT
python-soundfile (🥈30 · ⭐ 620) - SoundFile is an audio library based on libsndfile, CFFI, and.. BSD-3
pyAudioAnalysis (🥉25 · ⭐ 5.5K) - Python Audio Analysis Library: Feature Extraction,.. Apache-2
tinytag (🥉25 · ⭐ 640) - Read audio and music meta data and duration of MP3, OGG, OPUS, MP4, M4A,.. MIT
textlesslib (🥉10 · ⭐ 480) - Library for Textless Spoken Language Processing. MIT
-
GitHub (👨💻 8 · 🔀 48 · 📋 18 - 50% open · ⏱️ 29.08.2023):
git clone https://github.com/facebookresearch/textlesslib
Show 11 hidden projects...
- DeepSpeech (🥈34 · ⭐ 24K · 💀) - DeepSpeech is an open source embedded (offline, on-..
MPL-2.0 - Pydub (🥈33 · ⭐ 8K · 💀) - Manipulate audio with a simple and easy high level interface.
MIT - aubio (🥉29 · ⭐ 3.1K) - a library for audio and music analysis.
❗️GPL-3.0 - TTS (🥉27 · ⭐ 8.4K · 💀) - Deep learning for Text to Speech (Discussion forum:..
MPL-2.0 - Essentia (🥉27 · ⭐ 2.6K) - C++ library for audio and music analysis, description and..
❗️AGPL-3.0 - python_speech_features (🥉25 · ⭐ 2.3K · 💀) - This library provides common speech features for ASR..
MIT - Dejavu (🥉22 · ⭐ 6.2K · 💀) - Audio fingerprinting and recognition in Python.
MIT - kapre (🥉21 · ⭐ 900 · 💀) - kapre: Keras Audio Preprocessors.
MIT - Julius (🥉21 · ⭐ 380 · 💀) - Fast PyTorch based DSP for audio and 1D signals.
MIT - TimeSide (🥉20 · ⭐ 360 · 💤) - scalable audio processing framework and server written in..
❗️AGPL-3.0 - Muda (🥉17 · ⭐ 220 · 💀) - A library for augmenting annotated audio data.
ISC
Geospatial Data
Libraries to load, process, analyze, and write geographic data as well as libraries for spatial analysis, map visualization, and geocoding.
ipyleaflet (🥈34 · ⭐ 1.4K) - A Jupyter - Leaflet.js bridge. MIT
ArcGIS API (🥉30 · ⭐ 1.7K) - Documentation and samples for ArcGIS API for Python. Apache-2
EarthPy (🥉26 · ⭐ 470) - A package built to support working with spatial data using open source.. BSD-3
pymap3d (🥉25 · ⭐ 350) - pure-Python (Numpy optional) 3D coordinate conversions for geospace ecef.. BSD-2
Show 8 hidden projects...
- Rasterio (🥈36 · ⭐ 2.1K) - Rasterio reads and writes geospatial raster datasets.
❗Unlicensed - Geocoder (🥈32 · ⭐ 1.6K · 💀) - Python Geocoder.
MIT - Satpy (🥉31 · ⭐ 980) - Python package for earth-observing satellite data processing.
❗️GPL-3.0 - Sentinelsat (🥉26 · ⭐ 940) - Search and download Copernicus Sentinel satellite images.
❗️GPL-3.0 - Mapbox GL (🥉23 · ⭐ 640 · 💀) - Use Mapbox GL JS to visualize data in a Python Jupyter notebook.
MIT - prettymaps (🥉22 · ⭐ 11K · 💤) - A small set of Python functions to draw pretty maps from..
❗️AGPL-3.0 - gmaps (🥉20 · ⭐ 760 · 💀) - Google maps for Jupyter notebooks.
BSD-3 - geoplotlib (🥉18 · ⭐ 1K · 💀) - python toolbox for visualizing geographical data and making maps.
MIT
Financial Data
Libraries for algorithmic stock/crypto trading, risk analytics, backtesting, technical analysis, and other tasks on financial data.
Alpha Vantage (🥈28 · ⭐ 4.1K) - A python wrapper for Alpha Vantage API for financial data. MIT
stockstats (🥉26 · ⭐ 1.2K) - Supply a wrapper ``StockDataFrame`` based on the.. BSD-3
PyAlgoTrade (🥉25 · ⭐ 4.2K · 💤) - Python Algorithmic Trading Library. Apache-2
FinQuant (🥉24 · ⭐ 1.2K) - A program for financial portfolio management, analysis and optimisation. MIT
finmarketpy (🥉22 · ⭐ 3.3K) - Python library for backtesting trading strategies & analyzing.. Apache-2
tf-quant-finance (🥉20 · ⭐ 4.2K) - High-performance TensorFlow library for quantitative.. Apache-2
Show 13 hidden projects...
- zipline (🥇33 · ⭐ 17K · 💀) - Zipline, a Pythonic Algorithmic Trading Library.
Apache-2 - pyfolio (🥇32 · ⭐ 5.3K · 💀) - Portfolio and risk analytics in Python.
Apache-2 - arch (🥈31 · ⭐ 1.2K) - ARCH models in Python.
❗Unlicensed - backtrader (🥈29 · ⭐ 12K · 💤) - Python Backtesting library for trading strategies.
❗️GPL-3.0 - empyrical (🥈28 · ⭐ 1.2K · 💀) - Common financial risk and performance metrics. Used by..
Apache-2 - Alphalens (🥉26 · ⭐ 2.9K · 💀) - Performance analysis of predictive (alpha) stock factors.
Apache-2 - TensorTrade (🥉25 · ⭐ 4.3K · 💀) - An open source reinforcement learning framework for..
Apache-2 - Enigma Catalyst (🥉25 · ⭐ 2.5K · 💀) - An Algorithmic Trading Library for Crypto-Assets in..
Apache-2 - Crypto Signals (🥉23 · ⭐ 4.6K · 💀) - Github.com/CryptoSignal - Trading & Technical Analysis Bot -..
MIT - FinTA (🥉23 · ⭐ 2K · 💀) - Common financial technical indicators implemented in Pandas.
❗️LGPL-3.0 - Backtesting.py (🥉22 · ⭐ 4.4K · 💤) - Backtest trading strategies in Python.
❗️AGPL-3.0 - surpriver (🥉12 · ⭐ 1.7K · 💀) - Find big moving stocks before they move using machine..
❗️GPL-3.0 - pyrtfolio (🥉8 · ⭐ 140 · 💀) - Python package to generate stock portfolios.
❗️GPL-3.0
Time Series Data
Libraries for forecasting, anomaly detection, feature extraction, and machine learning on time-series and sequential data.
Prophet (🥇36 · ⭐ 17K) - Tool for producing high quality forecasts for time series data that has.. MIT
StatsForecast (🥇34 · ⭐ 3.3K) - Lightning fast forecasting with statistical and econometric.. Apache-2
pmdarima (🥈32 · ⭐ 1.5K) - A statistical library designed to fill the void in Pythons time series.. MIT
Darts (🥈31 · ⭐ 6.8K) - A python library for user-friendly forecasting and anomaly detection.. Apache-2
-
GitHub (👨💻 110 · 🔀 750 · 📦 480 · 📋 1.3K - 19% open · ⏱️ 29.12.2023):
git clone https://github.com/unit8co/darts -
PyPi (📥 17K / month · 📦 5 · ⏱️ 10.12.2023):
pip install u8darts -
Conda (📥 39K · ⏱️ 10.12.2023):
conda install -c conda-forge u8darts-all -
Docker Hub (📥 460 · ⏱️ 10.12.2023):
docker pull unit8/darts
NeuralProphet (🥈31 · ⭐ 3.5K) - NeuralProphet: A simple forecasting package. MIT
STUMPY (🥈31 · ⭐ 2.9K) - STUMPY is a powerful and scalable Python library for modern time series.. BSD-3
pytorch-forecasting (🥈29 · ⭐ 3.4K) - Time series forecasting with PyTorch. MIT
NeuralForecast (🥈29 · ⭐ 2.1K) - Scalable and user friendly neural forecasting algorithms. Apache-2
skforecast (🥈28 · ⭐ 760) - Time series forecasting with scikit-learn models. BSD-3
uber/orbit (🥉24 · ⭐ 1.8K) - A Python package for Bayesian forecasting with object-oriented.. Apache-2
tick (🥉21 · ⭐ 450 · 💤) - Module for statistical learning, with a particular emphasis on time-.. BSD-3
Show 8 hidden projects...
