Skip to content

Update README with new and existing PyTorch libraries #149

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
abhinavsriva wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update README with new and existing PyTorch libraries #149

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
89 changes: 45 additions & 44 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,50 +238,51 @@ This library contains a PyTorch implementation of the SO(3) equivariant CNNs for
110. [wavetorch](https://github.com/fancompute/wavetorch): Numerically solving and backpropagating through the wave equation arxiv.org/abs/1904.12831
111. [diffdist](https://github.com/ag14774/diffdist): diffdist is a python library for pytorch. It extends the default functionality of torch.autograd and adds support for differentiable communication between processes.
112. [torchprof](https://github.com/awwong1/torchprof): A minimal dependency library for layer-by-layer profiling of Pytorch models.
113. [osqpth](https://github.com/oxfordcontrol/osqpth): The differentiable OSQP solver layer for PyTorch.
114. [mctorch](https://github.com/mctorch/mctorch): A manifold optimization library for deep learning.
115. [pytorch-hessian-eigenthings](https://github.com/noahgolmant/pytorch-hessian-eigenthings): Efficient PyTorch Hessian eigendecomposition using the Hessian-vector product and stochastic power iteration.
116. [MinkowskiEngine](https://github.com/StanfordVL/MinkowskiEngine): Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors.
117. [pytorch-cpp-rl](https://github.com/Omegastick/pytorch-cpp-rl): PyTorch C++ Reinforcement Learning
118. [pytorch-toolbelt](https://github.com/BloodAxe/pytorch-toolbelt): PyTorch extensions for fast R&D prototyping and Kaggle farming
119. [argus-tensor-stream](https://github.com/Fonbet/argus-tensor-stream): A library for real-time video stream decoding to CUDA memory tensorstream.argus-ai.com
120. [macarico](https://github.com/hal3/macarico): learning to search in pytorch
121. [rlpyt](https://github.com/astooke/rlpyt): Reinforcement Learning in PyTorch
122. [pywarm](https://github.com/blue-season/pywarm): A cleaner way to build neural networks for PyTorch. blue-season.github.io/pywarm
123. [learn2learn](https://github.com/learnables/learn2learn): PyTorch Meta-learning Framework for Researchers http://learn2learn.net
124. [torchbeast](https://github.com/facebookresearch/torchbeast): A PyTorch Platform for Distributed RL
125. [higher](https://github.com/facebookresearch/higher): higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
126. [Torchelie](https://github.com/Vermeille/Torchelie/): Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch. torchelie.readthedocs.org
127. [CrypTen](https://github.com/facebookresearch/CrypTen): CrypTen is a Privacy Preserving Machine Learning framework written using PyTorch that allows researchers and developers to train models using encrypted data. CrypTen currently supports Secure multi-party computation as its encryption mechanism.
128. [cvxpylayers](https://github.com/cvxgrp/cvxpylayers): cvxpylayers is a Python library for constructing differentiable convex optimization layers in PyTorch
129. [RepDistiller](https://github.com/HobbitLong/RepDistiller): Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
130. [kaolin](https://github.com/NVIDIAGameWorks/kaolin): PyTorch library aimed at accelerating 3D deep learning research
131. [PySNN](https://github.com/BasBuller/PySNN): Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration.
132. [sparktorch](https://github.com/dmmiller612/sparktorch): Train and run Pytorch models on Apache Spark.
133. [pytorch-metric-learning](https://github.com/KevinMusgrave/pytorch-metric-learning): The easiest way to use metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
134. [autonomous-learning-library](https://github.com/cpnota/autonomous-learning-library): A PyTorch library for building deep reinforcement learning agents.
135. [flambe](https://github.com/asappresearch/flambe): An ML framework to accelerate research and its path to production. flambe.ai
136. [pytorch-optimizer](https://github.com/jettify/pytorch-optimizer): Collections of modern optimization algorithms for PyTorch, includes: AccSGD, AdaBound, AdaMod, DiffGrad, Lamb, RAdam, RAdam, Yogi.
137. [PyTorch-VAE](https://github.com/AntixK/PyTorch-VAE): A Collection of Variational Autoencoders (VAE) in PyTorch.
138. [ray](https://github.com/ray-project/ray): A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library. ray.io
139. [Pytorch Geometric Temporal](https://github.com/benedekrozemberczki/pytorch_geometric_temporal): A temporal extension library for PyTorch Geometric
140. [Poutyne](https://github.com/GRAAL-Research/poutyne): A Keras-like framework for PyTorch that handles much of the boilerplating code needed to train neural networks.
