🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
This curated list contains 840 awesome open-source projects with a total of 2.7M stars grouped into 32 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 54 projects
- Data Visualization 49 projects
- Text Data & NLP 82 projects
- Image Data 49 projects
- Graph Data 29 projects
- Audio Data 23 projects
- Geospatial Data 22 projects
- Financial Data 23 projects
- Time Series Data 20 projects
- Medical Data 19 projects
- Optical Character Recognition 11 projects
- Data Containers & Structures 28 projects
- Data Loading & Extraction 23 projects
- Web Scraping & Crawling 1 projects
- Data Pipelines & Streaming 35 projects
- Distributed Machine Learning 26 projects
- Hyperparameter Optimization & AutoML 45 projects
- Reinforcement Learning 19 projects
- Recommender Systems 14 projects
- Privacy Machine Learning 6 projects
- Workflow & Experiment Tracking 35 projects
- Model Serialization & Conversion 11 projects
- Model Interpretability 46 projects
- Vector Similarity Search (ANN) 12 projects
- Probabilistics & Statistics 21 projects
- Adversarial Robustness 8 projects
- GPU Utilities 18 projects
- Tensorflow Utilities 13 projects
- Sklearn Utilities 17 projects
- Pytorch Utilities 27 projects
- Database Clients 1 projects
- Others 52 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
Machine Learning Frameworks
General-purpose machine learning and deep learning frameworks.
Tensorflow (🥇44 · ⭐ 160K) - An Open Source Machine Learning Framework for Everyone. Apache-2
-
GitHub (👨💻 3.5K · 🔀 84K · 📦 120K · 📋 31K - 13% open · ⏱️ 18.02.2021):
git clone https://github.com/tensorflow/tensorflow
-
PyPi (📥 3.6M / month · 📦 23K · ⏱️ 21.01.2021):
pip install tensorflow
-
Conda (📥 2.3M · ⏱️ 15.07.2020):
conda install -c conda-forge tensorflow
-
Docker Hub (📥 48M · ⭐ 1.8K · ⏱️ 18.02.2021):
docker pull tensorflow/tensorflow
scikit-learn (🥇37 · ⭐ 45K) - scikit-learn: machine learning in Python. BSD-3
StatsModels (🥇36 · ⭐ 6K) - Statsmodels: statistical modeling and econometrics in Python. BSD-3
XGBoost (🥇35 · ⭐ 21K) - Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or.. Apache-2
LightGBM (🥇35 · ⭐ 12K) - A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT,.. MIT
pytorch-lightning (🥈33 · ⭐ 12K) - The lightweight PyTorch wrapper for high-performance.. Apache-2
Thinc (🥈32 · ⭐ 2.2K) - A refreshing functional take on deep learning, compatible with your favorite.. MIT
Catboost (🥈31 · ⭐ 5.7K) - A fast, scalable, high performance Gradient Boosting on Decision.. Apache-2
PaddlePaddle (🥈30 · ⭐ 14K) - PArallel Distributed Deep LEarning: Machine Learning.. Apache-2
Vowpal Wabbit (🥈30 · ⭐ 7.4K) - Vowpal Wabbit is a machine learning system which pushes the.. BSD-3
Turi Create (🥈29 · ⭐ 10K) - Turi Create simplifies the development of custom machine learning.. BSD-3
tensorpack (🥉28 · ⭐ 5.9K) - A Neural Net Training Interface on TensorFlow, with focus.. Apache-2
Jina (🥉27 · ⭐ 2.3K) - An easier way to build neural search on the cloud. Apache-2
-
GitHub (👨💻 86 · 🔀 360 · 📦 46 · 📋 650 - 7% open · ⏱️ 18.02.2021):
git clone https://github.com/jina-ai/jina
-
PyPi (📥 3.4K / month · ⏱️ 18.02.2021):
pip install jina
-
Docker Hub (📥 130K · ⏱️ 18.02.2021):
docker pull jinaai/jina
Flax (🥉27 · ⭐ 1.5K) - Flax is a neural network ecosystem for JAX that is designed for.. Apache-2
jax
CNTK (🥉26 · ⭐ 17K · 💤) - Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit. MIT
Neural Network Libraries (🥉25 · ⭐ 2.4K) - Neural Network Libraries. Apache-2
xLearn (🥉24 · ⭐ 2.8K · 💤) - High performance, easy-to-use, and scalable machine learning (ML).. Apache-2
tensorflow-upstream (🥉24 · ⭐ 540) - TensorFlow ROCm port. Apache-2
SHOGUN (🥉23 · ⭐ 2.8K) - Unified and efficient Machine Learning. BSD-3
-
GitHub (👨💻 250 · 🔀 1K · 📋 1.6K - 33% open · ⏱️ 08.12.2020):
git clone https://github.com/shogun-toolbox/shogun
-
Conda (📥 92K · ⏱️ 25.06.2018):
conda install -c conda-forge shogun
-
Docker Hub (📥 1.4K · ⭐ 1 · ⏱️ 31.01.2019):
docker pull shogun/shogun
mace (🥉21 · ⭐ 4.3K) - MACE is a deep learning inference framework optimized for mobile.. Apache-2
-
GitHub (👨💻 56 · 🔀 760 · 📥 1.3K · 📋 620 - 6% open · ⏱️ 18.02.2021):
git clone https://github.com/XiaoMi/mace
Neural Tangents (🥉21 · ⭐ 1.3K) - Fast and Easy Infinite Neural Networks in Python. Apache-2
ThunderSVM (🥉20 · ⭐ 1.3K) - ThunderSVM: A Fast SVM Library on GPUs and CPUs. Apache-2
Haiku (🥉20 · ⭐ 960) - JAX-based neural network library. Apache-2
-
GitHub (👨💻 37 · 🔀 67 · 📦 62 · 📋 69 - 28% open · ⏱️ 18.02.2021):
git clone https://github.com/deepmind/dm-haiku
Objax (🥉19 · ⭐ 570 · 🐣) - Objax is a machine learning framework that provides an Object.. Apache-2
jax
Torchbearer (🥉18 · ⭐ 580 · 💤) - torchbearer: A model fitting library for PyTorch. MIT
ThunderGBM (🥉16 · ⭐ 580) - ThunderGBM: Fast GBDTs and Random Forests on GPUs. Apache-2
NeoML (🥉13 · ⭐ 560) - Machine learning framework for both deep learning and traditional.. Apache-2
-
GitHub (👨💻 18 · 🔀 80 · 📋 29 - 55% open · ⏱️ 18.02.2021):
git clone https://github.com/neoml-lib/neoml
Show 7 hidden projects...
- dlib (🥈32 · ⭐ 9.9K) - A toolkit for making real world machine learning and data analysis..
❗️BSL-1.0
- NuPIC (🥉24 · ⭐ 6.2K · 💀) - Numenta Platform for Intelligent Computing is an implementation..
❗️AGPL-3.0
- Lasagne (🥉23 · ⭐ 3.8K · 💀) - Lightweight library to build and train neural networks in Theano.
MIT
- neon (🥉22 · ⭐ 3.8K · 💀) - Intel Nervana reference deep learning framework committed to best..
Apache-2
- MindsDB (🥉20 · ⭐ 3.2K) - Predictive AI layer for existing databases.
❗️GPL-3.0
- NeuPy (🥉20 · ⭐ 660 · 💀) - NeuPy is a Tensorflow based python library for prototyping and building..
MIT
- StarSpace (🥉13 · ⭐ 3.5K · 💀) - Learning embeddings for classification, retrieval and ranking.
MIT
Data Visualization
General-purpose and task-specific data visualization libraries.
Matplotlib (🥇41 · ⭐ 13K) - matplotlib: plotting with Python. Python-2.0
Plotly (🥇35 · ⭐ 8.9K) - The interactive graphing library for Python (includes Plotly Express). MIT
-
GitHub (👨💻 160 · 🔀 1.8K · 📦 5 · 📋 1.9K - 43% open · ⏱️ 14.01.2021):
git clone https://github.com/plotly/plotly.py
-
PyPi (📥 1.8M / month · 📦 5K · ⏱️ 12.01.2021):
pip install plotly
-
Conda (📥 1.2M · ⏱️ 12.01.2021):
conda install -c conda-forge plotly
-
NPM (📥 250K / month · 📦 4 · ⏱️ 12.01.2021):
npm install plotlywidget
dash (🥇34 · ⭐ 14K) - Analytical Web Apps for Python, R, Julia, and Jupyter. No JavaScript Required. MIT
bqplot (🥈30 · ⭐ 3K) - Plotting library for IPython/Jupyter notebooks. Apache-2
-
GitHub (👨💻 51 · 🔀 410 · 📦 1.2K · 📋 510 - 37% open · ⏱️ 18.02.2021):
git clone https://github.com/bqplot/bqplot
-
PyPi (📥 14K / month · 📦 110 · ⏱️ 13.02.2021):
pip install bqplot
-
Conda (📥 490K · ⏱️ 13.02.2021):
conda install -c conda-forge bqplot
-
NPM (📥 160K / month · 📦 10 · ⏱️ 14.01.2021):
npm install bqplot
pandas-profiling (🥈29 · ⭐ 6.8K) - Create HTML profiling reports from pandas DataFrame.. MIT
HoloViews (🥈29 · ⭐ 1.8K) - With Holoviews, your data visualizes itself. BSD-3
-
GitHub (👨💻 100 · 🔀 300 · 📋 2.5K - 27% open · ⏱️ 18.02.2021):
git clone https://github.com/holoviz/holoviews
-
PyPi (📥 53K / month · 📦 170 · ⏱️ 17.02.2021):
pip install holoviews
-
Conda (📥 420K · ⏱️ 28.12.2020):
conda install -c conda-forge holoviews
-
NPM (📥 7.4K / month · ⏱️ 24.05.2020):
npm install @pyviz/jupyterlab_pyviz
datashader (🥈28 · ⭐ 2.4K) - Quickly and accurately render even the largest data. BSD-3
data-validation (🥈27 · ⭐ 520) - Library for exploring and validating machine learning.. Apache-2
Perspective (🥈26 · ⭐ 3.2K) - Streaming pivot visualization via WebAssembly. Apache-2
Facets Overview (🥉25 · ⭐ 6.5K) - Visualizations for machine learning datasets. Apache-2
Chartify (🥉25 · ⭐ 2.8K) - Python library that makes it easy for data scientists to create.. Apache-2
HyperTools (🥉25 · ⭐ 1.6K) - A Python toolbox for gaining geometric insights into high-dimensional.. MIT
hvPlot (🥉25 · ⭐ 350) - A high-level plotting API for pandas, dask, xarray, and networkx built on.. BSD-3
pythreejs (🥉24 · ⭐ 700) - A Jupyter - Three.js bridge. BSD-3
-
GitHub (👨💻 26 · 🔀 160 · 📦 15 · 📋 200 - 30% open · ⏱️ 15.02.2021):
git clone https://github.com/jupyter-widgets/pythreejs
-
PyPi (📥 5.2K / month · 📦 13 · ⏱️ 09.10.2020):
pip install pythreejs
-
Conda (📥 270K · ⏱️ 12.10.2020):
conda install -c conda-forge pythreejs
-
NPM (📥 6.4K / month · 📦 8 · ⏱️ 19.03.2020):
npm install jupyter-threejs
Multicore-TSNE (🥉23 · ⭐ 1.5K) - Parallel t-SNE implementation with Python and Torch.. BSD-3
python-ternary (🥉23 · ⭐ 390) - Ternary plotting library for python with matplotlib. MIT
D-Tale (🥉22 · ⭐ 2.1K) - Visualizer for pandas data structures. ❗️LGPL-2.1
Pandas-Bokeh (🥉22 · ⭐ 610) - Bokeh Plotting Backend for Pandas and GeoPandas. MIT
Sweetviz (🥉19 · ⭐ 1.2K) - Visualize and compare datasets, target values and associations, with one.. MIT
animatplot (🥉19 · ⭐ 360) - A python package for animating plots build on matplotlib. MIT
AutoViz (🥉19 · ⭐ 300) - Automatically Visualize any dataset, any size with a single line of.. Apache-2
data-describe (🥉14 · ⭐ 250 · ➕) - datadescribe: Pythonic EDA Accelerator for Data Science. Apache-2
Show 6 hidden projects...