- Streamz (🥉25 · ⭐ 1.2K · 💀) - Real-time stream processing for python.
BSD-3 - PyFlux (🥉24 · ⭐ 2.1K · 💀) - Open source time series library for Python.
BSD-3 - ADTK (🥉20 · ⭐ 990 · 💀) - A Python toolkit for rule-based/unsupervised anomaly detection in time..
MPL-2.0 - seglearn (🥉20 · ⭐ 560 · 💀) - Python module for machine learning time series:.
BSD-3 - matrixprofile-ts (🥉17 · ⭐ 720 · 💀) - A Python library for detecting patterns and anomalies..
Apache-2 - tsaug (🥉13 · ⭐ 320 · 💀) - A Python package for time series augmentation.
Apache-2 - atspy (🥉11 · ⭐ 500 · 💀) - AtsPy: Automated Time Series Models in Python (by @firmai).
❗Unlicensed - tslumen (🥉8 · ⭐ 55 · 💀) - A library for Time Series EDA (exploratory data analysis).
Apache-2
Medical Data
Libraries for processing and analyzing medical data such as MRIs, EEGs, genomic data, and other medical imaging formats.
MNE (🥇38 · ⭐ 2.4K) - MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python. BSD-3
DeepVariant (🥉27 · ⭐ 3K) - DeepVariant is an analysis pipeline that uses a deep neural.. BSD-3
Brainiak (🥉16 · ⭐ 320) - Brain Imaging Analysis Kit. Apache-2
-
GitHub (👨💻 35 · 🔀 130 · 📋 210 - 38% open · ⏱️ 27.11.2023):
git clone https://github.com/brainiak/brainiak -
PyPi (📥 78 / month):
pip install brainiak -
Docker Hub (📥 1.8K · ⭐ 1 · ⏱️ 15.10.2020):
docker pull brainiak/brainiak
Show 10 hidden projects...
- DIPY (🥈31 · ⭐ 640) - DIPY is the paragon 3D/4D+ imaging library in Python. Contains..
❗Unlicensed - NiftyNet (🥉24 · ⭐ 1.3K · 💀) - [unmaintained] An open-source convolutional neural..
Apache-2 - NIPY (🥉24 · ⭐ 360) - Neuroimaging in Python FMRI analysis package.
❗Unlicensed - MedPy (🥉22 · ⭐ 530) - Medical image processing in Python.
❗️GPL-3.0 - DLTK (🥉20 · ⭐ 1.4K · 💀) - Deep Learning Toolkit for Medical Image Analysis.
Apache-2 - Glow (🥉20 · ⭐ 250 · 💤) - An open-source toolkit for large-scale genomic analysis.
Apache-2 - MedicalTorch (🥉15 · ⭐ 820 · 💀) - A medical imaging framework for Pytorch.
Apache-2 - Medical Detection Toolkit (🥉14 · ⭐ 1.2K · 💀) - The Medical Detection Toolkit contains 2D + 3D..
Apache-2 - MedicalNet (🥉13 · ⭐ 1.8K · 💀) - Many studies have shown that the performance on deep learning is..
MIT - DeepNeuro (🥉10 · ⭐ 120 · 💀) - A deep learning python package for neuroimaging data. Made by:.
MIT
Tabular Data
Libraries for processing tabular and structured data.
pytorch_tabular (🥈22 · ⭐ 1.1K) - A standard framework for modelling Deep Learning Models.. MIT
carefree-learn (🥉21 · ⭐ 400) - Deep Learning PyTorch. MIT
Show 3 hidden projects...
Optical Character Recognition
Libraries for optical character recognition (OCR) and text extraction from images or videos.
EasyOCR (🥇35 · ⭐ 21K) - Ready-to-use OCR with 80+ supported languages and all popular writing.. Apache-2
OCRmyPDF (🥈34 · ⭐ 11K) - OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them.. MPL-2.0
Tesseract (🥈28 · ⭐ 5.3K · 📉) - Python-tesseract is an optical character recognition (OCR).. Apache-2
attention-ocr (🥉20 · ⭐ 1K) - A Tensorflow model for text recognition (CNN + seq2seq with.. MIT
Show 3 hidden projects...
Data Containers & Structures
General-purpose data containers & structures as well as utilities & extensions for pandas.
🔗 best-of-python - Data Containers ( ⭐ 3.3K) - Collection of data-container, dataframe, and pandas-..
Data Loading & Extraction
Libraries for loading, collecting, and extracting data from a variety of data sources and formats.
🔗 best-of-python - Data Extraction ( ⭐ 3.3K) - Collection of data-loading and -extraction libraries.
Web Scraping & Crawling
Libraries for web scraping, crawling, downloading, and mining as well as libraries.
🔗 best-of-web-python - Web Scraping ( ⭐ 2.1K) - Collection of web-scraping and crawling libraries.
Data Pipelines & Streaming
Libraries for data batch- and stream-processing, workflow automation, job scheduling, and other data pipeline tasks.
🔗 best-of-python - Data Pipelines ( ⭐ 3.3K) - Libraries for data batch- and stream-processing,..
Distributed Machine Learning
Libraries that provide capabilities to distribute and parallelize machine learning tasks across large-scale compute infrastructure.
Ray (🥇44 · ⭐ 29K) - Ray is a unified framework for scaling AI and Python applications. Ray.. Apache-2
DeepSpeed (🥇40 · ⭐ 31K) - DeepSpeed is a deep learning optimization library that makes.. Apache-2
-
GitHub (👨💻 280 · 🔀 3.7K · 📦 5.3K · 📋 2.3K - 37% open · ⏱️ 03.01.2024):
git clone https://github.com/microsoft/DeepSpeed -
PyPi (📥 330K / month · 📦 91 · ⏱️ 21.12.2023):
pip install deepspeed -
Docker Hub (📥 17K · ⭐ 4 · ⏱️ 02.09.2022):
docker pull deepspeed/deepspeed
dask.distributed (🥇40 · ⭐ 1.5K) - A distributed task scheduler for Dask. BSD-3
BigDL (🥈36 · ⭐ 4.7K) - Accelerate LLM with low-bit (FP4 / INT4 / FP8 / INT8) optimizations.. Apache-2
-
GitHub (👨💻 200 · 🔀 1.2K · 📥 180 · 📦 46 · 📋 2.3K - 41% open · ⏱️ 04.01.2024):
git clone https://github.com/intel-analytics/BigDL -
PyPi (📥 7.3K / month · 📦 1 · ⏱️ 04.01.2024):
pip install bigdl -
Maven (📦 4 · ⏱️ 20.04.2021):
<dependency> <groupId>com.intel.analytics.bigdl</groupId> <artifactId>bigdl-SPARK_2.4</artifactId> <version>[VERSION]</version> </dependency>
horovod (🥈35 · ⭐ 14K) - Distributed training framework for TensorFlow, Keras, PyTorch, and.. Apache-2
H2O-3 (🥈35 · ⭐ 6.6K) - H2O is an Open Source, Distributed, Fast & Scalable Machine Learning.. Apache-2
ColossalAI (🥈33 · ⭐ 36K) - Making large AI models cheaper, faster and more accessible. Apache-2
-
GitHub (👨💻 160 · 🔀 4K · 📦 280 · 📋 1.5K - 22% open · ⏱️ 04.01.2024):
git clone https://github.com/hpcaitech/colossalai
TensorFlowOnSpark (🥉27 · ⭐ 3.9K · 💤) - TensorFlowOnSpark brings TensorFlow programs to.. Apache-2
petastorm (🥉26 · ⭐ 1.7K) - Petastorm library enables single machine or distributed training.. Apache-2
Apache Singa (🥉23 · ⭐ 3K) - a distributed deep learning platform. Apache-2
-
GitHub (👨💻 85 · 🔀 1K · 📦 3 · 📋 120 - 42% open · ⏱️ 05.11.2023):
git clone https://github.com/apache/singa -
Conda (📥 730 · ⏱️ 16.06.2023):
conda install -c nusdbsystem singa -
Docker Hub (📥 5.2K · ⭐ 4 · ⏱️ 31.05.2022):
docker pull apache/singa
analytics-zoo (🥉23 · ⭐ 2.6K) - Distributed Tensorflow, Keras and PyTorch on Apache.. Apache-2
mesh-transformer-jax (🥉18 · ⭐ 6.2K · 💤) - Model parallel transformers in JAX and Haiku. Apache-2
-
GitHub (👨💻 23 · 🔀 870 · 📦 20 · 📋 200 - 22% open · ⏱️ 12.01.2023):
git clone https://github.com/kingoflolz/mesh-transformer-jax
Show 13 hidden projects...