141. [Pytorch-Toolbox](https://github.com/PistonY/torch-toolbox): This is toolbox project for Pytorch. Aiming to make you write Pytorch code more easier, readable and concise.
142. [Pytorch-contrib](https://github.com/pytorch/contrib): It contains reviewed implementations of ideas from recent machine learning papers.
143. [EfficientNet PyTorch](https://github.com/lukemelas/EfficientNet-PyTorch): It contains an op-for-op PyTorch reimplementation of EfficientNet, along with pre-trained models and examples.
144. [PyTorch/XLA](https://github.com/pytorch/xla): PyTorch/XLA is a Python package that uses the XLA deep learning compiler to connect the PyTorch deep learning framework and Cloud TPUs.
145. [webdataset](https://github.com/tmbdev/webdataset): WebDataset is a PyTorch Dataset (IterableDataset) implementation providing efficient access to datasets stored in POSIX tar archives.
146. [volksdep](https://github.com/Media-Smart/volksdep): volksdep is an open-source toolbox for deploying and accelerating PyTorch, Onnx and Tensorflow models with TensorRT.
147. [PyTorch-StudioGAN](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN): StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation. StudioGAN aims to offer an identical playground for modern GANs so that machine learning researchers can readily compare and analyze a new idea.
148. [torchdrift](https://github.com/torchdrift/torchdrift/): drift detection library
149. [accelerate](https://github.com/huggingface/accelerate) : A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
150. [lightning-transformers](https://github.com/PyTorchLightning/lightning-transformers): Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.
151. [Flower](https://flower.dev/) A unified approach to federated learning, analytics, and evaluation. It allows to federated any machine learning workload.
152. [lightning-flash](https://github.com/PyTorchLightning/lightning-flash): Flash is a collection of tasks for fast prototyping, baselining and fine-tuning scalable Deep Learning models, built on PyTorch Lightning.
153. [Pytorch Geometric Signed Directed](https://github.com/SherylHYX/pytorch_geometric_signed_directed): A signed and directed extension library for PyTorch Geometric.
154. [Koila](https://github.com/rentruewang/koila): A simple wrapper around pytorch that prevents CUDA out of memory issues.
155. [Renate](https://github.com/awslabs/renate): A library for real-world continual learning.
156. [ANEE](https://github.com/abkmystery/ANEE) – Adaptive Neural Execution Engine for PyTorch transformers. Provides per-token dynamic layer skipping, profiler-based gating, and KV-cache-safe sparse inference.
113. [TraceML](https://github.com/traceopt-ai/traceml): PyTorch DDP training observability with per-rank step timing, skew detection, and step breakdown (dataloader, forward, backward).
114. [osqpth](https://github.com/oxfordcontrol/osqpth): The differentiable OSQP solver layer for PyTorch.
115. [mctorch](https://github.com/mctorch/mctorch): A manifold optimization library for deep learning.
116. [pytorch-hessian-eigenthings](https://github.com/noahgolmant/pytorch-hessian-eigenthings): Efficient PyTorch Hessian eigendecomposition using the Hessian-vector product and stochastic power iteration.
117. [MinkowskiEngine](https://github.com/StanfordVL/MinkowskiEngine): Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors.
118. [pytorch-cpp-rl](https://github.com/Omegastick/pytorch-cpp-rl): PyTorch C++ Reinforcement Learning
119. [pytorch-toolbelt](https://github.com/BloodAxe/pytorch-toolbelt): PyTorch extensions for fast R&D prototyping and Kaggle farming
120. [argus-tensor-stream](https://github.com/Fonbet/argus-tensor-stream): A library for real-time video stream decoding to CUDA memory tensorstream.argus-ai.com
121. [macarico](https://github.com/hal3/macarico): learning to search in pytorch
122. [rlpyt](https://github.com/astooke/rlpyt): Reinforcement Learning in PyTorch
123. [pywarm](https://github.com/blue-season/pywarm): A cleaner way to build neural networks for PyTorch. blue-season.github.io/pywarm
124. [learn2learn](https://github.com/learnables/learn2learn): PyTorch Meta-learning Framework for Researchers http://learn2learn.net
125. [torchbeast](https://github.com/facebookresearch/torchbeast): A PyTorch Platform for Distributed RL
126. [higher](https://github.com/facebookresearch/higher): higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
127. [Torchelie](https://github.com/Vermeille/Torchelie/): Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch. torchelie.readthedocs.org
128. [CrypTen](https://github.com/facebookresearch/CrypTen): CrypTen is a Privacy Preserving Machine Learning framework written using PyTorch that allows researchers and developers to train models using encrypted data. CrypTen currently supports Secure multi-party computation as its encryption mechanism.