- plotnine (🥈27 · ⭐ 2.6K) - A grammar of graphics for Python.
❗️GPL-2.0
- PDPbox (🥉23 · ⭐ 530 · 💀) - python partial dependence plot toolbox.
MIT
- pivottablejs (🥉19 · ⭐ 420 · 💀) - Dragndrop Pivot Tables and Charts for Jupyter/IPython..
MIT
- ivis (🥉18 · ⭐ 220) - Dimensionality reduction in very large datasets using Siamese..
❗️GPL-2.0
- pdvega (🥉16 · ⭐ 340 · 💀) - Interactive plotting for Pandas using Vega-Lite.
MIT
- nptsne (🥉14 · ⭐ 24) - nptsne is a numpy compatible python binary package that offers a number..
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 (🥇36 · ⭐ 41K) - Transformers: State-of-the-art Natural Language.. Apache-2
gensim (🥇35 · ⭐ 12K) - Topic Modelling for Humans. ❗️LGPL-2.1
nltk (🥇34 · ⭐ 9.6K) - Suite of libraries and programs for symbolic and statistical natural.. Apache-2
ChatterBot (🥇31 · ⭐ 11K) - ChatterBot is a machine learning, conversational dialog engine for.. BSD-3
sentencepiece (🥇31 · ⭐ 4.8K) - Unsupervised text tokenizer for Neural Network-based text.. Apache-2
flair (🥇30 · ⭐ 10K) - A very simple framework for state-of-the-art Natural Language Processing.. MIT
snowballstemmer (🥇30 · ⭐ 470) - Snowball compiler and stemming algorithms. BSD-3
TextBlob (🥈29 · ⭐ 7.5K) - Simple, Pythonic, text processing--Sentiment analysis, part-of-speech.. MIT
Tokenizers (🥈28 · ⭐ 4.3K) - Fast State-of-the-Art Tokenizers optimized for Research and.. Apache-2
sentence-transformers (🥈28 · ⭐ 4.2K) - Sentence Embeddings with BERT & XLNet. Apache-2
phonenumbers (🥈28 · ⭐ 2.6K) - Python port of Google's libphonenumber. Apache-2
inflect (🥈28 · ⭐ 480) - Correctly generate plurals, ordinals, indefinite articles; convert numbers.. MIT
DeepPavlov (🥈26 · ⭐ 5K) - An open source library for deep learning end-to-end dialog.. Apache-2
TextDistance (🥈26 · ⭐ 1.9K) - Compute distance between sequences. 30+ algorithms, pure python.. MIT
TensorFlow Text (🥈26 · ⭐ 690) - Making text a first-class citizen in TensorFlow. Apache-2
vaderSentiment (🥈25 · ⭐ 2.8K · 💤) - VADER Sentiment Analysis. VADER (Valence Aware Dictionary.. MIT
pyahocorasick (🥈25 · ⭐ 580) - Python module (C extension and plain python) implementing Aho-.. BSD-3
fastNLP (🥉24 · ⭐ 2K) - fastNLP: A Modularized and Extensible NLP Framework. Currently still.. Apache-2
pytorch-nlp (🥉24 · ⭐ 1.9K) - Basic Utilities for PyTorch Natural Language Processing (NLP). BSD-3
PyTextRank (🥉24 · ⭐ 1.4K) - Python implementation of TextRank for phrase extraction and.. MIT
spacy-transformers (🥉24 · ⭐ 900) - Use pretrained transformers like BERT, XLNet and GPT-2.. MIT
spacy
Ciphey (🥉23 · ⭐ 6.3K) - Automatically decrypt encryptions without knowing the key or cipher,.. MIT
-
GitHub (👨💻 39 · 🔀 350 · 📋 220 - 21% open · ⏱️ 10.02.2021):
git clone https://github.com/Ciphey/Ciphey
-
PyPi (📥 2.1K / month · ⏱️ 02.12.2020):
pip install ciphey
-
Docker Hub (📥 8K · ⭐ 2 · ⏱️ 14.02.2021):
docker pull remnux/ciphey
textgenrnn (🥉23 · ⭐ 4.3K · 💤) - Easily train your own text-generating neural network of any.. MIT
neuralcoref (🥉23 · ⭐ 2.2K) - Fast Coreference Resolution in spaCy with Neural Networks. MIT
SciSpacy (🥉23 · ⭐ 830) - A full spaCy pipeline and models for scientific/biomedical documents. Apache-2
pySBD (🥉23 · ⭐ 280) - pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence.. MIT
scattertext (🥉22 · ⭐ 1.5K) - Beautiful visualizations of how language differs among document.. Apache-2
DeepMatcher (🥉21 · ⭐ 3.5K · 💤) - Python package for performing Entity and Text Matching using.. BSD-3
NLP Architect (🥉21 · ⭐ 2.6K) - A model library for exploring state-of-the-art deep learning.. Apache-2
gpt-2-simple (🥉21 · ⭐ 2.5K) - Python package to easily retrain OpenAI's GPT-2 text-.. MIT
Texar (🥉21 · ⭐ 2.1K · 💤) - Toolkit for Machine Learning, Natural Language Processing, and.. Apache-2
Texthero (🥉20 · ⭐ 2.1K) - Text preprocessing, representation and visualization from zero to hero. MIT
DELTA (🥉20 · ⭐ 1.4K) - DELTA is a deep learning based natural language and speech.. Apache-2
-
GitHub (👨💻 41 · 🔀 280 · 📋 77 - 11% open · ⏱️ 17.12.2020):
git clone https://github.com/Delta-ML/delta
-
PyPi (📥 5 / month · ⏱️ 27.03.2020):
pip install delta-nlp
-
Docker Hub (📥 12K · ⏱️ 17.02.2021):
docker pull zh794390558/delta
YouTokenToMe (🥉20 · ⭐ 720) - Unsupervised text tokenizer focused on computational efficiency. MIT
OpenNRE (🥉14 · ⭐ 3K) - An Open-Source Package for Neural Relation Extraction (NRE). MIT
-
GitHub (👨💻 9 · 🔀 860 · 📋 300 - 6% open · ⏱️ 24.11.2020):
git clone https://github.com/thunlp/OpenNRE
TransferNLP (🥉14 · ⭐ 290 · 💤) - NLP library designed for reproducible experimentation.. MIT
NeuralQA (🥉14 · ⭐ 180) - NeuralQA: A Usable Library for Question Answering on Large Datasets with.. MIT
Show 9 hidden projects...
- fuzzywuzzy (🥈29 · ⭐ 7.9K · 💤) - Fuzzy String Matching in Python.
❗️GPL-2.0
- langid (🥈26 · ⭐ 1.7K · 💀) - Stand-alone language identification system.
BSD-3
- polyglot (🥉24 · ⭐ 1.8K) - Multilingual text (NLP) processing toolkit.
❗️GPL-3.0
- anaGo (🥉22 · ⭐ 1.4K · 💀) - Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition,..
MIT
- stop-words (🥉21 · ⭐ 120 · 💀) - Get list of common stop words in various languages in Python.
BSD-3
- MatchZoo (🥉20 · ⭐ 3.4K · 💀) - Facilitating the design, comparison and sharing of deep..
Apache-2
- pyfasttext (🥉19 · ⭐ 230 · 💀) - Yet another Python binding for fastText.
❗️GPL-3.0
- NeuroNER (🥉17 · ⭐ 1.5K · 💀) - Named-entity recognition using neural networks. Easy-to-use and..
MIT
- ONNX-T5 (🥉14 · ⭐ 140 · 🐣) - Summarization, translation, sentiment-analysis, text-generation..