- DEAP (🥈32 · ⭐ 5.4K) - Distributed Evolutionary Algorithms in Python.
❗️LGPL-3.0 - Elephas (🥈29 · ⭐ 1.6K · 💀) - Distributed Deep learning with Keras & Spark.
MITkeras - ipyparallel (🥈28 · ⭐ 2.5K) - IPython Parallel: Interactive Parallel Computing in..
❗Unlicensed - BytePS (🥉20 · ⭐ 3.5K · 💀) - A high performance and generic framework for distributed DNN..
Apache-2 - TensorFrames (🥉20 · ⭐ 750 · 💀) - [DEPRECATED] Tensorflow wrapper for DataFrames on..
Apache-2 - sk-dist (🥉20 · ⭐ 290 · 💤) - Distributed scikit-learn meta-estimators in PySpark.
Apache-2 - somoclu (🥉20 · ⭐ 260 · 💀) - Massively parallel self-organizing maps: accelerate training on..
MIT - Fiber (🥉17 · ⭐ 1K · 💀) - Distributed Computing for AI Made Simple.
Apache-2 - bluefog (🥉17 · ⭐ 290 · 💤) - Distributed and decentralized training framework for PyTorch..
Apache-2 - parallelformers (🥉16 · ⭐ 730 · 💀) - Parallelformers: An Efficient Model Parallelization..
Apache-2 - LazyCluster (🥉12 · ⭐ 49 · 💀) - Distributed machine learning made simple.
Apache-2 - moolib (🥉10 · ⭐ 360 · 💀) - A library for distributed ML training with PyTorch.
MIT - autodist (🥉10 · ⭐ 130 · 💀) - Simple Distributed Deep Learning on TensorFlow.
Apache-2
Hyperparameter Optimization & AutoML
Libraries for hyperparameter optimization, automl and neural architecture search.
featuretools (🥈32 · ⭐ 6.9K) - An open source python library for automated feature engineering. BSD-3
Keras Tuner (🥈32 · ⭐ 2.8K) - A Hyperparameter Tuning Library for Keras. Apache-2
auto-sklearn (🥈31 · ⭐ 7.3K · 💤) - Automated Machine Learning with scikit-learn. BSD-3
Bayesian Optimization (🥈30 · ⭐ 7.2K) - A Python implementation of global optimization with.. MIT
AutoGluon (🥈29 · ⭐ 6.6K) - AutoGluon: AutoML for Image, Text, Time Series, and.. Apache-2
-
GitHub (👨💻 110 · 🔀 790 · 📦 2 · 📋 1.2K - 23% open · ⏱️ 28.12.2023):
git clone https://github.com/autogluon/autogluon -
PyPi (📥 68K / month):
pip install autogluon -
Docker Hub (📥 6.3K · ⭐ 17 · ⏱️ 26.07.2023):
docker pull autogluon/autogluon
mljar-supervised (🥈28 · ⭐ 2.9K) - Python package for AutoML on Tabular Data with Feature.. MIT
featurewiz (🥈24 · ⭐ 510) - Use advanced feature engineering strategies and select best.. Apache-2
Hyperactive (🥉23 · ⭐ 480) - An optimization and data collection toolbox for convenient and fast.. MIT
igel (🥉19 · ⭐ 3.1K · 💤) - a delightful machine learning tool that allows you to train, test, and.. MIT
AlphaPy (🥉19 · ⭐ 1K) - Automated Machine Learning [AutoML] with Python, scikit-learn, Keras,.. Apache-2
Auto ViML (🥉19 · ⭐ 480) - Automatically Build Multiple ML Models with a Single Line of Code... Apache-2
opytimizer (🥉18 · ⭐ 580) - Opytimizer is a Python library consisting of meta-heuristic.. Apache-2
Show 31 hidden projects...
- Optuna (🥇39 · ⭐ 9.1K) - A hyperparameter optimization framework.
❗Unlicensed - TPOT (🥇33 · ⭐ 9.4K) - A Python Automated Machine Learning tool that optimizes machine..
❗️LGPL-3.0 - scikit-optimize (🥇33 · ⭐ 2.7K · 💀) - Sequential model-based optimization with a..
BSD-3 - SMAC3 (🥈27 · ⭐ 940) - SMAC3: A Versatile Bayesian Optimization Package for..
❗️BSD-1-Clause - lazypredict (🥈26 · ⭐ 2.3K · 💀) - Lazy Predict help build a lot of basic models without much..
MIT - Orion (🥈25 · ⭐ 270) - Asynchronous Distributed Hyperparameter Optimization.
BSD-3 - AdaNet (🥈24 · ⭐ 3.5K · 💀) - Fast and flexible AutoML with learning guarantees.
Apache-2 - Talos (🥈24 · ⭐ 1.6K · 💀) - Hyperparameter Optimization for TensorFlow, Keras and PyTorch.
MIT - auto_ml (🥉22 · ⭐ 1.6K · 💀) - [UNMAINTAINED] Automated machine learning for analytics & production.
MIT - HpBandSter (🥉22 · ⭐ 590 · 💀) - a distributed Hyperband implementation on Steroids.
BSD-3 - optunity (🥉22 · ⭐ 410 · 💀) - optimization routines for hyperparameter tuning.
BSD-3 - lightwood (🥉22 · ⭐ 390) - Lightwood is Legos for Machine Learning.
❗️GPL-3.0 - Neuraxle (🥉21 · ⭐ 590 · 💀) - The worlds cleanest AutoML library - Do hyperparameter tuning..
Apache-2 - MLBox (🥉20 · ⭐ 1.5K · 💀) - MLBox is a powerful Automated Machine Learning python library.
❗Unlicensed - sklearn-deap (🥉20 · ⭐ 750 · 💀) - Use evolutionary algorithms instead of gridsearch in..
MIT - Dragonfly (🥉19 · ⭐ 820 · 💀) - An open source python library for scalable Bayesian optimisation.
MIT - Test Tube (🥉19 · ⭐ 730 · 💀) - Python library to easily log experiments and parallelize..
MIT - Auto Tune Models (🥉18 · ⭐ 520 · 💀) - Auto Tune Models - A multi-tenant, multi-data system for..
MIT - Sherpa (🥉18 · ⭐ 320 · 💀) - Hyperparameter optimization that enables researchers to..
❗️GPL-3.0 - Advisor (🥉17 · ⭐ 1.5K · 💀) - Open-source implementation of Google Vizier for hyper parameters..
Apache-2 - shap-hypetune (🥉17 · ⭐ 510 · 💀) - A python package for simultaneous Hyperparameters Tuning and..
MIT - automl-gs (🥉16 · ⭐ 1.8K · 💀) - Provide an input CSV and a target field to predict, generate a..
MIT - Xcessiv (🥉16 · ⭐ 1.3K · 💀) - A web-based application for quick, scalable, and automated..
