jiant: The jiant sentence representation learning toolkit.
BERT-PyTorch: Pytorch implementation of Google AI's 2018 BERT, with simple annotation
InferSent: Sentence embeddings (InferSent) and training code for NLI.
uis-rnn:This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization. arxiv.org/abs/1810.04719
flair: A very simple framework for state-of-the-art Natural Language Processing (NLP)
pytext: A natural language modeling framework based on PyTorch fb.me/pytextdocs
transfer-nlp: NLP library designed for flexible research and development
texar-pytorch: Toolkit for Machine Learning and Text Generation, in PyTorch texar.io
pytorch-kaldi: pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
NeMo: Neural Modules: a toolkit for conversational AI nvidia.github.io/NeMo
pytorch-struct: A library of vectorized implementations of core structured prediction algorithms (HMM, Dep Trees, CKY, ..,)
espresso: Espresso: A Fast End-to-End Neural Speech Recognition Toolkit
transformers: huggingface Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch. huggingface.co/transformers
reformer-pytorch: Reformer, the efficient Transformer, in Pytorch
torch-metrics: Metrics for model evaluation in pytorch
CV:
pytorch vision: Datasets, Transforms and Models specific to Computer Vision.
RoIAlign.pytorch: This is a PyTorch version of RoIAlign. This implementation is based on crop_and_resize and supports both forward and backward on CPU and GPU.
pytorch-cnn-finetune: Fine-tune pretrained Convolutional Neural Networks with PyTorch.
s2cnn:
This library contains a PyTorch implementation of the SO(3) equivariant CNNs for spherical signals (e.g. omnidirectional cameras, signals on the globe)
TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision.
maskrcnn-benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
functional zoo: PyTorch, unlike lua torch, has autograd in it's core, so using modular structure of torch.nn modules is not necessary, one can easily allocate needed Variables and write a function that utilizes them, which is sometimes more convenient. This repo contains model definitions in this functional way, with pretrained weights for some models.
torch-sampling: This package provides a set of transforms and data structures for sampling from in-memory or out-of-memory data.
torchcraft-py: Python wrapper for TorchCraft, a bridge between Torch and StarCraft for AI research.
aorun: Aorun intend to be a Keras with PyTorch as backend.
pytorch-extension: This is a CUDA extension for PyTorch which computes the Hadamard product of two tensors.
tensorboard-pytorch: This module saves PyTorch tensors in tensorboard format for inspection. Currently supports scalar, image, audio, histogram features in tensorboard.
gpytorch: GPyTorch is a Gaussian Process library, implemented using PyTorch. It is designed for creating flexible and modular Gaussian Process models with ease, so that you don't have to be an expert to use GPs.
pytorch-ctc: PyTorch-CTC is an implementation of CTC (Connectionist Temporal Classification) beam search decoding for PyTorch. C++ code borrowed liberally from TensorFlow with some improvements to increase flexibility.
opencv_transforms: OpenCV implementation of Torchvision's image augmentations
fastai: The fast.ai deep learning library, lessons, and tutorials
pytorch-dense-correspondence: Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation" arxiv.org/pdf/1806.08756.pdf
colorization-pytorch: PyTorch reimplementation of Interactive Deep Colorization richzhang.github.io/ideepcolor
beauty-net: A simple, flexible, and extensible template for PyTorch. It's beautiful.
OpenChem: OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research mariewelt.github.io/OpenChem
torchani: Accurate Neural Network Potential on PyTorch aiqm.github.io/torchani
Tor10: A Generic Tensor-Network library that is designed for quantum simulation, base on the pytorch.
Catalyst: High-level utils for PyTorch DL & RL research. It was developed with a focus on reproducibility, fast experimentation and code/ideas reusing. Being able to research/develop something new, rather than write another regular train loop.
pywick: High-level batteries-included neural network training library for Pytorch
torchgpipe: A GPipe implementation in PyTorch torchgpipe.readthedocs.io
hub: Pytorch Hub is a pre-trained model repository designed to facilitate research reproducibility.
pytorch-lightning: Rapid research framework for Pytorch. The researcher's version of keras.
Tor10: A Generic Tensor-Network library that is designed for quantum simulation, base on the pytorch.
tensorwatch: Debugging, monitoring and visualization for Deep Learning and Reinforcement Learning from Microsoft Research.
wavetorch: Numerically solving and backpropagating through the wave equation arxiv.org/abs/1904.12831
diffdist: diffdist is a python library for pytorch. It extends the default functionality of torch.autograd and adds support for differentiable communication between processes.
torchprof: A minimal dependency library for layer-by-layer profiling of Pytorch models.
osqpth: The differentiable OSQP solver layer for PyTorch.
mctorch: A manifold optimization library for deep learning.
pytorch-hessian-eigenthings: Efficient PyTorch Hessian eigendecomposition using the Hessian-vector product and stochastic power iteration.