Apache-2
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.
scikit-image (🥇36 · ⭐ 4.2K) - Image processing in Python. BSD-2
torchvision (🥇35 · ⭐ 8.4K) - Datasets, Transforms and Models specific to Computer Vision. BSD-3
opencv-python (🥈30 · ⭐ 1.7K) - Automated CI toolchain to produce precompiled opencv-python,.. MIT
Face Recognition (🥈29 · ⭐ 39K) - The world's simplest facial recognition api for Python.. MIT
Albumentations (🥈28 · ⭐ 7.3K) - Fast image augmentation library and easy to use wrapper.. MIT
imageai (🥈27 · ⭐ 5.9K) - A python library built to empower developers to build applications and.. MIT
detectron2 (🥈26 · ⭐ 15K) - Detectron2 is FAIR's next-generation platform for object.. Apache-2
InsightFace (🥈26 · ⭐ 8.6K) - Face Analysis Project on MXNet. MIT
PyTorch Image Models (🥈26 · ⭐ 7.3K) - PyTorch image models, scripts, pretrained weights --.. Apache-2
-
GitHub (👨💻 29 · 🔀 1K · 📥 240K · 📦 310 · 📋 260 - 8% open · ⏱️ 16.02.2021):
git clone https://github.com/rwightman/pytorch-image-models
MMDetection (🥈25 · ⭐ 14K) - OpenMMLab Detection Toolbox and Benchmark. Apache-2
-
GitHub (👨💻 190 · 🔀 4.7K · 📦 26 · 📋 3.4K - 10% open · ⏱️ 18.02.2021):
git clone https://github.com/open-mmlab/mmdetection
facenet-pytorch (🥉24 · ⭐ 1.8K) - Pretrained Pytorch face detection (MTCNN) and recognition.. MIT
Face Alignment (🥉23 · ⭐ 4.7K) - 2D and 3D Face alignment library build using pytorch. BSD-3
segmentation_models (🥉23 · ⭐ 3K · 💤) - Segmentation models with pretrained backbones. Keras.. MIT
CellProfiler (🥉23 · ⭐ 540) - An open-source application for biological image analysis. BSD-3
Caer (🥉23 · ⭐ 430 · 🐣) - A lightweight Computer Vision library. Scale your models, not boilerplate. MIT
Image Deduplicator (🥉22 · ⭐ 3.4K) - Finding duplicate images made easy!. Apache-2
vidgear (🥉22 · ⭐ 1.6K) - High-performance cross-platform Video Processing Python framework.. Apache-2
Image Super-Resolution (🥉21 · ⭐ 2.5K) - Super-scale your images and run experiments with.. Apache-2
-
GitHub (👨💻 9 · 🔀 480 · 📦 40 · 📋 150 - 34% open · ⏱️ 11.11.2020):
git clone https://github.com/idealo/image-super-resolution
-
PyPi (📥 1.6K / month · 📦 8 · ⏱️ 08.01.2020):
pip install ISR
-
Docker Hub (📥 130 · ⏱️ 01.04.2019):
docker pull idealo/image-super-resolution-gpu
tensorflow-graphics (🥉21 · ⭐ 2.4K) - TensorFlow Graphics: Differentiable Graphics Layers.. Apache-2
Classy Vision (🥉21 · ⭐ 1.1K) - An end-to-end PyTorch framework for image and video.. MIT
image-match (🥉20 · ⭐ 2.5K) - Quickly search over billions of images. Apache-2
Torch Points 3D (🥉20 · ⭐ 1.1K) - Pytorch framework for doing deep learning on point clouds. BSD-3
vit-pytorch (🥉18 · ⭐ 2.6K · 🐣) - Implementation of Vision Transformer, a simple way to.. MIT
Norfair (🥉18 · ⭐ 900) - Lightweight Python library for adding real-time 2D object tracking to.. BSD-3
PaddleDetection (🥉17 · ⭐ 2.3K) - Object detection and instance segmentation toolkit.. Apache-2
-
GitHub (👨💻 44 · 🔀 640 · 📋 1.2K - 27% open · ⏱️ 02.02.2021):
git clone https://github.com/PaddlePaddle/PaddleDetection
DE⫶TR (🥉14 · ⭐ 6.2K) - End-to-End Object Detection with Transformers. Apache-2
-
GitHub (👨💻 19 · 🔀 930 · 📋 280 - 22% open · ⏱️ 15.11.2020):
git clone https://github.com/facebookresearch/detr
PySlowFast (🥉14 · ⭐ 3.4K) - PySlowFast: video understanding codebase from FAIR for.. Apache-2
-
GitHub (👨💻 19 · 🔀 630 · 📦 2 · 📋 350 - 46% open · ⏱️ 11.02.2021):
git clone https://github.com/facebookresearch/SlowFast
pycls (🥉14 · ⭐ 1.4K) - Codebase for Image Classification Research, written in PyTorch. MIT
-
GitHub (👨💻 9 · 🔀 150 · 📦 2 · 📋 55 - 20% open · ⏱️ 14.01.2021):
git clone https://github.com/facebookresearch/pycls
Show 4 hidden projects...
- glfw (🥈29 · ⭐ 7.3K) - A multi-platform library for OpenGL, OpenGL ES, Vulkan, window and input.
❗️Zlib
- chainercv (🥈25 · ⭐ 1.4K · 💀) - ChainerCV: a Library for Deep Learning in Computer Vision.
MIT
- Pillow-SIMD (🥉23 · ⭐ 1.5K · 💤) - The friendly PIL fork.
❗️PIL
- Luminoth (🥉21 · ⭐ 2.3K · 💀) - Deep Learning toolkit for Computer Vision.
BSD-3
Graph Data
Libraries for graph processing, clustering, embedding, and machine learning tasks.
PyTorch Geometric (🥇28 · ⭐ 10K) - Geometric Deep Learning Extension Library for PyTorch. MIT
dgl (🥇27 · ⭐ 6.7K) - Python package built to ease deep learning on graph, on top of existing.. Apache-2
StellarGraph (🥈25 · ⭐ 1.8K) - StellarGraph - Machine Learning on Graphs. Apache-2
ogb (🥈22 · ⭐ 740) - Benchmark datasets, data loaders, and evaluators for graph machine learning. MIT
torch-cluster (🥈21 · ⭐ 340) - PyTorch Extension Library of Optimized Graph Cluster.. MIT
AmpliGraph (🥈20 · ⭐ 1.4K) - Python library for Representation Learning on Knowledge.. Apache-2
graph-nets (🥉19 · ⭐ 4.8K) - Build Graph Nets in Tensorflow. Apache-2
PyTorch-BigGraph (🥉19 · ⭐ 2.7K) - Generate embeddings from large-scale graph-structured.. BSD-3
Paddle Graph Learning (🥉18 · ⭐ 900) - Paddle Graph Learning (PGL) is an efficient and.. Apache-2
pytorch_geometric_temporal (🥉16 · ⭐ 340) - A Temporal Extension Library for PyTorch Geometric. MIT
GraphEmbedding (🥉15 · ⭐ 1.8K) - Implementation and experiments of graph embedding algorithms. MIT
-
GitHub (👨💻 8 · 🔀 560 · 📦 7 · 📋 40 - 67% open · ⏱️ 18.10.2020):
git clone https://github.com/shenweichen/GraphEmbedding
OpenKE (🥉13 · ⭐ 2.4K · 💤) - An Open-Source Package for Knowledge Embedding (KE). MIT
-
GitHub (👨💻 10 · 🔀 740 · 📋 280 - 18% open · ⏱️ 08.04.2020):
git clone https://github.com/thunlp/OpenKE
GraphVite (🥉13 · ⭐ 850) - GraphVite: A General and High-performance Graph Embedding System. Apache-2
Show 8 hidden projects...
- igraph (🥇27 · ⭐ 770) - Python interface for igraph.
❗️GPL-2.0
- pygal (🥈26 · ⭐ 2.3K) - PYthon svg GrAph plotting Library.
❗️LGPL-3.0
- Karate Club (🥈21 · ⭐ 1.2K) - Karate Club: An API Oriented Open-source Python Framework for..
❗️GPL-3.0
- DeepWalk (🥉19 · ⭐ 2.2K · 💤) - DeepWalk - Deep Learning for Graphs.
❗️GPL-3.0
- Sematch (🥉16 · ⭐ 340 · 💀) - semantic similarity framework for knowledge graph.
Apache-2
- pyRDF2Vec (🥉15 · ⭐ 84) - Python Implementation and Extension of RDF2Vec.
MIT
- GraphSAGE (🥉14 · ⭐ 2.2K · 💀) - Representation learning on large graphs using stochastic..
MIT
- OpenNE (🥉14 · ⭐ 1.4K · 💀) - An Open-Source Package for Network Embedding (NE).
MIT
Audio Data
Libraries for audio analysis, manipulation, transformation, and extraction, as well as speech recognition and music generation tasks.
torchaudio (🥈28 · ⭐ 1.2K) - Data manipulation and transformation for audio signal.. BSD-2
audioread (🥈27 · ⭐ 360) - cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding.. MIT
pyAudioAnalysis (🥈26 · ⭐ 3.8K) - Python Audio Analysis Library: Feature Extraction,.. Apache-2
python-soundfile (🥈25 · ⭐ 370) - SoundFile is an audio library based on libsndfile, CFFI, and.. BSD-3
DeepSpeech (🥉24 · ⭐ 16K · 📉) - DeepSpeech is an open source embedded (offline, on-.. MPL-2.0
python_speech_features (🥉24 · ⭐ 1.8K) - This library provides common speech features for ASR.. MIT
tinytag (🥉22 · ⭐ 440) - Read music meta data and length of MP3, OGG, OPUS, MP4, M4A, FLAC, WMA and.. MIT
TTS (🥉20 · ⭐ 3.2K) - Deep learning for Text to Speech (Discussion forum:.. MPL-2.0
-
GitHub (👨💻 51 · 🔀 670 · 📥 100 · 📋 470 - 6% open · ⏱️ 12.02.2021):
git clone https://github.com/mozilla/TTS
Show 4 hidden projects...
- SpeechRecognition (🥇30 · ⭐ 5.4K · 💀) - Speech recognition module for Python, supporting..
BSD-3
- aubio (🥈26 · ⭐ 2K) - a library for audio and music analysis.
❗️GPL-3.0
- Essentia (🥉22 · ⭐ 1.7K) - C++ library for audio and music analysis, description and..
❗️AGPL-3.0
- Madmom (🥉20 · ⭐ 720 · 💀) - Python audio and music signal processing library.