Apache-2 - HyperparameterHunter (🥉16 · ⭐ 700 · 💀) - Easy hyperparameter optimization and automatic result..
MIT - Parfit (🥉16 · ⭐ 200 · 💀) - A package for parallelizing the fit and flexibly scoring of..
MIT - ENAS (🥉13 · ⭐ 2.7K · 💀) - PyTorch implementation of Efficient Neural Architecture Search via..
Apache-2 - Auptimizer (🥉12 · ⭐ 200 · 💀) - An automatic ML model optimization tool.
❗️GPL-3.0 - model_search (🥉11 · ⭐ 3.3K · 💀) - AutoML algorithms for model architecture search at scale.
Apache-2 - Devol (🥉11 · ⭐ 950 · 💀) - Genetic neural architecture search with Keras.
MIT - Hypermax (🥉10 · ⭐ 110) - Better, faster hyper-parameter optimization.
BSD-3 - Hypertunity (🥉8 · ⭐ 140 · 💀) - A toolset for black-box hyperparameter optimisation.
Apache-2
Reinforcement Learning
Libraries for building and evaluating reinforcement learning & agent-based systems.
OpenAI Gym (🥇39 · ⭐ 33K · 💤) - A toolkit for developing and comparing reinforcement learning.. MIT
TensorLayer (🥈28 · ⭐ 7.3K · 💤) - Deep Learning and Reinforcement Learning Library for.. Apache-2
TensorForce (🥉26 · ⭐ 3.3K) - Tensorforce: a TensorFlow library for applied.. Apache-2
rliable (🥉14 · ⭐ 660 · 💤) - [NeurIPS21 Outstanding Paper] Library for reliable evaluation on.. Apache-2
Show 9 hidden projects...
- baselines (🥈29 · ⭐ 15K · 💀) - OpenAI Baselines: high-quality implementations of reinforcement..
MIT - keras-rl (🥈28 · ⭐ 5.5K · 💀) - Deep Reinforcement Learning for Keras.
MIT - Stable Baselines (🥉24 · ⭐ 4K · 💀) - A fork of OpenAI Baselines, implementations of..
MIT - ChainerRL (🥉24 · ⭐ 1.1K · 💀) - ChainerRL is a deep reinforcement learning library built on top of..
MIT - TRFL (🥉21 · ⭐ 3.1K · 💀) - TensorFlow Reinforcement Learning.
Apache-2 - Coach (🥉20 · ⭐ 2.3K · 💀) - Reinforcement Learning Coach by Intel AI Lab enables easy..
Apache-2 - SerpentAI (🥉18 · ⭐ 6.6K · 💀) - Game Agent Framework. Helping you create AIs / Bots that learn to..
MIT - DeepMind Lab (🥉17 · ⭐ 7K · 💤) - A customisable 3D platform for agent-based AI research.
❗Unlicensed - Maze (🥉13 · ⭐ 250 · 💀) - Maze Applied Reinforcement Learning Framework.
❗️Custom
Recommender Systems
Libraries for building and evaluating recommendation systems.
Recommenders (🥇35 · ⭐ 17K) - Best Practices on Recommendation Systems. MIT
TF Recommenders (🥈28 · ⭐ 1.7K) - TensorFlow Recommenders is a library for building.. Apache-2
scikit-surprise (🥈27 · ⭐ 6.1K · 💤) - A Python scikit for building and analyzing recommender.. BSD-3
TF Ranking (🥈27 · ⭐ 2.7K) - Learning to Rank in TensorFlow. Apache-2
recmetrics (🥉21 · ⭐ 540) - A library of metrics for evaluating recommender systems. MIT
Show 7 hidden projects...
- lkpy (🥉24 · ⭐ 250) - Python recommendation toolkit.
MIT - tensorrec (🥉21 · ⭐ 1.3K · 💀) - A TensorFlow recommendation algorithm and framework in..
Apache-2 - fastFM (🥉21 · ⭐ 1.1K · 💀) - fastFM: A Library for Factorization Machines.
BSD-3 - Spotlight (🥉18 · ⭐ 2.9K · 💀) - Deep recommender models using PyTorch.
MIT - Case Recommender (🥉17 · ⭐ 450 · 💀) - Case Recommender: A Flexible and Extensible Python..
MIT - OpenRec (🥉16 · ⭐ 400 · 💀) - OpenRec is an open-source and modular library for neural network-..
Apache-2 - Collie (🥉16 · ⭐ 100 · 💤) - A library for preparing, training, and evaluating scalable deep..
BSD-3
Privacy Machine Learning
Libraries for encrypted and privacy-preserving machine learning using methods like federated learning & differential privacy.
TensorFlow Privacy (🥈27 · ⭐ 1.8K) - Library for training machine learning models with.. Apache-2
TFEncrypted (🥉24 · ⭐ 1.2K · 💤) - A Framework for Encrypted Machine Learning in.. Apache-2
Show 1 hidden projects...
- PipelineDP (🥉19 · ⭐ 260) - PipelineDP is a Python framework for applying differentially..
Apache-2
Workflow & Experiment Tracking
Libraries to organize, track, and visualize machine learning experiments.
Tensorboard (🥇43 · ⭐ 6.4K) - TensorFlows Visualization Toolkit. Apache-2
wandb client (🥇40 · ⭐ 7.7K) - A tool for visualizing and tracking your machine learning.. MIT
SageMaker SDK (🥇40 · ⭐ 2K) - A library for training and deploying machine learning.. Apache-2
ClearML (🥈34 · ⭐ 5K) - ClearML - Auto-Magical CI/CD to streamline your ML workflow... Apache-2
-
GitHub (👨💻 88 · 🔀 620 · 📥 1.9K · 📦 870 · 📋 940 - 44% open · ⏱️ 03.01.2024):
git clone https://github.com/allegroai/clearml -
PyPi (📥 210K / month · 📦 17 · ⏱️ 03.01.2024):
pip install clearml -
Docker Hub (📥 30K · ⏱️ 05.10.2020):
docker pull allegroai/trains
AzureML SDK (🥈34 · ⭐ 3.9K) - Python notebooks with ML and deep learning examples with Azure.. MIT
tensorboardX (🥈32 · ⭐ 7.7K) - tensorboard for pytorch (and chainer, mxnet, numpy, ...). MIT
Neptune.ai (🥈30 · ⭐ 440) - The MLOps stack component for experiment tracking. Apache-2
Labml (🥉27 · ⭐ 1.7K) - Monitor deep learning model training and hardware usage from your mobile.. MIT
ml-metadata (🥉26 · ⭐ 580) - For recording and retrieving metadata associated with ML.. Apache-2
TensorWatch (🥉20 · ⭐ 3.4K) - Debugging, monitoring and visualization for Python Machine Learning.. MIT
Show 17 hidden projects...
- Catalyst (🥉28 · ⭐ 3.2K · 💀) - Accelerated deep learning R&D.
Apache-2 - knockknock (🥉26 · ⭐ 2.7K · 💀) - Knock Knock: Get notified when your training ends with only two..
MIT - quinn (🥉26 · ⭐ 540) - pyspark methods to enhance developer productivity.
❗Unlicensed - SKLL (🥉25 · ⭐ 550) - SciKit-Learn Laboratory (SKLL) makes it easy to run machine..
❗️BSD-1-Clause - gokart (🥉25 · ⭐ 300) - Gokart solves reproducibility, task dependencies, constraints of good code,..
MIT - livelossplot (🥉23 · ⭐ 1.3K · 💀) - Live training loss plot in Jupyter Notebook for Keras,..
MIT - hiddenlayer (🥉21 · ⭐ 1.7K · 💀) - Neural network graphs and training metrics for..
MIT - TensorBoard Logger (🥉20 · ⭐ 630 · 💀) - Log TensorBoard events without touching TensorFlow.
MIT - MXBoard (🥉20 · ⭐ 320 · 💀) - Logging MXNet data for visualization in TensorBoard.
Apache-2 - keepsake (🥉19 · ⭐ 1.6K · 💀) - Version control for machine learning.