MinkowskiEngine: Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors.
higher: higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
Torchelie: Torchélie is a set of utility functions, layers, losses, models, trainers and other things for PyTorch. torchelie.readthedocs.org
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.
cvxpylayers: cvxpylayers is a Python library for constructing differentiable convex optimization layers in PyTorch
RepDistiller: Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
kaolin: PyTorch library aimed at accelerating 3D deep learning research
PySNN: Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration.
sparktorch: Train and run Pytorch models on Apache Spark.
pytorch-metric-learning: The easiest way to use metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
flambe: An ML framework to accelerate research and its path to production. flambe.ai
pytorch-optimizer: Collections of modern optimization algorithms for PyTorch, includes: AccSGD, AdaBound, AdaMod, DiffGrad, Lamb, RAdam, RAdam, Yogi.
PyTorch-VAE: A Collection of Variational Autoencoders (VAE) in PyTorch.
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
cats vs dogs: Example of network fine-tuning in pytorch for the kaggle competition Dogs vs. Cats Redux: Kernels Edition. Currently #27 (0.05074) on the leaderboard.
convnet: This is a complete training example for Deep Convolutional Networks on various datasets (ImageNet, Cifar10, Cifar100, MNIST).
pytorch containers: This repository aims to help former Torchies more seamlessly transition to the "Containerless" world of PyTorch by providing a list of PyTorch implementations of Torch Table Layers.
pytorch_tutoria-quick: Quick PyTorch introduction and tutorial. Targets computer vision, graphics and machine learning researchers eager to try a new framework.
cifar10-fast:
Demonstration of training a small ResNet on CIFAR10 to 94% test accuracy in 79 seconds as described in this blog series.
Intro to Deep Learning with PyTorch: A free course by Udacity and facebook, with a good intro to PyTorch, and an interview with Soumith Chintala, one of the original authors of PyTorch.
pytorch-sentiment-analysis: Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
pytorch-image-models: PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet, and more.
CIFAR-ZOO: Pytorch implementation for multiple CNN architectures and improve methods with state-of-the-art results.
d2l-pytorch: This is an attempt to modify Dive into Deep Learning, Berkeley STAT 157 (Spring 2019) textbook's code into PyTorch.
SentimentAnalysis: Sentiment analysis neural network trained by fine tuning BERT on the Stanford Sentiment Treebank, thanks to Hugging Face's Transformers library.
pytorch-cpp: C++ implementations of PyTorch tutorials for deep learning researchers (based on the Python tutorials from pytorch-tutorial).
Deep Learning with PyTorch: Deep Learning with PyTorch teaches you how to implement deep learning algorithms with Python and PyTorch, the book includes a case study: building an algorithm capable of detecting malignant lung tumors using CT scans.
Serverless Machine Learning in Action with PyTorch and AWS: Serverless Machine Learning in Action is a guide to bringing your experimental PyTorch machine learning code to production using serverless capabilities from major cloud providers like AWS, Azure, or GCP.
LabML NN: A collection of PyTorch implementations of neural networks architectures and algorithms with side-by-side notes.
Paper implementations
google_evolution: This implements one of result networks from Large-scale evolution of image classifiers by Esteban Real, et. al.
pyscatwave: Fast Scattering Transform with CuPy/PyTorch,read the paper here
scalingscattering: Scaling The Scattering Transform : Deep Hybrid Networks.
deep-auto-punctuation: a pytorch implementation of auto-punctuation learned character by character.
pytorch-NeuCom: Pytorch implementation of DeepMind's differentiable neural computer paper.
captionGen: Generate captions for an image using PyTorch.
AnimeGAN: A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.