BSD-3
Geospatial Data
Libraries to load, process, analyze, and write geographic data as well as libraries for spatial analysis, map visualization, and geocoding.
pydeck (🥇33 · ⭐ 8.4K) - WebGL2 powered geospatial visualization layers. MIT
-
GitHub (👨💻 150 · 🔀 1.5K · 📦 1.4K · 📋 2.1K - 4% open · ⏱️ 18.02.2021):
git clone https://github.com/visgl/deck.gl
-
PyPi (📥 77K / month · 📦 2 · ⏱️ 12.02.2021):
pip install pydeck
-
Conda (📥 15K · ⏱️ 12.02.2021):
conda install -c conda-forge pydeck
-
NPM (📥 190K / month · 📦 560 · ⏱️ 16.02.2021):
npm install deck.gl
ipyleaflet (🥉27 · ⭐ 1.1K) - A Jupyter - Leaflet.js bridge. MIT
-
GitHub (👨💻 63 · 🔀 280 · 📦 690 · 📋 380 - 34% open · ⏱️ 11.02.2021):
git clone https://github.com/jupyter-widgets/ipyleaflet
-
PyPi (📥 12K / month · 📦 98 · ⏱️ 05.01.2021):
pip install ipyleaflet
-
Conda (📥 600K · ⏱️ 16.01.2021):
conda install -c conda-forge ipyleaflet
-
NPM (📥 160K / month · 📦 2 · ⏱️ 05.01.2021):
npm install jupyter-leaflet
ArcGIS API (🥉25 · ⭐ 970) - Documentation and samples for ArcGIS API for Python. Apache-2
-
GitHub (👨💻 61 · 🔀 700 · 📋 310 - 35% open · ⏱️ 26.01.2021):
git clone https://github.com/Esri/arcgis-python-api
-
PyPi (📥 11K / month · 📦 20 · ⏱️ 27.01.2021):
pip install arcgis
-
Docker Hub (📥 4.1K · ⭐ 29 · ⏱️ 06.03.2020):
docker pull esridocker/arcgis-api-python-notebook
EarthPy (🥉20 · ⭐ 230) - A package built to support working with spatial data using open source.. BSD-3
pymap3d (🥉19 · ⭐ 180 · 📉) - pure-Python (Numpy optional) 3D coordinate conversions for geospace.. BSD-2
Show 7 hidden projects...
- Geocoder (🥈30 · ⭐ 1.3K · 💀) - Python Geocoder.
MIT
- Cartopy (🥉27 · ⭐ 1.4K) - Rasterio reads and writes geospatial raster datasets.
❗️LGPL-3.0
- Satpy (🥉25 · ⭐ 670) - Python package for earth-observing satellite data processing.
❗️GPL-3.0
- gmaps (🥉22 · ⭐ 700 · 💀) - Google maps for Jupyter notebooks.
BSD-3
- Sentinelsat (🥉21 · ⭐ 560) - Search and download Copernicus Sentinel satellite images.
❗️GPL-3.0
- Mapbox GL (🥉20 · ⭐ 560 · 💀) - Use Mapbox GL JS to visualize data in a Python Jupyter notebook.
MIT
- geoplotlib (🥉19 · ⭐ 890 · 💀) - 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.
yfinance (🥇29 · ⭐ 4.3K) - Yahoo! Finance market data downloader (+faster Pandas Datareader). Apache-2
Alpha Vantage (🥇27 · ⭐ 3.1K) - A python wrapper for Alpha Vantage API for financial data. MIT
empyrical (🥈25 · ⭐ 720) - Common financial risk and performance metrics. Used by zipline and.. Apache-2
stockstats (🥈24 · ⭐ 720) - Supply a wrapper ``StockDataFrame`` based on the.. BSD-3
Enigma Catalyst (🥉23 · ⭐ 2K) - An Algorithmic Trading Library for Crypto-Assets in Python. Apache-2
TensorTrade (🥉21 · ⭐ 2.9K) - An open source reinforcement learning framework for training,.. Apache-2
tf-quant-finance (🥉20 · ⭐ 2.5K) - High-performance TensorFlow library for quantitative.. Apache-2
finmarketpy (🥉20 · ⭐ 2.5K) - Python library for backtesting trading strategies & analyzing.. Apache-2
Crypto Signals (🥉18 · ⭐ 2.6K) - Github.com/CryptoSignal - #1 Quant Trading & Technical Analysis.. MIT
-
GitHub (👨💻 25 · 🔀 690 · 📋 230 - 16% open · ⏱️ 03.09.2020):
git clone https://github.com/CryptoSignal/crypto-signal
-
Docker Hub (📥 42K · ⭐ 8 · ⏱️ 03.09.2020):
docker pull shadowreaver/crypto-signal
Show 6 hidden projects...
- backtrader (🥈26 · ⭐ 5.7K) - Python Backtesting library for trading strategies.
❗️GPL-3.0
- arch (🥈25 · ⭐ 640 · 📈) - ARCH models in Python.
❗️NCSA
- PyAlgoTrade (🥉23 · ⭐ 3.2K · 💀) - Python Algorithmic Trading Library.
Apache-2
- FinTA (🥉22 · ⭐ 840) - Common financial technical indicators implemented in Pandas.
❗️LGPL-3.0
- Backtesting.py (🥉17 · ⭐ 1K) - Backtest trading strategies in Python.
❗️AGPL-3.0
- surpriver (🥉12 · ⭐ 1.1K · 🐣) - Find big moving stocks before they move using machine..
❗️GPL-3.0
Time Series Data
Libraries for forecasting, anomaly detection, feature extraction, and machine learning on time-series and sequential data.
Prophet (🥇29 · ⭐ 12K) - Tool for producing high quality forecasts for time series data that has.. MIT
pmdarima (🥈26 · ⭐ 810) - A statistical library designed to fill the void in Python's time series.. MIT
Darts (🥉22 · ⭐ 730) - A python library for easy manipulation and forecasting of time series. Apache-2
-
GitHub (👨💻 23 · 🔀 93 · 📦 12 · 📋 67 - 31% open · ⏱️ 03.02.2021):
git clone https://github.com/unit8co/darts
-
PyPi (📥 4.1K / month · ⏱️ 03.02.2021):
pip install u8darts
-
Docker Hub (📥 100 · ⏱️ 03.02.2021):
docker pull unit8/darts
STUMPY (🥉20 · ⭐ 1.7K) - STUMPY is a powerful and scalable Python library for computing a Matrix.. BSD-3
pytorch-forecasting (🥉19 · ⭐ 770) - Time series forecasting with PyTorch. MIT
matrixprofile-ts (🥉19 · ⭐ 610 · 💤) - A Python library for detecting patterns and anomalies.. Apache-2
ADTK (🥉17 · ⭐ 600 · 💤) - A Python toolkit for rule-based/unsupervised anomaly detection in time.. MPL-2.0
tick (🥉17 · ⭐ 320 · 💤) - Module for statistical learning, with a particular emphasis on time-.. BSD-3
Show 3 hidden projects...
Medical Data
Libraries for processing and analyzing medical data such as MRIs, EEGs, genomic data, and other medical imaging formats.
MNE (🥈27 · ⭐ 1.5K) - MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python. BSD-3
DeepVariant (🥉21 · ⭐ 2.2K) - DeepVariant is an analysis pipeline that uses a deep neural.. BSD-3
Brainiak (🥉19 · ⭐ 230) - Brain Imaging Analysis Kit. Apache-2
-
GitHub (👨💻 32 · 🔀 110 · 📦 12 · 📋 180 - 35% open · ⏱️ 15.10.2020):
git clone https://github.com/brainiak/brainiak
-
PyPi (📥 110 / month · 📦 1 · ⏱️ 15.10.2020):
pip install brainiak
-
Docker Hub (📥 490 · ⭐ 1 · ⏱️ 15.10.2020):
docker pull brainiak/brainiak
Medical Detection Toolkit (🥉12 · ⭐ 900 · 💤) - The Medical Detection Toolkit contains 2D + 3D.. Apache-2
-
GitHub (👨💻 3 · 🔀 230 · 📋 110 - 24% open · ⏱️ 18.04.2020):
git clone https://github.com/MIC-DKFZ/medicaldetectiontoolkit
MedicalNet (🥉11 · ⭐ 1.1K) - Many studies have shown that the performance on deep learning is.. MIT
-
GitHub (👨💻 1 · 🔀 280 · 📋 57 - 75% open · ⏱️ 27.08.2020):
git clone https://github.com/Tencent/MedicalNet
Show 4 hidden projects...
- DLTK (🥉20 · ⭐ 1.2K · 💀) - Deep Learning Toolkit for Medical Image Analysis.
Apache-2
- MedPy (🥉20 · ⭐ 310 · 💤) - Medical image processing in Python.
❗️GPL-3.0
- MedicalTorch (🥉15 · ⭐ 710 · 💀) - A medical imaging framework for Pytorch.
Apache-2
- DeepNeuro (🥉14 · ⭐ 98 · 💤) - A deep learning python package for neuroimaging data. Made by:.
MIT
Optical Character Recognition
Libraries for optical character recognition (OCR) and text extraction from images or videos.
Tesseract (🥇30 · ⭐ 3.4K) - Python-tesseract is an optical character recognition (OCR) tool.. Apache-2
EasyOCR (🥇27 · ⭐ 11K) - Ready-to-use OCR with 80+ supported languages and all popular writing.. Apache-2
OCRmyPDF (🥈26 · ⭐ 3.9K) - OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them.. MPL-2.0
attention-ocr (🥉20 · ⭐ 840) - A Tensorflow model for text recognition (CNN + seq2seq with.. MIT
doc2text (🥉19 · ⭐ 1.2K) - Detect text blocks and OCR poorly scanned PDFs in bulk. Python module.. MIT
Mozart (🥉10 · ⭐ 230 · 🐣) - An optical music recognition (OMR) system. Converts sheet.. Apache-2
-
GitHub (👨💻 5 · 🔀 36 · 📋 2 - 50% open · ⏱️ 14.01.2021):
git clone https://github.com/aashrafh/Mozart
Show 1 hidden projects...
- pdftabextract (🥉20 · ⭐ 1.9K · 💀) - A set of tools for extracting tables from PDF files..