Apache-2 - lore (🥉19 · ⭐ 1.6K · 💀) - Lore makes machine learning approachable for Software Engineers and..
MIT - datmo (🥉17 · ⭐ 340 · 💀) - Open source production model management tool for data scientists.
MIT - chitra (🥉16 · ⭐ 220) - A multi-functional library for full-stack Deep Learning. Simplifies..
Apache-2 - steppy (🥉16 · ⭐ 140 · 💀) - Lightweight, Python library for fast and reproducible experimentation.
MIT - CometML (🥉13) - Supercharging Machine Learning.
❗Unlicensed - ModelChimp (🥉12 · ⭐ 120 · 💀) - Experiment tracking for machine and deep learning projects.
BSD-2 - traintool (🥉9 · ⭐ 12 · 💀) - Train off-the-shelf machine learning models in one..
Apache-2
Model Serialization & Deployment
Libraries to serialize models to files, convert between a variety of model formats, and optimize models for deployment.
TorchServe (🥈34 · ⭐ 3.8K) - Serve, optimize and scale PyTorch models in production. Apache-2
-
GitHub (👨💻 180 · 🔀 790 · 📥 5.5K · 📦 580 · 📋 1.5K - 22% open · ⏱️ 04.01.2024):
git clone https://github.com/pytorch/serve -
PyPi (📥 32K / month · 📦 16 · ⏱️ 12.10.2023):
pip install torchserve -
Conda (📥 140K · ⏱️ 12.10.2023):
conda install -c pytorch torchserve -
Docker Hub (📥 1.2M · ⭐ 22 · ⏱️ 12.10.2023):
docker pull pytorch/torchserve
Core ML Tools (🥈33 · ⭐ 3.8K) - Core ML tools contain supporting tools for Core ML model.. BSD-3
huggingface_hub (🥈31 · ⭐ 1.4K) - The official Python client for the Huggingface Hub. Apache-2
Hummingbird (🥉24 · ⭐ 3.3K) - Hummingbird compiles trained ML models into tensor computation for.. MIT
Show 9 hidden projects...
- m2cgen (🥈26 · ⭐ 2.7K · 💀) - Transform ML models into a native code (Java, C, Python, Go,..
MIT - mmdnn (🥉25 · ⭐ 5.8K · 💀) - MMdnn is a set of tools to help users inter-operate among different deep..
MIT - sklearn-porter (🥉23 · ⭐ 1.3K · 💀) - Transpile trained scikit-learn estimators to C, Java,..
BSD-3 - Larq Compute Engine (🥉20 · ⭐ 230) - Highly optimized inference engine for Binarized..
Apache-2 - pytorch2keras (🥉19 · ⭐ 840 · 💀) - PyTorch to Keras model convertor.
MIT - modelkit (🥉16 · ⭐ 150) - Toolkit for developing and maintaining ML models.
MIT - OMLT (🥉15 · ⭐ 230) - Represent trained machine learning models as Pyomo optimization..
❗Unlicensed - ml-ane-transformers (🥉14 · ⭐ 2.4K · 💀) - Reference implementation of the Transformer..
❗Unlicensed - backprop (🥉10 · ⭐ 240 · 💀) - Backprop makes it simple to use, finetune, and deploy state-..
❗Unlicensed
Model Interpretability
Libraries to visualize, explain, debug, evaluate, and interpret machine learning models.
shap (🥇41 · ⭐ 21K) - A game theoretic approach to explain the output of any machine learning model. MIT
InterpretML (🥇33 · ⭐ 5.9K) - Fit interpretable models. Explain blackbox machine learning. MIT
evaluate (🥇32 · ⭐ 1.7K) - Evaluate: A library for easily evaluating machine learning models.. Apache-2
explainerdashboard (🥈31 · ⭐ 2.1K) - Quickly build Explainable AI dashboards that show the inner.. MIT
dtreeviz (🥈29 · ⭐ 2.7K) - A python library for decision tree visualization and model interpretation. MIT
responsible-ai-widgets (🥈29 · ⭐ 1.1K) - Responsible AI Toolbox is a suite of tools providing.. MIT
Model Analysis (🥈27 · ⭐ 1.2K) - Model analysis tools for TensorFlow. Apache-2
yellowbrick (🥈26 · ⭐ 4.1K) - Visual analysis and diagnostic tools to facilitate machine.. Apache-2
LIT (🥈26 · ⭐ 3.3K) - The Learning Interpretability Tool: Interactively analyze ML models to.. Apache-2
Fairness 360 (🥈26 · ⭐ 2.2K) - A comprehensive set of fairness metrics for datasets and.. Apache-2
iNNvestigate (🥉25 · ⭐ 1.2K) - A toolbox to iNNvestigate neural networks predictions!. BSD-2
Explainability 360 (🥉24 · ⭐ 1.5K) - Interpretability and explainability of data and.. Apache-2
What-If Tool (🥉20 · ⭐ 860 · 💤) - Source code/webpage/demos for the What-If Tool. Apache-2
model-card-toolkit (🥉20 · ⭐ 400) - A toolkit that streamlines and automates the generation.. Apache-2
fairness-indicators (🥉19 · ⭐ 330) - Tensorflows Fairness Evaluation and Visualization.. Apache-2
FlashTorch (🥉16 · ⭐ 720) - Visualization toolkit for neural networks in PyTorch! Demo --. MIT
interpret-text (🥉13 · ⭐ 390) - A library that incorporates state-of-the-art explainers for.. MIT
Show 20 hidden projects...
- Lime (🥇32 · ⭐ 11K · 💀) - Lime: Explaining the predictions of any machine learning classifier.
BSD-2 - Deep Checks (🥈28 · ⭐ 3.2K) - Deepchecks: Tests for Continuous Validation of ML Models &..
❗Unlicensed - eli5 (🥈27 · ⭐ 2.7K · 💀) - A library for debugging/inspecting machine learning classifiers and..
MIT - scikit-plot (🥈27 · ⭐ 2.4K · 💀) - An intuitive library to add plotting functionality to..
MIT - Lucid (🥉25 · ⭐ 4.6K · 💀) - A collection of infrastructure and tools for research in..
Apache-2 - DALEX (🥉25 · ⭐ 1.3K) - moDel Agnostic Language for Exploration and eXplanation.
❗️GPL-3.0 - keras-vis (🥉24 · ⭐ 3K · 💀) - Neural network visualization toolkit for keras.
MIT - random-forest-importances (🥉23 · ⭐ 580 · 💀) - Code to compute permutation and drop-column..
MIT - tf-explain (🥉22 · ⭐ 1K · 💀) - Interpretability Methods for tf.keras models with Tensorflow..
MIT - deeplift (🥉21 · ⭐ 780 · 💀) - Public facing deeplift repo.
MIT - Quantus (🥉21 · ⭐ 450) - Quantus is an eXplainable AI toolkit for responsible evaluation..
❗Unlicensed - TreeInterpreter (🥉19 · ⭐ 730 · 💀) - Package for interpreting scikit-learns decision tree..
BSD-3 - tcav (🥉18 · ⭐ 600 · 💀) - Code for the TCAV ML interpretability project.
Apache-2 - XAI (🥉16 · ⭐ 980 · 💀) - XAI - An eXplainability toolbox for machine learning.
MIT - Anchor (🥉14 · ⭐ 770 · 💀) - Code for High-Precision Model-Agnostic Explanations paper.
BSD-2 - ExplainX.ai (🥉14 · ⭐ 370 · 💀) - Explainable AI framework for data scientists. Explain & debug any..
MIT - contextual-ai (🥉12 · ⭐ 84 · 💀) - Contextual AI adds explainability to different stages of..
Apache-2 - Attribution Priors (🥉11 · ⭐ 120 · 💀) - Tools for training explainable models using..
MIT - bias-detector (🥉10 · ⭐ 42 · 💀) -
MIT - sklearn-evaluation (🥉10 · ⭐ 3 · 💤) - Machine learning model evaluation made easy: plots,..
