Software Design and User Interface of ESPnet-SE++
Software Design and User Interface of ESPnet-SE++: Speech Enhancement for Robust Speech Processing - Published in JOSS (2023)
sbi reloaded
sbi reloaded: a toolkit for simulation-based inference workflows - Published in JOSS (2025)
pyhf
pyhf: pure-Python implementation of HistFactory statistical models - Published in JOSS (2021)
TorchGAN
TorchGAN: A Flexible Framework for GAN Training and Evaluation - Published in JOSS (2021)
pytorch-widedeep
pytorch-widedeep: A flexible package for multimodal deep learning - Published in JOSS (2023)
normflows
normflows: A PyTorch Package for Normalizing Flows - Published in JOSS (2023)
Physics-Informed Neural networks for Advanced modeling
Physics-Informed Neural networks for Advanced modeling - Published in JOSS (2023)
Foolbox Native
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX - Published in JOSS (2020)
torchquad
torchquad: Numerical Integration in Arbitrary Dimensions with PyTorch - Published in JOSS (2021)
CCA-Zoo
CCA-Zoo: A collection of Regularized, Deep Learning based, Kernel, and Probabilistic CCA methods in a scikit-learn style framework - Published in JOSS (2021)
Caustics
Caustics: A Python Package for Accelerated Strong Gravitational Lensing Simulations - Published in JOSS (2024)
DeepHyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning - Published in JOSS (2025)
DeepRiver
DeepRiver: A Deep Learning Library for Data Streams - Published in JOSS (2025)
DeepRank2
DeepRank2: Mining 3D Protein Structures with Geometric Deep Learning - Published in JOSS (2024)
AutoEmulate
AutoEmulate: A Python package for semi-automated emulation - Published in JOSS (2025)
instances
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Delve
Delve: Neural Network Feature Variance Analysis - Published in JOSS (2022)
Nkululeko 1.0: A Python package to predict speaker characteristics with a high-level interface
Nkululeko 1.0: A Python package to predict speaker characteristics with a high-level interface - Published in JOSS (2025)
PyBCI
PyBCI: A Python Package for Brain-Computer Interface (BCI) Design - Published in JOSS (2023)
MemCNN
MemCNN: A Python/PyTorch package for creating memory-efficient invertible neural networks - Published in JOSS (2019)
MapReader
MapReader: Open software for the visual analysis of maps - Published in JOSS (2024)
FTorch
FTorch: a library for coupling PyTorch models to Fortran - Published in JOSS (2025)
FuseMedML
FuseMedML: a framework for accelerated discovery in machine learning based biomedicine - Published in JOSS (2023)
Jury
Jury: A Comprehensive Evaluation Toolkit - Published in JOSS (2024)
TorchMetrics - Measuring Reproducibility in PyTorch
TorchMetrics - Measuring Reproducibility in PyTorch - Published in JOSS (2022)
FastGeodis
FastGeodis: Fast Generalised Geodesic Distance Transform - Published in JOSS (2022)
swyft
swyft: Truncated Marginal Neural Ratio Estimation in Python - Published in JOSS (2022)
TorchSurv
TorchSurv: A Lightweight Package for Deep Survival Analysis - Published in JOSS (2024)
GNS
GNS: A generalizable Graph Neural Network-based simulator for particulate and fluid modeling - Published in JOSS (2023)
giotto-deep
giotto-deep: A Python Package for Topological Deep Learning - Published in JOSS (2022)
DIRECT
DIRECT: Deep Image REConstruction Toolkit - Published in JOSS (2022)
BlackBIRDS
BlackBIRDS: Black-Box Inference foR Differentiable Simulators - Published in JOSS (2023)
VisualTorch
VisualTorch: Streamlining Visualization for PyTorch Neural Network Architectures - Published in JOSS (2024)
GraphNeT
GraphNeT: Graph neural networks for neutrino telescope event reconstruction - Published in JOSS (2023)
Sapsan
Sapsan: Framework for Supernovae Turbulence Modeling with Machine Learning - Published in JOSS (2021)
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
deepCR
deepCR: Cosmic Ray Rejection with Deep Learning - Published in JOSS (2019)
Rainbow
Rainbow: Automated Air-Liquid Interface Cell Culture Analysis Using Deep Optical Flow - Published in JOSS (2022)
hivemind
Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
deepmd-kit
A deep learning package for many-body potential energy representation and molecular dynamics
pypots
A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputation/classification/clustering/forecasting/anomaly detection/cleaning on incomplete industrial (irregularly-sampled) multivariate TS with NaN missing values
datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
pyabsa
Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
openfold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
gladia-torchaudio
Data manipulation and transformation for audio signal processing, powered by PyTorch
edsnlp
Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.
heat
Distributed tensors and Machine Learning framework with GPU and MPI acceleration in Python
cebra
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
fuxictr
A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io
quantus
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
autopytorch
Automatic architecture search and hyperparameter optimization for PyTorch
tensorcircuit
Tensor network based quantum software framework for the NISQ era
tts
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
astrophot
A fast, flexible, automated, and differentiable astronomical image 2D forward modelling tool for precise parallel multi-wavelength photometry
tensorcircuit-ng
The next-gen tensor network based quantum software framework: superseding the original TensorCircuit
deepxde
A library for scientific machine learning and physics-informed learning
torch-pme
Particle-mesh based calculations of long-range interactions in PyTorch
pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
simulated-bifurcation
Python CPU/GPU implementation of the Simulated Bifurcation (SB) algorithm to solve quadratic optimization problems (QUBO, Ising, TSP, optimal asset allocations for a portfolio, etc.).
lumin
LUMIN - a deep learning and data science ecosystem for high-energy physics.
https://github.com/mir-group/allegro
Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic potentials
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
analogvnn
A fully modular framework for modeling and optimizing analog neural networks
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
torchxrayvision
TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
sb3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
torchrl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
voodoonet
Machine learning application for detecting liquid droplets in mixed-phase clouds using Doppler cloud radar spectra
smart-transformers
Smart Transformers are a versatile machine learning tool that can be integrated with Pytorch, TensorFlow, and JAX. Smart transformers provide accurate computations required for cryptographic algorithms. These transformers is that they are independent modules, making it efficient to experiment with various research projects related to cryptanalysis
matsciml
Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lightning, the Deep Graph Library, and PyTorch Geometric.
active-learning-as-a-service
A scalable & efficient active learning/data selection system for everyone.
avalanche-lib
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.