Apache-2
Data Containers & Structures
General-purpose data containers & structures as well as utilities & extensions for pandas.
h5py (🥇36 · ⭐ 1.5K) - HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5.. BSD-3
Arrow (🥈35 · ⭐ 7.2K) - Apache Arrow is a cross-language development platform for in-memory.. Apache-2
numexpr (🥈31 · ⭐ 1.5K) - Fast numerical array expression evaluator for Python, NumPy, PyTables,.. MIT
Bottleneck (🥈29 · ⭐ 580) - Fast NumPy array functions written in C. BSD-2
Modin (🥈28 · ⭐ 5.7K) - Modin: Speed up your Pandas workflows by changing a single line of.. Apache-2
datasketch (🥉27 · ⭐ 1.4K) - MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog,.. MIT
Arctic (🥉24 · ⭐ 2.2K) - Arctic is a high performance datastore for numeric data. ❗️LGPL-2.1
Vaex (🥉23 · ⭐ 5.8K) - Out-of-Core DataFrames for Python, ML, visualize and explore big tabular data.. MIT
Pandaral·lel (🥉23 · ⭐ 1.4K) - A simple and efficient tool to parallelize Pandas.. BSD-3
StaticFrame (🥉20 · ⭐ 210) - The StaticFrame library defines the Series and Frame, immutable data.. MIT
Show 5 hidden projects...
- Blaze (🥈28 · ⭐ 2.9K · 💀) - NumPy and Pandas interface to Big Data.
BSD-3
- sklearn-pandas (🥈28 · ⭐ 2.3K) - Pandas integration with sklearn.
❗️Zlib
- pandasql (🥉22 · ⭐ 940 · 💀) - sqldf for pandas.
MIT
- pickleDB (🥉21 · ⭐ 540 · 💀) - pickleDB is an open source key-value store using Python's json..
BSD-3
- Pandas Summary (🥉21 · ⭐ 360 · 💀) - An extension to pandas dataframes describe function.
MIT
Data Loading & Extraction
Libraries for loading, collecting, and extracting data from a variety of data sources and formats.
python-magic (🥇32 · ⭐ 1.8K) - A python wrapper for libmagic. MIT
TensorFlow Datasets (🥈31 · ⭐ 2.7K) - TFDS is a collection of datasets ready to use with.. Apache-2
smart-open (🥈30 · ⭐ 1.9K) - Utils for streaming large files (S3, HDFS, gzip, bz2...). MIT
Datasets (🥈29 · ⭐ 6.8K) - The largest hub of ready-to-use NLP datasets for ML models with.. Apache-2
pandas-datareader (🥈29 · ⭐ 1.9K) - Extract data from a wide range of Internet sources.. BSD-3
csvkit (🥉28 · ⭐ 4.5K) - A suite of utilities for converting to and working with CSV, the king of.. MIT
snorkel (🥉27 · ⭐ 4.5K) - A system for quickly generating training data with weak supervision. Apache-2
tabulator-py (🥉26 · ⭐ 200) - Python library for reading and writing tabular data via streams. MIT
Intake (🥉25 · ⭐ 530) - Intake is a lightweight package for finding, investigating, loading and.. BSD-2
Show 8 hidden projects...
- PDFMiner (🥉27 · ⭐ 4.5K · 💀) - Python PDF Parser (Not actively maintained). Check out pdfminer.six.
MIT
- textract (🥉26 · ⭐ 3K · 💀) - extract text from any document. no muss. no fuss.
MIT
- Singer (🥉24 · ⭐ 700) - Standard for moving data between databases, web APIs, files, queues,..
❗️AGPL-3.0
- Camelot (🥉23 · ⭐ 3K · 💀) - Camelot: PDF Table Extraction for Humans.
MIT
- messytables (🥉23 · ⭐ 360 · 💀) - Tools for parsing messy tabular data. This is now superseded by..
MIT
- pyexcel-xlsx (🥉22 · ⭐ 85) - A wrapper library to read, manipulate and write data in xlsx and..
BSD-3
- openpyxl (🥉22 · ⭐ 17) - A Python library to read/write Excel 2010 xlsx/xlsm files.
MIT
- rows (🥉20 · ⭐ 740) - A common, beautiful interface to tabular data, no matter the format.
❗️LGPL-3.0
Web Scraping & Crawling
Libraries for web scraping, crawling, downloading, and mining as well as libraries.
🔗 best-of-web-python - Web Scraping ( ⭐ 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.
Celery (🥇38 · ⭐ 17K) - Asynchronous task queue/job queue based on distributed message passing. BSD-3
Airflow (🥇35 · ⭐ 21K) - Platform to programmatically author, schedule, and monitor workflows. Apache-2
-
GitHub (👨💻 1.8K · 🔀 8K · 📥 91K · 📋 3K - 33% open · ⏱️ 18.02.2021):
git clone https://github.com/apache/airflow
-
PyPi (📥 470K / month · 📦 290 · ⏱️ 08.02.2021):
pip install apache-airflow
-
Conda (📥 280K · ⏱️ 16.02.2021):
conda install -c conda-forge airflow
-
Docker Hub (📥 7M · ⭐ 220 · ⏱️ 17.02.2021):
docker pull apache/airflow
luigi (🥇33 · ⭐ 14K) - Luigi is a Python module that helps you build complex pipelines of batch.. Apache-2
dbt (🥈29 · ⭐ 2.5K) - dbt (data build tool) enables data analysts and engineers to transform.. Apache-2
Kedro (🥈28 · ⭐ 3.5K) - A Python framework for creating reproducible, maintainable and modular.. Apache-2
PyFunctional (🥈26 · ⭐ 1.8K) - Python library for creating data pipelines with chain functional.. MIT
streamparse (🥉25 · ⭐ 1.4K) - Run Python in Apache Storm topologies. Pythonic API, CLI.. Apache-2
Great Expectations (🥉24 · ⭐ 3.7K) - Always know what to expect from your data. Apache-2
pysparkling (🥉23 · ⭐ 230) - A pure Python implementation of Apache Spark's RDD and DStream.. MIT
spark-deep-learning (🥉18 · ⭐ 1.8K) - Deep Learning Pipelines for Apache Spark. Apache-2
-
GitHub (👨💻 15 · 🔀 450 · 📦 16 · 📋 100 - 74% open · ⏱️ 20.01.2021):
git clone https://github.com/databricks/spark-deep-learning
Mara Pipelines (🥉18 · ⭐ 1.6K) - A lightweight opinionated ETL framework, halfway between plain.. MIT
Databolt Flow (🥉18 · ⭐ 900) - Python library for building highly effective data science workflows. MIT
BatchFlow (🥉17 · ⭐ 150) - BatchFlow helps you conveniently work with random or sequential.. Apache-2
Show 1 hidden projects...
Distributed Machine Learning
Libraries that provide capabilities to distribute and parallelize machine learning tasks across large-scale compute infrastructure.
dask.distributed (🥇34 · ⭐ 1.1K) - A distributed task scheduler for Dask. BSD-3
Ray (🥇32 · ⭐ 15K · 📉) - An open source framework that provides a simple, universal API for.. Apache-2
horovod (🥈29 · ⭐ 11K · 📉) - Distributed training framework for TensorFlow, Keras, PyTorch,.. Apache-2
ipyparallel (🥈28 · ⭐ 1.9K) - Interactive Parallel Computing in Python. BSD-3
BigDL (🥈25 · ⭐ 3.7K) - BigDL: Distributed Deep Learning Framework for Apache Spark. Apache-2
-
GitHub (👨💻 70 · 🔀 900 · 📦 23 · 📋 910 - 20% open · ⏱️ 21.01.2021):
git clone https://github.com/intel-analytics/BigDL
-
PyPi (📥 1.8K / month · 📦 6 · ⏱️ 29.12.2020):
pip install bigdl
-
Maven (⏱️ 05.12.2020):
<dependency> <groupId>com.intel.analytics.bigdl</groupId> <artifactId>bigdl-SPARK_2.4</artifactId> <version>[VERSION]</version> </dependency>
DeepSpeed (🥈24 · ⭐ 4.3K) - DeepSpeed is a deep learning optimization library that makes.. MIT
-
GitHub (👨💻 45 · 🔀 410 · 📦 10 · 📋 330 - 47% open · ⏱️ 18.02.2021):
git clone https://github.com/microsoft/DeepSpeed
-
PyPi (📥 2.1K / month · ⏱️ 02.02.2021):
pip install deepspeed
-
Docker Hub (📥 7.2K · ⭐ 2 · ⏱️ 11.02.2021):
docker pull deepspeed/deepspeed
TensorFlowOnSpark (🥈24 · ⭐ 3.6K) - TensorFlowOnSpark brings TensorFlow programs to.. Apache-2
petastorm (🥈24 · ⭐ 1.1K) - Petastorm library enables single machine or distributed training.. Apache-2
analytics-zoo (🥉22 · ⭐ 2.2K) - Distributed Tensorflow, Keras and PyTorch on Apache.. Apache-2
Apache Singa (🥉19 · ⭐ 2.2K) - a distributed deep learning platform. Apache-2
-
GitHub (👨💻 70 · 🔀 610 · 📦 1 · 📋 74 - 54% open · ⏱️ 15.01.2021):
git clone https://github.com/apache/singa
-
Conda (📥 260 · ⏱️ 20.01.2021):
conda install -c nusdbsystem singa
-
Docker Hub (📥 160 · ⭐ 2 · ⏱️ 04.06.2019):
docker pull apache/singa
BytePS (🥉18 · ⭐ 2.7K) - A high performance and generic framework for distributed DNN training. Apache-2
-
GitHub (👨💻 18 · 🔀 370 · 📋 210 - 34% open · ⏱️ 17.02.2021):
git clone https://github.com/bytedance/byteps
-
PyPi (📥 74 / month · ⏱️ 04.11.2020):
pip install byteps
-
Docker Hub (📥 1K · ⏱️ 03.03.2020):
docker pull bytepsimage/tensorflow
Show 3 hidden projects...
- DEAP (🥈27 · ⭐ 4.1K) - Distributed Evolutionary Algorithms in Python.
❗️LGPL-3.0
- TensorFrames (🥉18 · ⭐ 770 · 💀) - [DEPRECATED] Tensorflow wrapper for DataFrames on..
Apache-2
- LazyCluster (🥉12 · ⭐ 33) - Distributed machine learning made simple.