MIT
Vector Similarity Search (ANN)
Libraries for Approximate Nearest Neighbor Search and Vector Indexing/Similarity Search.
🔗 ANN Benchmarks ( ⭐ 4.3K) - Benchmarks of approximate nearest neighbor libraries in Python.
Milvus (🥇41 · ⭐ 25K) - A cloud-native vector database, storage for next generation AI.. Apache-2
-
GitHub (👨💻 260 · 🔀 2.5K · 📥 63K · 📋 9.9K - 6% open · ⏱️ 04.01.2024):
git clone https://github.com/milvus-io/milvus -
PyPi (📥 380K / month · 📦 80 · ⏱️ 03.01.2024):
pip install pymilvus -
Docker Hub (📥 10M · ⭐ 38 · ⏱️ 04.01.2024):
docker pull milvusdb/milvus
Faiss (🥇38 · ⭐ 26K) - A library for efficient similarity search and clustering of dense vectors. MIT
Annoy (🥈33 · ⭐ 12K) - Approximate Nearest Neighbors in C++/Python optimized for memory usage.. Apache-2
hnswlib (🥈33 · ⭐ 3.8K) - Header-only C++/python library for fast approximate nearest neighbors. Apache-2
PyNNDescent (🥉29 · ⭐ 820) - A Python nearest neighbor descent for approximate nearest neighbors. BSD-2
USearch (🥉28 · ⭐ 1.2K) - Fast Open-Source Search & Clustering engine for Vectors & Strings in.. Apache-2
-
GitHub (👨💻 26 · 🔀 60 · 📥 840 · 📦 40 · 📋 65 - 23% open · ⏱️ 26.11.2023):
git clone https://github.com/unum-cloud/usearch -
PyPi (📥 42K / month · 📦 1 · ⏱️ 26.11.2023):
pip install usearch -
npm (📥 5.1K / month · 📦 4 · ⏱️ 26.11.2023):
npm install usearch -
Docker Hub (📥 43 · ⭐ 1 · ⏱️ 26.11.2023):
docker pull unum/usearch
NearPy (🥉20 · ⭐ 750 · 💤) - Python framework for fast (approximated) nearest neighbour search in.. MIT
N2 (🥉19 · ⭐ 560 · 💤) - TOROS N2 - lightweight approximate Nearest Neighbor library which runs.. Apache-2
Show 3 hidden projects...
- NMSLIB (🥈31 · ⭐ 3.2K · 💀) - Non-Metric Space Library (NMSLIB): An efficient similarity search..
Apache-2 - Magnitude (🥉23 · ⭐ 1.6K · 💀) - A fast, efficient universal vector embedding utility package.
MIT - PySparNN (🥉11 · ⭐ 910 · 💀) - Approximate Nearest Neighbor Search for Sparse Data in Python!.
BSD-3
Probabilistics & Statistics
Libraries providing capabilities for probabilistic programming/reasoning, bayesian inference, gaussian processes, or statistics.
tensorflow-probability (🥇37 · ⭐ 4K) - Probabilistic reasoning and statistical analysis in.. Apache-2
SALib (🥈30 · ⭐ 770) - Sensitivity Analysis Library in Python. Contains Sobol, Morris, FAST, and.. MIT
pomegranate (🥉29 · ⭐ 3.2K) - Fast, flexible and easy to use probabilistic modelling in Python. MIT
scikit-posthocs (🥉25 · ⭐ 310) - Multiple Pairwise Comparisons (Post Hoc) Tests in Python. MIT
Orbit (🥉24 · ⭐ 1.8K) - A Python package for Bayesian forecasting with object-oriented design.. Apache-2
Baal (🥉22 · ⭐ 810) - Library to enable Bayesian active learning in your research or labeling.. Apache-2
Show 8 hidden projects...
- filterpy (🥈32 · ⭐ 3K · 💀) - Python Kalman filtering and optimal estimation library. Implements..
MIT - pandas-ta (🥈30 · ⭐ 4.3K · 💀) - Technical Analysis Indicators - Pandas TA is an easy to use..
MIT - pingouin (🥈30 · ⭐ 1.5K) - Statistical package in Python based on Pandas.
❗️GPL-3.0 - PyStan (🥉29 · ⭐ 290) - PyStan, a Python interface to Stan, a platform for statistical modeling...
ISC - Edward (🥉27 · ⭐ 4.8K · 💀) - A probabilistic programming language in TensorFlow. Deep..
Apache-2 - Funsor (🥉21 · ⭐ 220) - Functional tensors for probabilistic programming.
Apache-2 - pyhsmm (🥉20 · ⭐ 540 · 💀) - Bayesian inference in HSMMs and HMMs.
MIT - ZhuSuan (🥉15 · ⭐ 2.2K · 💀) - A probabilistic programming library for Bayesian deep learning,..
MIT
Adversarial Robustness
Libraries for testing the robustness of machine learning models against attacks with adversarial/malicious examples.
ART (🥇34 · ⭐ 4.2K) - Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning.. MIT
-
GitHub (👨💻 130 · 🔀 1.1K · 📦 470 · 📋 880 - 15% open · ⏱️ 27.12.2023):
git clone https://github.com/Trusted-AI/adversarial-robustness-toolbox -
PyPi (📥 22K / month · 📦 11 · ⏱️ 27.12.2023):
pip install adversarial-robustness-toolbox -
Conda (📥 35K · ⏱️ 27.12.2023):
conda install -c conda-forge adversarial-robustness-toolbox
TextAttack (🥈30 · ⭐ 2.6K) - TextAttack is a Python framework for adversarial attacks, data.. MIT
CleverHans (🥈29 · ⭐ 6K · 💤) - An adversarial example library for constructing attacks,.. MIT
Foolbox (🥈27 · ⭐ 2.6K) - A Python toolbox to create adversarial examples that fool neural networks.. MIT
Show 5 hidden projects...
- advertorch (🥉22 · ⭐ 1.2K · 💀) - A Toolbox for Adversarial Robustness Research.
❗️GPL-3.0 - AdvBox (🥉18 · ⭐ 1.4K · 💀) - Advbox is a toolbox to generate adversarial examples that fool..
Apache-2 - robustness (🥉18 · ⭐ 850 · 💀) - A library for experimenting with, training and evaluating neural..
MIT - textflint (🥉16 · ⭐ 620 · 💀) - Unified Multilingual Robustness Evaluation Toolkit for..
❗️GPL-3.0 - Adversary (🥉15 · ⭐ 390 · 💀) - Tool to generate adversarial text examples and test machine..
MIT
GPU & Accelerator Utilities
Libraries that require and make use of CUDA/GPU or other accelerator hardware capabilities to optimize machine learning tasks.
optimum (🥇34 · ⭐ 1.9K) - Accelerate training and inference of Transformers and Diffusers with.. Apache-2
CuPy (🥉26 · ⭐ 7.4K · 📉) - NumPy & SciPy for GPU. MIT
-
GitHub (👨💻 300 · 🔀 720):
git clone https://github.com/cupy/cupy -
PyPi (📥 20K / month · 📦 210 · ⏱️ 07.12.2023):
pip install cupy -
Conda (📥 3.2M · ⏱️ 07.12.2023):
conda install -c conda-forge cupy -
Docker Hub (📥 58K · ⭐ 11 · ⏱️ 07.12.2023):
docker pull cupy/cupy
DALI (🥉25 · ⭐ 4.7K) - A GPU-accelerated library containing highly optimized building blocks.. Apache-2
-
GitHub (👨💻 88 · 🔀 600 · 📋 1.6K - 19% open · ⏱️ 03.01.2024):
git clone https://github.com/NVIDIA/DALI
scikit-cuda (🥉23 · ⭐ 960) - Python interface to GPU-powered libraries. BSD-3
Vulkan Kompute (🥉22 · ⭐ 1.3K) - General purpose GPU compute framework built on Vulkan to.. Apache-2
cuSignal (🥉17 · ⭐ 700) - GPU accelerated signal processing. Apache-2
-
GitHub (👨💻 46 · 🔀 120 · 📋 160 - 16% open · ⏱️ 21.09.2023):
git clone https://github.com/rapidsai/cusignal
Show 6 hidden projects...