Cnn-text classification: This is the implementation of Kim's Convolutional Neural Networks for Sentence Classification paper in PyTorch.
deepspeech2: Implementation of DeepSpeech2 using Baidu Warp-CTC. Creates a network based on the DeepSpeech2 architecture, trained with the CTC activation function.
seq2seq: This repository contains implementations of Sequence to Sequence (Seq2Seq) models in PyTorch
Asynchronous Advantage Actor-Critic in PyTorch: This is PyTorch implementation of A3C as described in Asynchronous Methods for Deep Reinforcement Learning. Since PyTorch has a easy method to control shared memory within multiprocess, we can easily implement asynchronous method like A3C.
densenet: This is a PyTorch implementation of the DenseNet-BC architecture as described in the paper Densely Connected Convolutional Networks by G. Huang, Z. Liu, K. Weinberger, and L. van der Maaten. This implementation gets a CIFAR-10+ error rate of 4.77 with a 100-layer DenseNet-BC with a growth rate of 12. Their official implementation and links to many other third-party implementations are available in the liuzhuang13/DenseNet repo on GitHub.
nninit: Weight initialization schemes for PyTorch nn.Modules. This is a port of the popular nninit for Torch7 by @kaixhin.
faster rcnn: This is a PyTorch implementation of Faster RCNN. This project is mainly based on py-faster-rcnn and TFFRCNN.For details about R-CNN please refer to the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.
doomnet: PyTorch's version of Doom-net implementing some RL models in ViZDoom environment.
flownet: Pytorch implementation of FlowNet by Dosovitskiy et al.
sqeezenet: Implementation of Squeezenet in pytorch, #### pretrained models on CIFAR10 data to come Plan to train the model on cifar 10 and add block connections too.
optnet: This repository is by Brandon Amos and J. Zico Kolter and contains the PyTorch source code to reproduce the experiments in our paper OptNet: Differentiable Optimization as a Layer in Neural Networks.
qp solver: A fast and differentiable QP solver for PyTorch. Crafted by Brandon Amos and J. Zico Kolter.
GAN-weight-norm: Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"
lgamma: Implementations of polygamma, lgamma, and beta functions for PyTorch
bigBatch: Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"
rl_a3c_pytorch: Reinforcement learning with implementation of A3C LSTM for Atari 2600.
pytorch-retraining: Transfer Learning Shootout for PyTorch's model zoo (torchvision)
nmp_qc: Neural Message Passing for Computer Vision
face-alignment: Pytorch implementation of the paper "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)", ICCV 2017
DepthNet: PyTorch DepthNet Training on Still Box dataset.
EDSR-PyTorch: PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
e2c-pytorch: Embed to Control implementation in PyTorch.
bandit-nmt: This is code repo for our EMNLP 2017 paper "Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback", which implements the A2C algorithm on top of a neural encoder-decoder model and benchmarks the combination under simulated noisy rewards.
pytorch-a2c-ppo-acktr: PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
skip-gram-pytorch: A complete pytorch implementation of skipgram model (with subsampling and negative sampling). The embedding result is tested with Spearman's rank correlation.
stackGAN-v2: Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks by Han Zhang*, Tao Xu*, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas.
self-critical.pytorch: Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning.
pytorch-capsule: Pytorch implementation of Hinton's Dynamic Routing Between Capsules.
PyramidNet-PyTorch: A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks, arxiv.org/abs/1610.02915)
radio-transformer-networks: A PyTorch implementation of Radio Transformer Networks from the paper "An Introduction to Deep Learning for the Physical Layer". arxiv.org/abs/1702.00832
honk: PyTorch reimplementation of Google's TensorFlow CNNs for keyword spotting.
DeepCORAL: A PyTorch implementation of 'Deep CORAL: Correlation Alignment for Deep Domain Adaptation.', ECCV 2016
pytorch-pose: A PyTorch toolkit for 2D Human Pose Estimation.
lang-emerge-parlai: Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI
Rainbow: Rainbow: Combining Improvements in Deep Reinforcement Learning
pytorch_compact_bilinear_pooling v1: This repository has a pure Python implementation of Compact Bilinear Pooling and Count Sketch for PyTorch.
yolo2-pytorch: The YOLOv2 is one of the most popular one-stage object detector. This project adopts PyTorch as the developing framework to increase productivity, and utilize ONNX to convert models into Caffe 2 to benifit engineering deployment.
reseg-pytorch: PyTorch Implementation of ReSeg (arxiv.org/pdf/1511.07053.pdf)
pytorch-pose-estimation: PyTorch Implementation of Realtime Multi-Person Pose Estimation project.
interaction_network_pytorch: Pytorch Implementation of Interaction Networks for Learning about Objects, Relations and Physics.
NoisyNaturalGradient: Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference".
ewc.pytorch: An implementation of Elastic Weight Consolidation (EWC), proposed in James Kirkpatrick et al. Overcoming catastrophic forgetting in neural networks 2016(10.1073/pnas.1611835114).
pytorch-zssr: PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning
deep_image_prior: An implementation of image reconstruction methods from Deep Image Prior (Ulyanov et al., 2017) in PyTorch.
minimal_glo: Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"
LearningToCompare-Pytorch: Pytorch Implementation for Paper: Learning to Compare: Relation Network for Few-Shot Learning.
poincare-embeddings: PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations".
pytorch-trpo(Hessian-vector product version): This is a PyTorch implementation of "Trust Region Policy Optimization (TRPO)" with exact Hessian-vector product instead of finite differences approximation.
ggnn.pytorch: A PyTorch Implementation of Gated Graph Sequence Neural Networks (GGNN).