Apache-2
Hyperparameter Optimization & AutoML
Libraries for hyperparameter optimization, automl and neural architecture search.
scikit-optimize (🥇30 · ⭐ 2K) - Sequential model-based optimization with a `scipy.optimize`.. BSD-3
Keras Tuner (🥇28 · ⭐ 2.2K) - Hyperparameter tuning for humans. Apache-2
featuretools (🥈27 · ⭐ 5.4K) - An open source python library for automated feature engineering. BSD-3
Bayesian Optimization (🥈27 · ⭐ 4.9K) - A Python implementation of global optimization with.. MIT
auto-sklearn (🥈26 · ⭐ 5.2K) - Automated Machine Learning with scikit-learn. BSD-3
lazypredict (🥉21 · ⭐ 380 · 📈) - Lazy Predict help build a lot of basic models without much.. MIT
Neuraxle (🥉21 · ⭐ 360) - A Sklearn-like Framework for Hyperparameter Tuning and AutoML in.. Apache-2
mljar-supervised (🥉20 · ⭐ 890) - Automates Machine Learning Pipeline with Feature Engineering.. MIT
Auto ViML (🥉20 · ⭐ 210) - Automatically Build Multiple ML Models with a Single Line of Code... Apache-2
HyperparameterHunter (🥉16 · ⭐ 640) - Easy hyperparameter optimization and automatic result.. MIT
AlphaPy (🥉16 · ⭐ 550) - Automated Machine Learning [AutoML] with Python, scikit-learn, Keras,.. Apache-2
Auto Tune Models (🥉16 · ⭐ 500 · 💤) - Auto Tune Models - A multi-tenant, multi-data system for.. MIT
ENAS (🥉14 · ⭐ 2.4K · 💤) - PyTorch implementation of Efficient Neural Architecture Search via.. Apache-2
-
GitHub (👨💻 6 · 🔀 450 · 📋 44 - 84% open · ⏱️ 16.06.2020):
git clone https://github.com/carpedm20/ENAS-pytorch
Devol (🥉11 · ⭐ 920 · 💤) - Genetic neural architecture search with Keras. MIT
-
GitHub (👨💻 18 · 🔀 110 · 📋 27 - 25% open · ⏱️ 05.07.2020):
git clone https://github.com/joeddav/devol
Show 13 hidden projects...
- TPOT (🥇29 · ⭐ 7.8K) - A Python Automated Machine Learning tool that optimizes machine..
❗️LGPL-3.0
- auto_ml (🥉21 · ⭐ 1.5K · 💀) - [UNMAINTAINED] Automated machine learning for analytics & production.
MIT
- MLBox (🥉20 · ⭐ 1.2K) - MLBox is a powerful Automated Machine Learning python library.
❗️BSD-1-Clause
- HpBandSter (🥉20 · ⭐ 450 · 💀) - a distributed Hyperband implementation on Steroids.
BSD-3
- Advisor (🥉17 · ⭐ 1.3K · 💀) - Open-source implementation of Google Vizier for hyper parameters..
Apache-2
- sklearn-deap (🥉17 · ⭐ 630 · 💀) - Use evolutionary algorithms instead of gridsearch in..
MIT
- Sherpa (🥉17 · ⭐ 280) - Hyperparameter optimization that enables researchers to experiment,..
❗️GPL-3.0
- automl-gs (🥉16 · ⭐ 1.7K · 💀) - 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
- Auptimizer (🥉13 · ⭐ 160) - An automatic ML model optimization tool.
❗️GPL-3.0
- Hypermax (🥉13 · ⭐ 94) - Better, faster hyper-parameter optimization.
BSD-3
- featurewiz (🥉12 · ⭐ 39 · 🐣) - Use advanced feature engineering strategies and select the..
Apache-2
- Hypertunity (🥉10 · ⭐ 120 · 💀) - A toolset for black-box hyperparameter optimisation.
Apache-2
Reinforcement Learning
Libraries for building and evaluating reinforcement learning & agent-based systems.
OpenAI Gym (🥇35 · ⭐ 23K) - A toolkit for developing and comparing reinforcement learning.. MIT
TensorLayer (🥈27 · ⭐ 6.5K) - Deep Learning and Reinforcement Learning Library for.. Apache-2
TensorForce (🥈25 · ⭐ 2.9K) - Tensorforce: a TensorFlow library for applied.. Apache-2
Stable Baselines (🥈24 · ⭐ 2.9K) - A fork of OpenAI Baselines, implementations of reinforcement.. MIT
PARL (🥉20 · ⭐ 1.8K) - A high-performance distributed training framework for Reinforcement.. Apache-2
ReAgent (🥉16 · ⭐ 2.8K) - A platform for Reasoning systems (Reinforcement Learning,.. BSD-3
-
GitHub (👨💻 86 · 🔀 380 · 📋 94 - 21% open · ⏱️ 13.02.2021):
git clone https://github.com/facebookresearch/ReAgent
Show 3 hidden projects...
Recommender Systems
Libraries for building and evaluating recommendation systems.
scikit-surprise (🥇26 · ⭐ 4.7K) - A Python scikit for building and analyzing recommender.. BSD-3
lightfm (🥇26 · ⭐ 3.5K) - A Python implementation of LightFM, a hybrid recommendation algorithm. Apache-2
TF Ranking (🥈22 · ⭐ 2K) - Learning to Rank in TensorFlow. Apache-2
Recommenders (🥈21 · ⭐ 9.2K) - Best Practices on Recommendation Systems. MIT
-
GitHub (👨💻 89 · 🔀 1.6K · 📦 1 · 📋 540 - 19% open · ⏱️ 11.02.2021):
git clone https://github.com/microsoft/recommenders
TF Recommenders (🥉19 · ⭐ 720) - TensorFlow Recommenders is a library for building.. Apache-2
recmetrics (🥉19 · ⭐ 240) - A library of metrics for evaluating recommender systems. MIT
Case Recommender (🥉16 · ⭐ 320 · 💤) - Case Recommender: A Flexible and Extensible Python.. MIT
OpenRec (🥉14 · ⭐ 350 · 💤) - OpenRec is an open-source and modular library for neural network-.. Apache-2
Privacy Machine Learning
Libraries for encrypted and privacy-preserving machine learning using methods like federated learning & differential privacy.
TensorFlow Privacy (🥈21 · ⭐ 1.3K) - Library for training machine learning models with.. Apache-2
FATE (🥉20 · ⭐ 2.8K) - An Industrial Grade Federated Learning Framework. Apache-2
-
GitHub (👨💻 52 · 🔀 820 · 📋 800 - 34% open · ⏱️ 07.02.2021):
git clone https://github.com/FederatedAI/FATE
TFEncrypted (🥉20 · ⭐ 820) - A Framework for Encrypted Machine Learning in TensorFlow. Apache-2
Workflow & Experiment Tracking
Libraries to organize, track, and visualize machine learning experiments.
Tensorboard (🥇36 · ⭐ 5.2K) - TensorFlow's Visualization Toolkit. Apache-2
wandb client (🥇30 · ⭐ 2.7K) - A tool for visualizing and tracking your machine learning.. MIT
SageMaker SDK (🥇30 · ⭐ 1.3K) - A library for training and deploying machine learning.. Apache-2
AzureML SDK (🥈28 · ⭐ 2.1K) - Python notebooks with ML and deep learning examples with Azure.. MIT
tensorboardX (🥈27 · ⭐ 6.8K · 💤) - tensorboard for pytorch (and chainer, mxnet, numpy, ...). MIT
ClearML (🥈24 · ⭐ 2.2K) - ClearML - Auto-Magical Suite of tools to streamline your ML.. Apache-2
-
GitHub (👨💻 26 · 🔀 330 · 📥 300 · 📦 13 · 📋 270 - 22% open · ⏱️ 14.02.2021):
git clone https://github.com/allegroai/clearml
-
PyPi (📥 2.6K / month · ⏱️ 14.02.2021):
pip install clearml
-
Docker Hub (📥 30K · ⏱️ 05.10.2020):
docker pull allegroai/trains
livelossplot (🥈24 · ⭐ 1K) - Live training loss plot in Jupyter Notebook for Keras, PyTorch.. MIT
ml-metadata (🥈24 · ⭐ 280) - For recording and retrieving metadata associated with ML.. Apache-2
TensorWatch (🥉23 · ⭐ 3K) - Debugging, monitoring and visualization for Python Machine Learning.. MIT
knockknock (🥉22 · ⭐ 2K · 💤) - Knock Knock: Get notified when your training ends with only two.. MIT
hiddenlayer (🥉19 · ⭐ 1.4K · 💤) - Neural network graphs and training metrics for.. MIT
aim (🥉15 · ⭐ 860) - Aim a super-easy way to record, search and compare 1000s of ML training.. Apache-2
Show 7 hidden projects...
- TensorBoard Logger (🥉19 · ⭐ 610 · 💀) - Log TensorBoard events without touching TensorFlow.
MIT
- MXBoard (🥉19 · ⭐ 330 · 💀) - Logging MXNet data for visualization in TensorBoard.
Apache-2
- SKLL (🥉16 · ⭐ 520) - SciKit-Learn Laboratory (SKLL) makes it easy to run machine..
❗️BSD-1-Clause
- datmo (🥉16 · ⭐ 330 · 💀) - Open source production model management tool for data scientists.
MIT
- steppy (🥉16 · ⭐ 130 · 💀) - Lightweight, Python library for fast and reproducible experimentation.
MIT
- ModelChimp (🥉14 · ⭐ 120) - Experiment tracking for machine and deep learning projects.
BSD-2
- traintool (🥉9 · ⭐ 9 · 🐣) - Train off-the-shelf machine learning models in one..
Apache-2
Model Serialization & Conversion
Libraries to serialize models to files, convert between a variety of model formats, and optimize models for deployment.
Core ML Tools (🥇26 · ⭐ 2.1K) - Core ML tools contain supporting tools for Core ML model.. BSD-3
TorchServe (🥈24 · ⭐ 1.6K) - Model Serving on PyTorch. Apache-2
-
GitHub (👨💻 61 · 🔀 240 · 📥 190 · 📦 29 · 📋 540 - 24% open · ⏱️ 13.01.2021):
git clone https://github.com/pytorch/serve
-
PyPi (📥 3K / month · ⏱️ 17.12.2020):
pip install torchserve
-
Conda (📥 6.6K · ⏱️ 17.12.2020):
conda install -c pytorch torchserve
-
Docker Hub (📥 52K · ⭐ 3 · ⏱️ 18.12.2020):
docker pull pytorch/torchserve
mmdnn (🥈23 · ⭐ 5.2K) - MMdnn is a set of tools to help users inter-operate among different deep.. MIT
m2cgen (🥈22 · ⭐ 1.8K) - Transform ML models into a native code (Java, C, Python, Go, JavaScript,.. MIT
Hummingbird (🥉20 · ⭐ 2.2K) - Hummingbird compiles trained ML models into tensor computation for.. MIT
pytorch2keras (🥉18 · ⭐ 670 · 💤) - PyTorch to Keras model convertor. MIT
Show 2 hidden projects...