- GPUtil (🥉24 · ⭐ 1K · 💀) - A Python module for getting the GPU status from NVIDA GPUs using nvidia-..
MIT - py3nvml (🥉22 · ⭐ 230 · 💀) - Python 3 Bindings for NVML library. Get NVIDIA GPU status inside..
BSD-3 - BlazingSQL (🥉20 · ⭐ 1.9K · 💀) - BlazingSQL is a lightweight, GPU accelerated, SQL engine for..
Apache-2 - ipyexperiments (🥉18 · ⭐ 180) - Automatic GPU+CPU memory profiling, re-use and memory..
Apache-2 - nvidia-ml-py3 (🥉18 · ⭐ 120 · 💀) - Python 3 Bindings for the NVIDIA Management Library.
BSD-3 - SpeedTorch (🥉15 · ⭐ 670 · 💀) - Library for faster pinned CPU - GPU transfer in Pytorch.
MIT
Tensorflow Utilities
Libraries that extend TensorFlow with additional capabilities.
TensorFlow Datasets (🥇38 · ⭐ 4.1K) - TFDS is a collection of datasets ready to use with.. Apache-2
tensor2tensor (🥈32 · ⭐ 14K · 💤) - Library of deep learning models and datasets designed.. Apache-2
TensorFlow Transform (🥈31 · ⭐ 980) - Input pipeline framework. Apache-2
TF Model Optimization (🥈30 · ⭐ 1.4K) - A toolkit to optimize ML models for deployment for.. Apache-2
tensorflow-hub (🥈29 · ⭐ 3.4K · 📉) - A library for transfer learning by reusing parts of.. Apache-2
TensorFlow I/O (🥈29 · ⭐ 680) - Dataset, streaming, and file system extensions.. Apache-2
Neural Structured Learning (🥉25 · ⭐ 970) - Training neural models with structured signals. Apache-2
TF Compression (🥉23 · ⭐ 790) - Data compression in TensorFlow. Apache-2
TensorFlow Cloud (🥉23 · ⭐ 360) - The TensorFlow Cloud repository provides APIs that.. Apache-2
Show 5 hidden projects...
- efficientnet (🥉26 · ⭐ 2K · 💀) - Implementation of EfficientNet model. Keras and..
Apache-2 - Keras-Preprocessing (🥉22 · ⭐ 1K · 💀) - Utilities for working with image data, text data, and..
❗Unlicensed - Saliency (🥉21 · ⭐ 920 · 💀) - Framework-agnostic implementation for state-of-the-art..
Apache-2 - TensorNets (🥉20 · ⭐ 1K · 💀) - High level network definitions with pre-trained weights in..
MIT - tffm (🥉16 · ⭐ 780 · 💀) - TensorFlow implementation of an arbitrary order Factorization Machine.
MIT
Jax Utilities
Libraries that extend Jax with additional capabilities.
Show 1 hidden projects...
- jaxdf (🥉14 · ⭐ 100) - A JAX-based research framework for writing differentiable..
❗️LGPL-3.0
Sklearn Utilities
Libraries that extend scikit-learn with additional capabilities.
scikit-learn-intelex (🥇35 · ⭐ 1.1K) - Intel(R) Extension for Scikit-learn is a seamless way.. Apache-2
imbalanced-learn (🥇34 · ⭐ 6.6K) - A Python Package to Tackle the Curse of Imbalanced.. MIT
category_encoders (🥈33 · ⭐ 2.3K) - A library of sklearn compatible categorical variable.. BSD-3
scikit-lego (🥈27 · ⭐ 1.1K) - Extra blocks for scikit-learn pipelines. MIT
scikit-multilearn (🥈26 · ⭐ 880 · 💤) - A scikit-learn based module for multi-label et. al... BSD-2
scikit-opt (🥉24 · ⭐ 4.7K) - Genetic Algorithm, Particle Swarm Optimization, Simulated.. MIT
Show 11 hidden projects...
- MLxtend (🥈31 · ⭐ 4.7K) - A library of extension and helper modules for Pythons data..
❗Unlicensed - scikit-survival (🥈27 · ⭐ 1K) - Survival analysis built on top of scikit-learn.
❗️GPL-3.0 - fancyimpute (🥈26 · ⭐ 1.2K · 💀) - Multivariate imputation and matrix completion..
Apache-2 - sklearn-crfsuite (🥈26 · ⭐ 420 · 💀) - scikit-learn inspired API for CRFsuite.
MIT - iterative-stratification (🥉21 · ⭐ 800 · 💀) - scikit-learn cross validators for iterative..
BSD-3 - skope-rules (🥉19 · ⭐ 570 · 💤) - machine learning with logical rules in Python.
❗Unlicensed - celer (🥉18 · ⭐ 180) - Fast solver for L1-type problems: Lasso, sparse Logisitic regression,..
BSD-3 - sklearn-contrib-lightning (🥉17 · ⭐ 1.7K · 💀) - Large-scale linear classification, regression and..
❗Unlicensed - skggm (🥉17 · ⭐ 230 · 💤) - Scikit-learn compatible estimation of general graphical models.
MIT - scikit-tda (🥉16 · ⭐ 460 · 💀) - Topological Data Analysis for Python.
❗Unlicensed - dabl (🥉14 · ⭐ 130 · 💤) - Data Analysis Baseline Library.
BSD-3
Pytorch Utilities
Libraries that extend Pytorch with additional capabilities.
accelerate (🥇39 · ⭐ 6.3K) - A simple way to train and use PyTorch models with multi-.. Apache-2
PML (🥇33 · ⭐ 5.6K) - The easiest way to use deep metric learning in your application. Modular,.. MIT
-
GitHub (👨💻 40 · 🔀 640 · 📦 1.1K · 📋 480 - 11% open · ⏱️ 16.12.2023):
git clone https://github.com/KevinMusgrave/pytorch-metric-learning -
PyPi (📥 220K / month · 📦 30 · ⏱️ 16.12.2023):
pip install pytorch-metric-learning -
Conda (📥 11K · ⏱️ 16.06.2023):
conda install -c metric-learning pytorch-metric-learning
tinygrad (🥇31 · ⭐ 22K) - You like pytorch? You like micrograd? You love tinygrad!. MIT
-
GitHub (👨💻 260 · 🔀 2.4K · 📦 36 · 📋 460 - 16% open · ⏱️ 04.01.2024):
git clone https://github.com/geohot/tinygrad
pytorch-optimizer (🥇29 · ⭐ 2.9K · 💤) - torch-optimizer -- collection of optimizers for.. Apache-2
torchdiffeq (🥈28 · ⭐ 5K) - Differentiable ODE solvers with full GPU support and O(1)-memory.. MIT
lightning-flash (🥈27 · ⭐ 1.7K) - Your PyTorch AI Factory - Flash enables you to easily.. Apache-2
torch-scatter (🥈27 · ⭐ 1.4K · 📈) - PyTorch Extension Library of Optimized Scatter Operations. MIT
PyTorch Sparse (🥈24 · ⭐ 910) - PyTorch Extension Library of Optimized Autograd Sparse.. MIT
Pytorch Toolbelt (🥉23 · ⭐ 1.5K) - PyTorch extensions for fast R&D prototyping and Kaggle.. MIT
reformer-pytorch (🥉20 · ⭐ 2K · 💤) - Reformer, the efficient Transformer, in Pytorch. MIT
Show 19 hidden projects...
- pretrainedmodels (🥇29 · ⭐ 8.9K · 💀) - Pretrained ConvNets for pytorch: NASNet, ResNeXt,..
BSD-3 - EfficientNet-PyTorch (🥈27 · ⭐ 7.6K · 💀) - A PyTorch implementation of EfficientNet and..