Structured-Self-Attention: Implementation for the paper A Structured Self-Attentive Sentence Embedding, which is published in ICLR 2017: arxiv.org/abs/1703.03130 .
Detectron.pytorch: A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
R2Plus1D-PyTorch: PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"
StackNN: A PyTorch implementation of differentiable stacks for use in neural networks.
translagent: Code for Emergent Translation in Multi-Agent Communication.
ban-vqa: Bilinear attention networks for visual question answering.
pytorch-openai-transformer-lm: This is a PyTorch implementation of the TensorFlow code provided with OpenAI's paper "Improving Language Understanding by Generative Pre-Training" by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever.
T2F: Text-to-Face generation using Deep Learning. This project combines two of the recent architectures StackGAN and ProGAN for synthesizing faces from textual descriptions.
pytorch - fid: A Port of Fréchet Inception Distance (FID score) to PyTorch
vae_vpflows:Code in PyTorch for the convex combination linear IAF and the Householder Flow, J.M. Tomczak & M. Welling jmtomczak.github.io/deebmed.html
CoordConv-pytorch: Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (arxiv.org/pdf/1807.03247.pdf)
SDPoint: Implementation of "Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks", published in CVPR 2018.
PNASNet.pytorch: PyTorch implementation of PNASNet-5 on ImageNet.
NALU-pytorch: Basic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units arxiv.org/pdf/1808.00508.pdf
LOLA_DiCE: Pytorch implementation of LOLA (arxiv.org/abs/1709.04326) using DiCE (arxiv.org/abs/1802.05098)
generative-query-network-pytorch: Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"
pytorch_hmax: Implementation of the HMAX model of vision in PyTorch.
FCN-pytorch-easiest: trying to be the most easiest and just get-to-use pytorch implementation of FCN (Fully Convolotional Networks)
transducer: A Fast Sequence Transducer Implementation with PyTorch Bindings.
AVO-pytorch: Implementation of Adversarial Variational Optimization in PyTorch.
HCN-pytorch: A pytorch reimplementation of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.
binary-wide-resnet: PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnel (ICLR 2018)
piggyback: Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights arxiv.org/abs/1801.06519
vid2vid: Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
tbd-nets: PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning" arxiv.org/abs/1803.05268
attn2d: Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction
yolov3: YOLOv3: Training and inference in PyTorch pjreddie.com/darknet/yolo
deep-dream-in-pytorch: Pytorch implementation of the DeepDream computer vision algorithm.
pytorch-flows: PyTorch implementations of algorithms for density estimation
Face_Attention_Network: Pytorch implementation of face attention network as described in Face Attention Network: An Effective Face Detector for the Occluded Faces.
waveglow: A Flow-based Generative Network for Speech Synthesis.
deepfloat: This repository contains the SystemVerilog RTL, C++, HLS (Intel FPGA OpenCL to wrap RTL code) and Python needed to reproduce the numerical results in "Rethinking floating point for deep learning"
ClariNet: A Pytorch Implementation of ClariNet arxiv.org/abs/1807.07281
pytorch-pretrained-BERT: PyTorch version of Google AI's BERT model with script to load Google's pre-trained models
torch_waveglow: A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis.
3DDFA: The pytorch improved re-implementation of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
loss-landscape: loss-landscape Code for visualizing the loss landscape of neural nets.
famos:
Pytorch implementation of the paper "Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization" available at http://arxiv.org/abs/1811.09236.
back2future.pytorch: This is a Pytorch implementation of
Janai, J., Güney, F., Ranjan, A., Black, M. and Geiger, A., Unsupervised Learning of Multi-Frame Optical Flow with Occlusions. ECCV 2018.
FFTNet: Unofficial Implementation of FFTNet vocode paper.
simple-effective-text-matching-pytorch: A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Adaptive-segmentation-mask-attack (ASMA): A pytorch implementation of the MICCAI2019 paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation".
ML Workspace: All-in-one web IDE for machine learning and data science. Combines Jupyter, VS Code, PyTorch, and many other tools/libraries into one Docker image.
PyTorch Style Guide Style guide for PyTorch code. Consistent and good code style helps collaboration and prevents errors!
Feedback: If you have any ideas or you want any other content to be added to this list, feel free to contribute.