- sklearn-porter (🥉17 · ⭐ 980 · 💀) - Transpile trained scikit-learn estimators to C, Java,..
MIT
- Larq Compute Engine (🥉17 · ⭐ 130) - Highly optimized inference engine for Binarized..
Apache-2
Model Interpretability
Libraries to visualize, explain, debug, evaluate, and interpret machine learning models.
shap (🥇34 · ⭐ 12K) - A game theoretic approach to explain the output of any machine learning model. MIT
InterpretML (🥇27 · ⭐ 3.5K) - Fit interpretable models. Explain blackbox machine learning. MIT
Model Analysis (🥇27 · ⭐ 1K) - Model analysis tools for TensorFlow. Apache-2
yellowbrick (🥈25 · ⭐ 3.1K) - Visual analysis and diagnostic tools to facilitate machine.. Apache-2
dtreeviz (🥈25 · ⭐ 1.4K) - A python library for decision tree visualization and model interpretation. MIT
Fairness 360 (🥈24 · ⭐ 1.2K) - A comprehensive set of fairness metrics for datasets and.. Apache-2
iNNvestigate (🥈22 · ⭐ 770) - A toolbox to iNNvestigate neural networks' predictions!. BSD-2
Explainability 360 (🥈22 · ⭐ 770) - Interpretability and explainability of data and machine.. Apache-2
TreeInterpreter (🥈22 · ⭐ 640) - Package for interpreting scikit-learn's decision tree.. BSD-3
random-forest-importances (🥈22 · ⭐ 410) - Code to compute permutation and drop-column.. MIT
tf-explain (🥉21 · ⭐ 760) - Interpretability Methods for tf.keras models with Tensorflow 2.x. MIT
explainerdashboard (🥉20 · ⭐ 320) - Quickly build Explainable AI dashboards that show the inner.. MIT
sklearn-evaluation (🥉20 · ⭐ 290) - Machine learning model evaluation made easy: plots,.. MIT
What-If Tool (🥉19 · ⭐ 440) - Source code/webpage/demos for the What-If Tool. Apache-2
fairness-indicators (🥉18 · ⭐ 180) - Tensorflow's Fairness Evaluation and Visualization.. Apache-2
LIT (🥉17 · ⭐ 2.4K) - The Language Interpretability Tool: Interactively analyze NLP models for.. Apache-2
ExplainX.ai (🥉17 · ⭐ 180) - Explainable AI framework for data scientists. Explain & debug any.. MIT
model-card-toolkit (🥉17 · ⭐ 160) - a tool that leverages rich metadata and lineage.. Apache-2
imodels (🥉17 · ⭐ 150) - Interpretable ML package for concise, transparent, and accurate predictive.. MIT
FlashTorch (🥉15 · ⭐ 550 · 💤) - Visualization toolkit for neural networks in PyTorch! Demo --. MIT
Show 8 hidden projects...
- eli5 (🥇27 · ⭐ 2.3K · 💀) - A library for debugging/inspecting machine learning classifiers and..
MIT
- scikit-plot (🥈23 · ⭐ 2K · 💀) - An intuitive library to add plotting functionality to scikit-..
MIT
- Skater (🥉19 · ⭐ 970 · 💤) - Python Library for Model Interpretation/Explanations.
❗️UPL-1.0
- DALEX (🥉18 · ⭐ 770) - moDel Agnostic Language for Exploration and eXplanation.
❗️GPL-3.0
- XAI (🥉16 · ⭐ 580 · 💀) - XAI - An eXplainability toolbox for machine learning.
MIT
- contextual-ai (🥉15 · ⭐ 67) - Contextual AI adds explainability to different stages of..
Apache-2
- Attribution Priors (🥉13 · ⭐ 74) - Tools for training explainable models using..
MIT
- bias-detector (🥉10 · ⭐ 15 · ➕) - Bias Detector is a python package for detecting bias in machine..
MIT
Vector Similarity Search (ANN)
Libraries for Approximate Nearest Neighbor Search and Vector Indexing/Similarity Search.
🔗 ANN Benchmarks ( ⭐ 2.1K) - Benchmarks of approximate nearest neighbor libraries in Python.
Annoy (🥇30 · ⭐ 8.1K) - Approximate Nearest Neighbors in C++/Python optimized for memory usage.. Apache-2
Faiss (🥇28 · ⭐ 12K · 📉) - A library for efficient similarity search and clustering of dense vectors. MIT
NMSLIB (🥇28 · ⭐ 2.3K) - Non-Metric Space Library (NMSLIB): An efficient similarity search.. Apache-2
hnswlib (🥈26 · ⭐ 1.3K) - Header-only C++/python library for fast approximate nearest neighbors. Apache-2
Milvus (🥈25 · ⭐ 5.1K) - An open source embedding vector similarity search engine powered by.. Apache-2
-
GitHub (👨💻 140 · 🔀 790 · 📋 2.1K - 10% open · ⏱️ 09.02.2021):
git clone https://github.com/milvus-io/milvus
-
PyPi (📥 4.3K / month · 📦 6 · ⏱️ 21.01.2021):
pip install pymilvus
-
Docker Hub (📥 250K · ⭐ 9 · ⏱️ 06.01.2021):
docker pull milvusdb/milvus
PyNNDescent (🥈25 · ⭐ 370 · 📈) - A Python nearest neighbor descent for approximate nearest.. BSD-2
N2 (🥉19 · ⭐ 460) - TOROS N2 - lightweight approximate Nearest Neighbor library which runs fast.. Apache-2
Show 2 hidden projects...
Probabilistics & Statistics
Libraries providing capabilities for probabilistic programming/reasoning, bayesian inference, gaussian processes, or statistics.
tensorflow-probability (🥇31 · ⭐ 3.2K) - Probabilistic reasoning and statistical analysis in.. Apache-2
pomegranate (🥈27 · ⭐ 2.6K) - Fast, flexible and easy to use probabilistic modelling in Python. MIT
scikit-posthocs (🥉20 · ⭐ 180) - Pairwise Multiple Comparisons (Post Hoc) Tests in Python. MIT
Baal (🥉17 · ⭐ 320) - Using approximate bayesian posteriors in deep nets for active learning. Apache-2
Show 5 hidden projects...
- patsy (🥈27 · ⭐ 740 · 💀) - Describing statistical models in Python using symbolic formulas.
BSD-2
- Edward (🥉24 · ⭐ 4.6K · 💀) - A probabilistic programming language in TensorFlow. Deep..
Apache-2
- pingouin (🥉22 · ⭐ 640) - Statistical package in Python based on Pandas.
❗️GPL-3.0
- PyStan (🥉21 · ⭐ 35 · 📉) - PyStan, a Python interface to Stan, a platform for statistical modeling...
ISC
- ZhuSuan (🥉14 · ⭐ 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.
CleverHans (🥇27 · ⭐ 5K) - An adversarial example library for constructing attacks, building.. MIT
Foolbox (🥈25 · ⭐ 1.8K) - A Python toolbox to create adversarial examples that fool neural networks.. MIT
TextAttack (🥈23 · ⭐ 1.2K) - TextAttack is a Python framework for adversarial attacks, data.. MIT
robustness (🥉18 · ⭐ 480) - A library for experimenting with, training and evaluating neural.. MIT
AdvBox (🥉15 · ⭐ 1K) - Advbox is a toolbox to generate adversarial examples that fool neural.. Apache-2
Show 2 hidden projects...
- advertorch (🥉17 · ⭐ 810 · 💤) - A Toolbox for Adversarial Robustness Research.
❗️GPL-3.0
- Adversary (🥉13 · ⭐ 340 · 💀) - Tool to generate adversarial text examples and test machine..
MIT
GPU Utilities
Libraries that require and make use of CUDA/GPU system capabilities to optimize data handling and machine learning tasks.
CuPy (🥇31 · ⭐ 4.8K) - A NumPy-compatible array library accelerated by CUDA. MIT
-
GitHub (👨💻 250 · 🔀 440 · 📥 8.4K · 📦 670 · 📋 1.3K - 28% open · ⏱️ 18.02.2021):
git clone https://github.com/cupy/cupy
-
PyPi (📥 16K / month · 📦 190 · ⏱️ 28.01.2021):
pip install cupy
-
Conda (📥 380K · ⏱️ 02.02.2021):
conda install -c conda-forge cupy
-
Docker Hub (📥 48K · ⭐ 6 · ⏱️ 18.02.2021):
docker pull cupy/cupy
scikit-cuda (🥈22 · ⭐ 800) - Python interface to GPU-powered libraries. BSD-3
py3nvml (🥉21 · ⭐ 160 · 💤) - Python 3 Bindings for NVML library. Get NVIDIA GPU status inside.. BSD-3
DALI (🥉20 · ⭐ 3.1K) - A library containing both highly optimized building blocks and an.. Apache-2
-
GitHub (👨💻 56 · 🔀 370 · 📋 810 - 24% open · ⏱️ 18.02.2021):
git clone https://github.com/NVIDIA/DALI
BlazingSQL (🥉17 · ⭐ 1.4K) - BlazingSQL is a lightweight, GPU accelerated, SQL engine for.. Apache-2
Vulkan Kompute (🥉17 · ⭐ 330) - General purpose GPU compute framework for cross vendor.. Apache-2
SpeedTorch (🥉16 · ⭐ 610 · 💤) - Library for faster pinned CPU - GPU transfer in Pytorch. MIT
cuSignal (🥉15 · ⭐ 450) - GPU accelerated signal processing. Apache-2
-
GitHub (👨💻 29 · 🔀 61 · 📋 100 - 14% open · ⏱️ 17.02.2021):
git clone https://github.com/rapidsai/cusignal
Show 3 hidden projects...
- GPUtil (🥈22 · ⭐ 670 · 💀) - A Python module for getting the GPU status from NVIDA GPUs using..