Apache-2 - pytorch-summary (🥈27 · ⭐ 3.9K · 💀) - Model summary in PyTorch similar to
model.summary()..MIT - SRU (🥉23 · ⭐ 2.1K · 💀) - Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755).
MIT - Torchmeta (🥉23 · ⭐ 1.9K · 💀) - A collection of extensions and data-loaders for few-shot..
MIT - Higher (🥉23 · ⭐ 1.6K · 💀) - higher is a pytorch library allowing users to obtain higher..
Apache-2 - EfficientNets (🥉23 · ⭐ 1.6K · 💀) - Pretrained EfficientNet, EfficientNet-Lite, MixNet,..
Apache-2 - Antialiased CNNs (🥉21 · ⭐ 1.6K · 💀) - pip install antialiased-cnns to improve stability and..
❗️CC BY-NC-SA 4.0 - AdaBound (🥉20 · ⭐ 2.9K · 💀) - An optimizer that trains as fast as Adam and as good as SGD.
Apache-2 - Lambda Networks (🥉20 · ⭐ 1.5K · 💀) - Implementation of LambdaNetworks, a new approach to..
MIT - pytorchviz (🥉19 · ⭐ 2.9K · 💀) - A small package to create visualizations of PyTorch execution..
MIT - Performer Pytorch (🥉19 · ⭐ 1K · 💀) - An implementation of Performer, a linear attention-..
MIT - Poutyne (🥉19 · ⭐ 560) - A simplified framework and utilities for PyTorch.
❗️LGPL-3.0 - micrograd (🥉18 · ⭐ 7K · 💀) - A tiny scalar-valued autograd engine and a neural net library..
MIT - Tez (🥉17 · ⭐ 1.2K · 💀) - Tez is a super-simple and lightweight Trainer for PyTorch. It..
Apache-2 - Torch-Struct (🥉17 · ⭐ 1.1K · 💀) - Fast, general, and tested differentiable structured..
MIT - Tensor Sensor (🥉17 · ⭐ 740 · 💀) - The goal of this library is to generate more helpful..
MIT - Pywick (🥉16 · ⭐ 400 · 💀) - High-level batteries-included neural network training library for..
MIT - TorchDrift (🥉14 · ⭐ 300 · 💀) - Drift Detection for your PyTorch Models.
Apache-2
Database Clients
Libraries for connecting to, operating, and querying databases.
🔗 best-of-python - DB Clients ( ⭐ 3.3K) - Collection of database clients for python.
Others
PyOD (🥈34 · ⭐ 7.7K) - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly.. BSD-2
anomalib (🥈28 · ⭐ 2.7K) - An anomaly detection library comprising state-of-the-art algorithms.. Apache-2
alibi-detect (🥉27 · ⭐ 2K) - Algorithms for outlier, adversarial and drift detection. Apache-2
metric-learn (🥉27 · ⭐ 1.4K) - Metric learning algorithms in Python. MIT
adapter-transformers (🥉26 · ⭐ 2.2K) - A Unified Library for Parameter-Efficient and Modular.. Apache-2 huggingface
TabPy (🥉26 · ⭐ 1.5K) - Execute Python code on the fly and display results in Tableau visualizations:. MIT
dstack (🥉25 · ⭐ 900) - dstack simplifies training, fine-tuning, and deploying generative AI.. MPL-2.0
MONAILabel (🥉24 · ⭐ 490) - MONAI Label is an intelligent open source image labeling and.. Apache-2
benchmark_VAE (🥉22 · ⭐ 1.6K) - Unifying Variational Autoencoder (VAE) implementations.. Apache-2
SUOD (🥉21 · ⭐ 360) - (MLSys 21) An Acceleration System for Large-scare Unsupervised Heterogeneous.. BSD-2
rrcf (🥉19 · ⭐ 460) - Implementation of the Robust Random Cut Forest algorithm for anomaly detection.. MIT
pymdp (🥉17 · ⭐ 340) - A Python implementation of active inference for Markov Decision Processes. MIT
NeuralCompression (🥉16 · ⭐ 430) - A collection of tools for neural compression enthusiasts. MIT
Show 22 hidden projects...
- SymPy (🥇44 · ⭐ 12K) - A computer algebra system written in pure Python.
❗Unlicensed - cleanlab (🥈30 · ⭐ 7.5K) - The standard data-centric AI package for data quality and machine..
❗️AGPL-3.0 - pyclustering (🥈29 · ⭐ 1.1K · 💀) - pyclustering is a Python, C++ data mining library.
BSD-3 - Cython BLIS (🥈29 · ⭐ 200) - Fast matrix-multiplication as a self-contained Python library no..
BSD-3 - tensorly (🥈28 · ⭐ 1.5K) - TensorLy: Tensor Learning in Python.
❗Unlicensed - minisom (🥉27 · ⭐ 1.3K) - MiniSom is a minimalistic implementation of the Self Organizing..
❗️CC-BY-3.0 - metricflow (🥉26 · ⭐ 1K) - MetricFlow allows you to define, build, and maintain metrics..
❗Unlicensed - Feature Engine (🥉24 · ⭐ 1.5K · 💀) - Feature engineering package with sklearn like functionality.
BSD-3 - AugLy (🥉23 · ⭐ 4.8K) - A data augmentations library for audio, image, text, and video.
❗Unlicensed - mlens (🥉23 · ⭐ 810 · 💀) - ML-Ensemble high performance ensemble learning.
MIT - findspark (🥉23 · ⭐ 500 · 💀) - Find pyspark to make it importable.
BSD-3 - opyrator (🥉22 · ⭐ 3K · 💀) - Turns your machine learning code into microservices with web API,..
MIT - AstroML (🥉22 · ⭐ 980 · 💀) - Machine learning, statistics, and data mining for astronomy and..
BSD-2 - apricot (🥉22 · ⭐ 480 · 💀) - apricot implements submodular optimization for the purpose of..
MIT - vecstack (🥉21 · ⭐ 680 · 💀) - Python package for stacking (machine learning technique).
❗Unlicensed - impyute (🥉21 · ⭐ 340 · 💀) - Data imputations library to preprocess datasets with missing data.
MIT - StreamAlert (🥉20 · ⭐ 2.8K · 💀) - StreamAlert is a serverless, realtime data analysis..
Apache-2 - scikit-rebate (🥉20 · ⭐ 390 · 💀) - A scikit-learn-compatible Python implementation of..
MIT - baikal (🥉18 · ⭐ 590 · 💀) - A graph-based functional API for building complex scikit-learn..
BSD-3 - pandas-ml (🥉18 · ⭐ 310 · 💀) - pandas, scikit-learn, xgboost and seaborn integration.
BSD-3 - traingenerator (🥉13 · ⭐ 1.3K · 💀) - A web app to generate template code for machine learning.
MIT - nylon (🥉10 · ⭐ 84 · 💀) - An intelligent, flexible grammar of machine learning.
MIT
Related Resources
- Papers With Code: Discover ML papers, code, and evaluation tables.
- Sotabench: Discover & compare open-source ML models.
- Google Dataset Search: Dataset search engine by Google.
- Dataset List: List of the biggest ML datasets from across the web.
- Awesome Public Datasets: A topic-centric list of open datasets.
- Best-of lists: Discover other best-of lists with awesome open-source projects on all kinds of topics.
- best-of-python-dev: A ranked list of awesome python developer tools and libraries.
- best-of-web-python: A ranked list of awesome python libraries for web development.
Contribution
Contributions are encouraged and always welcome! If you like to add or update projects, choose one of the following ways:
- Open an issue by selecting one of the provided categories from the issue page and fill in the requested information.
- Modify the projects.yaml with your additions or changes, and submit a pull request. This can also be done directly via the Github UI.
If you like to contribute to or share suggestions regarding the project metadata collection or markdown generation, please refer to the best-of-generator repository. If you like to create your own best-of list, we recommend to follow this guide.
For more information on how to add or update projects, please read the contribution guidelines. By participating in this project, you agree to abide by its Code of Conduct.
![@github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=64&v=4){kind=small}