129. [cvxpylayers](https://github.com/cvxgrp/cvxpylayers): cvxpylayers is a Python library for constructing differentiable convex optimization layers in PyTorch
130. [RepDistiller](https://github.com/HobbitLong/RepDistiller): Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
131. [kaolin](https://github.com/NVIDIAGameWorks/kaolin): PyTorch library aimed at accelerating 3D deep learning research
132. [PySNN](https://github.com/BasBuller/PySNN): Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration.
133. [sparktorch](https://github.com/dmmiller612/sparktorch): Train and run Pytorch models on Apache Spark.
134. [pytorch-metric-learning](https://github.com/KevinMusgrave/pytorch-metric-learning): The easiest way to use metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
135. [autonomous-learning-library](https://github.com/cpnota/autonomous-learning-library): A PyTorch library for building deep reinforcement learning agents.
136. [flambe](https://github.com/asappresearch/flambe): An ML framework to accelerate research and its path to production. flambe.ai
137. [pytorch-optimizer](https://github.com/jettify/pytorch-optimizer): Collections of modern optimization algorithms for PyTorch, includes: AccSGD, AdaBound, AdaMod, DiffGrad, Lamb, RAdam, RAdam, Yogi.
138. [PyTorch-VAE](https://github.com/AntixK/PyTorch-VAE): A Collection of Variational Autoencoders (VAE) in PyTorch.
139. [ray](https://github.com/ray-project/ray): A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library. ray.io
140. [Pytorch Geometric Temporal](https://github.com/benedekrozemberczki/pytorch_geometric_temporal): A temporal extension library for PyTorch Geometric
141. [Poutyne](https://github.com/GRAAL-Research/poutyne): A Keras-like framework for PyTorch that handles much of the boilerplating code needed to train neural networks.
142. [Pytorch-Toolbox](https://github.com/PistonY/torch-toolbox): This is toolbox project for Pytorch. Aiming to make you write Pytorch code more easier, readable and concise.
143. [Pytorch-contrib](https://github.com/pytorch/contrib): It contains reviewed implementations of ideas from recent machine learning papers.
144. [EfficientNet PyTorch](https://github.com/lukemelas/EfficientNet-PyTorch): It contains an op-for-op PyTorch reimplementation of EfficientNet, along with pre-trained models and examples.
145. [PyTorch/XLA](https://github.com/pytorch/xla): PyTorch/XLA is a Python package that uses the XLA deep learning compiler to connect the PyTorch deep learning framework and Cloud TPUs.
146. [webdataset](https://github.com/tmbdev/webdataset): WebDataset is a PyTorch Dataset (IterableDataset) implementation providing efficient access to datasets stored in POSIX tar archives.
147. [volksdep](https://github.com/Media-Smart/volksdep): volksdep is an open-source toolbox for deploying and accelerating PyTorch, Onnx and Tensorflow models with TensorRT.
148. [PyTorch-StudioGAN](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN): StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation. StudioGAN aims to offer an identical playground for modern GANs so that machine learning researchers can readily compare and analyze a new idea.
149. [torchdrift](https://github.com/torchdrift/torchdrift/): drift detection library
150. [accelerate](https://github.com/huggingface/accelerate) : A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
151. [lightning-transformers](https://github.com/PyTorchLightning/lightning-transformers): Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.
152. [Flower](https://flower.dev/) A unified approach to federated learning, analytics, and evaluation. It allows to federated any machine learning workload.
153. [lightning-flash](https://github.com/PyTorchLightning/lightning-flash): Flash is a collection of tasks for fast prototyping, baselining and fine-tuning scalable Deep Learning models, built on PyTorch Lightning.
154. [Pytorch Geometric Signed Directed](https://github.com/SherylHYX/pytorch_geometric_signed_directed): A signed and directed extension library for PyTorch Geometric.
155. [Koila](https://github.com/rentruewang/koila): A simple wrapper around pytorch that prevents CUDA out of memory issues.
156. [Renate](https://github.com/awslabs/renate): A library for real-world continual learning.
157. [ANEE](https://github.com/abkmystery/ANEE) – Adaptive Neural Execution Engine for PyTorch transformers. Provides per-token dynamic layer skipping, profiler-based gating, and KV-cache-safe sparse inference.


## Tutorials, books, & examples
Expand Down