MIT
- nvidia-ml-py3 (🥉18 · ⭐ 64 · 💀) - Python 3 Bindings for the NVIDIA Management Library.
BSD-3
- ipyexperiments (🥉16 · ⭐ 120) - jupyter/ipython experiment containers for GPU and..
Apache-2
Tensorflow Utilities
Libraries that extend TensorFlow with additional capabilities.
tensorflow-hub (🥇32 · ⭐ 2.7K) - A library for transfer learning by reusing parts of.. Apache-2
tensor2tensor (🥇31 · ⭐ 11K · 📉) - Library of deep learning models and datasets designed.. Apache-2
TensorFlow Transform (🥈29 · ⭐ 850) - Input pipeline framework. Apache-2
TF Model Optimization (🥈26 · ⭐ 970) - A toolkit to optimize ML models for deployment for.. Apache-2
efficientnet (🥉25 · ⭐ 1.7K) - Implementation of EfficientNet model. Keras and.. Apache-2
TensorFlow I/O (🥉25 · ⭐ 420) - Dataset, streaming, and file system extensions.. Apache-2
TensorFlow Cloud (🥉22 · ⭐ 230) - The TensorFlow Cloud repository provides APIs that.. Apache-2
Neural Structured Learning (🥉21 · ⭐ 780) - Training neural models with structured signals. Apache-2
TensorNets (🥉19 · ⭐ 980) - High level network definitions with pre-trained weights in.. MIT
TF Compression (🥉17 · ⭐ 440) - Data compression in TensorFlow. Apache-2
Sklearn Utilities
Libraries that extend scikit-learn with additional capabilities.
imbalanced-learn (🥇31 · ⭐ 5K · 📈) - A Python Package to Tackle the Curse of Imbalanced.. MIT
category_encoders (🥈24 · ⭐ 1.6K · 💤) - A library of sklearn compatible categorical variable.. BSD-3
sklearn-contrib-lightning (🥈23 · ⭐ 1.4K) - Large-scale linear classification, regression and.. BSD-3
fancyimpute (🥈23 · ⭐ 930) - Multivariate imputation and matrix completion algorithms.. Apache-2
scikit-opt (🥉22 · ⭐ 2K) - Genetic Algorithm, Particle Swarm Optimization, Simulated.. MIT
scikit-lego (🥉22 · ⭐ 420) - Extra blocks for scikit-learn pipelines. MIT
iterative-stratification (🥉19 · ⭐ 510) - scikit-learn cross validators for iterative.. BSD-3
scikit-tda (🥉19 · ⭐ 270) - Topological Data Analysis for Python. MIT
Show 5 hidden projects...
- sklearn-crfsuite (🥈24 · ⭐ 360 · 💀) - scikit-learn inspired API for CRFsuite.
MIT
- scikit-multilearn (🥉22 · ⭐ 630 · 💀) - A scikit-learn based module for multi-label et. al...
BSD-2
- skope-rules (🥉21 · ⭐ 350) - machine learning with logical rules in Python.
❗️BSD-1-Clause
- dabl (🥉17 · ⭐ 66 · 💤) - Data Analysis Baseline Library.
BSD-3
- celer (🥉16 · ⭐ 110) - Fast solver for L1-type problems: Lasso, sparse Logisitic regression,..
BSD-3
Pytorch Utilities
Libraries that extend Pytorch with additional capabilities.
pretrainedmodels (🥇27 · ⭐ 7.7K · 💤) - Pretrained ConvNets for pytorch: NASNet, ResNeXt,.. BSD-3
pytorch-optimizer (🥇25 · ⭐ 1.7K) - torch-optimizer -- collection of optimizers for.. Apache-2
torchdiffeq (🥇24 · ⭐ 3.4K) - Differentiable ODE solvers with full GPU support and.. MIT
pytorch-summary (🥇24 · ⭐ 2.9K) - Model summary in PyTorch similar to `model.summary()` in.. MIT
PML (🥇24 · ⭐ 2.7K) - The easiest way to use deep metric learning in your application. Modular,.. MIT
SRU (🥇24 · ⭐ 1.9K) - Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755). MIT
EfficientNet-PyTorch (🥈23 · ⭐ 5.5K) - A PyTorch implementation of EfficientNet. Apache-2
PyTorch Sparse (🥈21 · ⭐ 350) - PyTorch Extension Library of Optimized Autograd Sparse.. MIT
reformer-pytorch (🥈20 · ⭐ 1.4K) - Reformer, the efficient Transformer, in Pytorch. MIT
EfficientNets (🥈20 · ⭐ 1.2K) - Pretrained EfficientNet, EfficientNet-Lite, MixNet,.. Apache-2
torch-scatter (🥈20 · ⭐ 600) - PyTorch Extension Library of Optimized Scatter Operations. MIT
Pytorch Toolbelt (🥉19 · ⭐ 900) - PyTorch extensions for fast R&D prototyping and Kaggle.. MIT
Tensor Sensor (🥉17 · ⭐ 530 · 🐣) - The goal of this library is to generate more helpful.. MIT
Performer Pytorch (🥉17 · ⭐ 510 · 🐣) - An implementation of Performer, a linear attention-.. MIT
tinygrad (🥉15 · ⭐ 4.1K · 🐣) - You like pytorch? You like micrograd? You love tinygrad!. MIT
-
GitHub (👨💻 43 · 🔀 450 · 📋 76 - 18% open · ⏱️ 31.01.2021):
git clone https://github.com/geohot/tinygrad
Lambda Networks (🥉15 · ⭐ 1.3K · 🐣) - Implementation of LambdaNetworks, a new approach to.. MIT
Torch-Struct (🥉15 · ⭐ 900) - Fast, general, and tested differentiable structured prediction.. MIT
-
GitHub (👨💻 13 · 🔀 71 · 📋 42 - 42% open · ⏱️ 14.02.2021):
git clone https://github.com/harvardnlp/pytorch-struct
torchsde (🥉15 · ⭐ 650) - Differentiable SDE solvers with GPU support and efficient.. Apache-2
-
GitHub (👨💻 4 · 🔀 55 · 📋 34 - 17% open · ⏱️ 09.02.2021):
git clone https://github.com/google-research/torchsde
Show 3 hidden projects...
- AdaBound (🥉19 · ⭐ 2.8K · 💀) - An optimizer that trains as fast as Adam and as good as SGD.
Apache-2
- Poutyne (🥉19 · ⭐ 450) - A simplified framework and utilities for PyTorch.
❗️LGPL-3.0
- Antialiased CNNs (🥉17 · ⭐ 1.3K) - pip install antialiased-cnns to improve stability and..
❗️CC BY-NC-SA 4.0
Database Clients
Libraries for connecting to, operating, and querying databases.
🔗 best-of-python - DB Clients ( ⭐ 1.4K · 🐣) - Collection of database clients for python.
Others
scipy (🥇40 · ⭐ 7.9K) - Ecosystem of open-source software for mathematics, science, and engineering. BSD-3
Keras-Preprocessing (🥇28 · ⭐ 910) - Utilities for working with image data, text data, and.. MIT
Cython BLIS (🥇28 · ⭐ 160) - Fast matrix-multiplication as a self-contained Python library no.. BSD-3
agate (🥈26 · ⭐ 1K · 💤) - A Python data analysis library that is optimized for humans instead of.. MIT
pyclustering (🥈26 · ⭐ 790) - pyclustring is a Python, C++ data mining library. BSD-3
TabPy (🥈24 · ⭐ 1K) - Execute Python code on the fly and display results in Tableau visualizations:. MIT
PennyLane (🥈24 · ⭐ 760) - PennyLane is a cross-platform Python library for differentiable.. Apache-2
pyjanitor (🥈24 · ⭐ 630) - Clean APIs for data cleaning. Python implementation of R package Janitor. MIT
cleanlab (🥉22 · ⭐ 1.5K) - The standard package for machine learning with noisy labels and finding.. MIT
metric-learn (🥉22 · ⭐ 1.1K) - Metric learning algorithms in Python. MIT
Mars (🥉21 · ⭐ 2K) - Mars is a tensor-based unified framework for large-scale data computation.. Apache-2
StreamAlert (🥉20 · ⭐ 2.5K) - StreamAlert is a serverless, realtime data analysis framework.. Apache-2
-
GitHub (👨💻 31 · 🔀 280 · 📋 340 - 26% open · ⏱️ 10.02.2021):
git clone https://github.com/airbnb/streamalert
baikal (🥉20 · ⭐ 570) - A graph-based functional API for building complex scikit-learn pipelines. BSD-3
alibi-detect (🥉20 · ⭐ 560) - Algorithms for outlier and adversarial instance detection,.. Apache-2
scikit-rebate (🥉20 · ⭐ 310) - A scikit-learn-compatible Python implementation of ReBATE, a.. MIT
apricot (🥉19 · ⭐ 300) - apricot implements submodular optimization for the purpose of selecting.. MIT
Feature Engine (🥉18 · ⭐ 450) - Feature engineering package with sklearn like functionality. BSD-3
River (🥉17 · ⭐ 1.4K) - Online machine learning in Python. BSD-3
-
GitHub (👨💻 58 · 🔀 180 · 📋 290 - 13% open · ⏱️ 16.02.2021):
git clone https://github.com/online-ml/river
traingenerator (🥉10 · ⭐ 930 · 🐣) - A web app to generate template code for machine learning. MIT
-
GitHub (👨💻 3 · 🔀 120 · 📋 12 - 75% open · ⏱️ 20.01.2021):
git clone https://github.com/jrieke/traingenerator
Show 6 hidden projects...
- Autograd (🥇29 · ⭐ 5.1K · 💀) - Efficiently computes derivatives of numpy code.
MIT
- pysc2 (🥉23 · ⭐ 7.2K · 💀) - StarCraft II Learning Environment.
Apache-2
- minisom (🥉22 · ⭐ 770) - MiniSom is a minimalistic implementation of the Self Organizing..
❗️CC-BY-3.0
- impyute (🥉20 · ⭐ 270 · 💀) - Data imputations library to preprocess datasets with missing data.
MIT
- vecstack (🥉18 · ⭐ 580 · 💀) - Python package for stacking (machine learning technique).
MIT
- pandas-ml (🥉17 · ⭐ 270 · 💀) - pandas, scikit-learn, xgboost and seaborn integration.
BSD-3
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.