Soumith Chintala

Coauthor of PyTorch

Authored Projects (1)

Starred by

Aravind Srinivas

Aravind Srinivas(Cofounder of Perplexity),

Lilian Weng

Lilian Weng(Cofounder of Thinking Machines Lab),

Elie Bursztein

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Stefan van der Walt

Stefan van der Walt(Core Contributor to scientific Python ecosystem), and

23 more.

ganhacks by soumith

GAN training tips and tricks

Input normalization between -1 and 1, Tanh output.
Modified loss function, label flipping.
Spherical Z sampling from Gaussian distribution.
BatchNorm, Instance Normalization.
LeakyReLU, Average Pooling, PixelShuffle.
Soft and Noisy Labels, Label Smoothing.
DCGAN, ADAM Optimizer.

Created 8 years ago

Updated 3 years ago

Starred Projects (92)

opencode by opencode-ai

CLI tool for terminal-based AI coding assistance

tobi:

didierrlopes:

jrk:

schickling:

Created 6 months ago

Updated 19 hours ago

codemcp by ezyang

Coding assistant for Claude Desktop, enabling code edits and testing

willccbb:

Created 6 months ago

Updated 3 months ago

ao by pytorch

PyTorch library for quantization and sparsity in training/inference

parano:

willccbb:

alexchen4ai:

luiscape:

Created 1 year ago

Updated 20 hours ago

torchtitan by pytorch

PyTorch platform for generative AI model training research

karpathy:

lewtun:

zhuohan123:

CodeCreator:

Created 1 year ago

Updated 19 hours ago

torchtune by pytorch

PyTorch library for LLM post-training and experimentation

zhyncs:

lewtun:

patrickvonplaten:

JustinLin610:

Created 1 year ago

Updated 1 day ago

llm.c by karpathy

LLM training in pure C/CUDA, no PyTorch needed

norvig:

alexey-milovidov:

didierrlopes:

hiyouga:

Created 1 year ago

Updated 2 months ago

speechbrain by speechbrain

PyTorch toolkit for speech and text processing research

transitive-bullshit:

spahl:

soldni:

tridao:

Created 5 years ago

Updated 1 month ago

search_with_lepton by leptonai

Conversational search engine demo

chiphuyen:

zhiyuan8:

khou22:

zhuohan123:

Created 1 year ago

Updated 2 weeks ago

text-generation-webui by oobabooga

Web UI for LLM text generation

vincentweisser:

shimmyshimmer:

doriandarko:

JohannesHa:

Created 2 years ago

Updated 17 hours ago

gpt-fast by meta-pytorch

PyTorch text generation for efficient transformer inference

karpathy:

antiagainst:

jamesr66a:

merrymercy:

Created 1 year ago

Updated 3 weeks ago

open_flamingo by mlfoundations

Open-source framework for training large multimodal models

chiphuyen:

winglian:

osanseviero:

hammer:

Created 2 years ago

Updated 1 year ago

nanoGPT by karpathy

Minimalist repo for training/finetuning GPT models

tobi:

danielgross:

chiphuyen:

ankane:

Created 2 years ago

Updated 9 months ago

disco-diffusion by alembics

AI art and animation notebook

chenlin9:

taranjeet:

patrickvonplaten:

Jiayi-Pan:

Created 3 years ago

Updated 2 years ago

cleanlab by cleanlab

Data-centric AI package for ML with messy data

chiphuyen:

alexanderatallah:

transitive-bullshit:

simonw:

Created 7 years ago

Updated 1 week ago

CLIP by openai

Image-text matching model for zero-shot prediction

aravindsrinivas:

transitive-bullshit:

Edward-Sun:

mholt:

Created 4 years ago

Updated 1 year ago

minGPT by karpathy

Minimal PyTorch re-implementation for GPT training and inference

aravindsrinivas:

nat:

geohot:

lilianweng:

Created 5 years ago

Updated 1 year ago

stable-baselines3 by DLR-RM

PyTorch library for reinforcement learning algorithm implementations

chiphuyen:

ogabrielluiz:

thomwolf:

JohannesHa:

Created 5 years ago

Updated 5 days ago

PhiFlow by tum-pbs

Differentiable PDE solving framework for ML research

Edward-Sun:

lantiga:

rromb:

Created 5 years ago

Updated 1 month ago

jukebox by openai

Generative model for music research paper

aravindsrinivas:

gaearon:

lewtun:

schickling:

Created 5 years ago

Updated 1 year ago

TensorRT by pytorch

PyTorch compiler for NVIDIA GPUs using TensorRT

lantiga:

luiscape:

codekansas:

Created 5 years ago

Updated 17 hours ago

pytorch3d by facebookresearch

PyTorch3D is a PyTorch library for 3D deep learning research

aravindsrinivas:

chiphuyen:

hiyouga:

gkioxari:

Created 5 years ago

Updated 3 days ago

espresso by freewym

Fast end-to-end neural speech recognition

hammer:

Created 6 years ago

Updated 1 year ago

Megatron-LM by NVIDIA

Framework for training transformer models at scale

jiamings:

gravicle:

alexchen4ai:

parasj:

Created 6 years ago

Updated 13 hours ago

jetson-inference by dusty-nv

Vision DNN library for NVIDIA Jetson devices

chiphuyen:

parano:

Created 9 years ago

Updated 11 months ago

naacl_transfer_learning_tutorial by huggingface

NLP transfer learning tutorial code

clmnt:

hiyouga:

julien-c:

hammer:

Created 6 years ago

Updated 6 years ago

texar-pytorch by asyml

PyTorch toolkit for NLP and text generation research

ogabrielluiz:

trishume:

forresti:

Created 6 years ago

Updated 3 years ago

pytorch-kaldi by mravanelli

Speech recognition toolkit bridging PyTorch and Kaldi

tridao:

lantiga:

Created 7 years ago

Updated 3 years ago

pytorch-image-models by huggingface

PyTorch image model collection with training, eval, and inference scripts

clmnt:

karpathy:

osanseviero:

Jiayi-Pan:

Created 6 years ago

Updated 1 day ago

XLM by facebookresearch

PyTorch code for cross-lingual language model pretraining (XLM/XLM-R)

aravindsrinivas:

codekansas:

nottombrown:

trishume:

Created 6 years ago

Updated 2 years ago

spacy-course by explosion

Online course for advanced NLP with spaCy

hammer:

tiangolo:

cvalenzuela:

lysandrejik:

Created 6 years ago

Updated 7 months ago

pytorch-cpp-rl by Omegastick

RL framework using the PyTorch C++ frontend

apaszke:

rwightman:

thomwolf:

Created 6 years ago

Updated 5 years ago

pytorch-lightning by Lightning-AI

Deep learning framework for pretraining, finetuning, and deploying AI models

albertfgu:

soldni:

omarsar:

zhangce:

Created 6 years ago

Updated 23 hours ago

BigGAN-PyTorch by ajbrock

PyTorch code for BigGAN image synthesis research paper

aravindsrinivas:

jn2clark:

infwinston:

shizhediao:

Created 6 years ago

Updated 2 years ago

tch-rs by LaurentMazare

Rust bindings for PyTorch C++ API (libtorch)

sxyu:

transitive-bullshit:

parano:

apsdehal:

Created 6 years ago

Updated 1 month ago

gpt-2-Pytorch by graykode

Simple text generator with OpenAI GPT-2 PyTorch implementation

thomwolf:

Created 6 years ago

Updated 6 years ago

pytext by facebookresearch

NLP framework (deprecated, migrate to torchtext)

stas00:

lysandrejik:

chiphuyen:

codekansas:

Created 7 years ago

Updated 2 years ago

dgl by dmlc

Python package for deep learning on graphs

osanseviero:

jiamings:

xiezhq-hermann:

parasj:

Created 7 years ago

Updated 1 month ago

Made-With-ML by GokuMohandas

ML course for production-grade applications

pcmoritz:

robinjhuang:

ogabrielluiz:

chiphuyen:

Created 6 years ago

Updated 1 year ago

xla by pytorch

PyTorch on XLA devices

aravindsrinivas:

WoosukKwon:

Jiayi-Pan:

comaniac:

Created 6 years ago

Updated 1 day ago

catalyst by catalyst-team

PyTorch framework for accelerated deep learning R&D

logankilpatrick:

parasj:

chiphuyen:

luiscape:

Created 7 years ago

Updated 2 months ago

mindsdb by mindsdb

AI query engine for federated data sources

chiphuyen:

ebursztein:

shimmyshimmer:

didierrlopes:

Created 7 years ago

Updated 13 hours ago

transformers by huggingface

ML library for pretrained model inference and training

clmnt:

lilianweng:

karpathy:

tjbck:

Created 6 years ago

Updated 12 hours ago

tvm by apache

Compiler stack for deep learning systems

aravindsrinivas:

transitive-bullshit:

guberti:

wesm:

Created 9 years ago

Updated 2 days ago

pyhf by scikit-hep

HistFactory implementation for fitting/limit-setting/interval estimation

lantiga:

mattjj:

hammer:

Created 7 years ago

Updated 1 week ago

vel by MillionIntegrals

Deep-learning research library for modular model construction

millionintegrals:

nottombrown:

rwightman:

jachiam:

Created 7 years ago

Updated 2 years ago

yolov3 by ultralytics

Object detection in PyTorch > ONNX > CoreML > TFLite

khou22:

josephofiowa:

cvalenzuela:

luiscape:

Created 7 years ago

Updated 3 weeks ago

espnet by espnet

End-to-end speech processing toolkit for various speech tasks

patrickvonplaten:

codekansas:

lysandrejik:

trishume:

Created 7 years ago

Updated 3 days ago

grokking-pytorch by Kaixhin

PyTorch guide with notes on usage, best practices, and debugging

aravindsrinivas:

hammer:

eugeneyan:

iamtrask:

Created 7 years ago

Updated 4 years ago

lagom by zuoxingdong

PyTorch infrastructure for RL algorithm prototyping

apsdehal:

jachiam:

deshraj:

lantiga:

Created 7 years ago

Updated 2 years ago

pyannote-audio by pyannote

Speaker diarization toolkit

luiscape:

transitive-bullshit:

patrickvonplaten:

julien-c:

Created 9 years ago

Updated 1 day ago

DALI by NVIDIA

GPU-accelerated library for data pre-processing in deep learning

hammer:

agermanidis:

apsdehal:

cvalenzuela:

Created 7 years ago

Updated 15 hours ago

pytorch-openai-transformer-lm by huggingface

PyTorch implementation of OpenAI's Transformer LM

clmnt:

lysandrejik:

thomwolf:

nottombrown:

Created 7 years ago

Updated 4 years ago

bindsnet by BindsNET

PyTorch package for simulating spiking neural networks (SNNs)

Created 7 years ago

Updated 3 weeks ago

higgsfield by higgsfield-ai

ML framework for large model training and GPU orchestration

aravindsrinivas:

luiscape:

pgarbacki:

chiphuyen:

Created 7 years ago

Updated 1 year ago

apex by NVIDIA

PyTorch extension for streamlined mixed precision & distributed training

aravindsrinivas:

JohannesHa:

tgaddair:

hammer:

Created 7 years ago

Updated 1 week ago

tacotron2 by NVIDIA

PyTorch implementation for text-to-speech synthesis

aravindsrinivas:

patrickvonplaten:

lantiga:

jongwook:

Created 7 years ago

Updated 1 year ago

training by mlcommons

Reference implementations for MLPerf training benchmarks

shizhediao:

tiangolo:

Created 7 years ago

Updated 1 week ago

TTS by mozilla

Deep learning library for text-to-speech generation

transitive-bullshit:

ankane:

Created 7 years ago

Updated 1 year ago

jetson-reinforcement by dusty-nv

Deep RL GPU libraries for robotics on NVIDIA Jetson

Created 9 years ago

Updated 3 years ago

sentiment-discovery by NVIDIA

Language modeling and sentiment classification in PyTorch (deprecated, see Megatron-LM)

vincentweisser:

luiscape:

omarsar:

taranjeet:

Created 7 years ago

Updated 5 years ago

Rainbow by Kaixhin

Deep reinforcement learning research paper implementation

evhub:

millionintegrals:

jwyang:

iamtrask:

Created 8 years ago

Updated 3 years ago

spaCy by explosion

NLP library for production applications

aravindsrinivas:

fchollet:

nirga:

jn2clark:

Created 11 years ago

Updated 3 months ago

pytorch-a2c-ppo-acktr-gail by ikostrikov

PyTorch implementations of reinforcement learning algorithms

theophilegervet:

jachiam:

rwightman:

millionintegrals:

Created 8 years ago

Updated 3 years ago

fairseq by facebookresearch

Sequence modeling toolkit for translation, language modeling, and text generation research

lilianweng:

aravindsrinivas:

tjbck:

pathak22:

Created 8 years ago

Updated 1 week ago

DeepRLHacks by williamFalcon

RL training hacks from Deep RL Bootcamp (2017)

junxiaosong:

8enmann:

deshraj:

Created 8 years ago

Updated 8 years ago

StarData by TorchCraft

StarCraft replay dataset for AI research

denisyarats:

Created 8 years ago

Updated 4 years ago

ELF by facebookresearch

Game research platform for real-time strategy (RTS) games

jrk:

nottombrown:

AntonOsika:

deshraj:

Created 8 years ago

Updated 4 years ago

muniverse by unixpickle

RL environments for HTML5 games

aravindsrinivas:

8enmann:

deshraj:

nottombrown:

Created 8 years ago

Updated 6 years ago

pytorch-grad-cam by jacobgil

PyTorch SDK for explainable AI in computer vision

hammer:

rwightman:

rasbt:

Jiayi-Pan:

Created 8 years ago

Updated 5 months ago

rl_a3c_pytorch by dgriff777

PyTorch implementation of A3C for Atari games

zhuohan123:

junxiaosong:

ppwwyyxx:

jn2clark:

Created 8 years ago

Updated 2 years ago

pytorch-REINFORCE by chingyaoc

PyTorch implementation of REINFORCE for control tasks

Created 8 years ago

Updated 8 years ago

pytorch-rl by jingweiz

Deep RL research with PyTorch and Visdom

millionintegrals:

jwyang:

Created 8 years ago

Updated 5 years ago

pytorch-es by atgambardella

PyTorch implementation of Evolution Strategies for Markov Decision Processes

jekbradbury:

apaszke:

lantiga:

Created 8 years ago

Updated 8 years ago

the-incredible-pytorch by ritchieng

Curated list of PyTorch resources

ogabrielluiz:

philschmid:

stas00:

john-b-yang:

Created 8 years ago

Updated 1 month ago

pytorch-tutorial by yunjey

PyTorch tutorial for deep learning researchers

tjbck:

bryanhelmig:

stas00:

haotian-liu:

Created 8 years ago

Updated 2 years ago

mujoco-py by openai

Python bindings for MuJoCo physics engine

lilianweng:

aravindsrinivas:

ogabrielluiz:

evhub:

Created 9 years ago

Updated 1 year ago

faiss by facebookresearch

Similarity search library for dense vectors

lilianweng:

aravindsrinivas:

hsbt:

khou22:

Created 8 years ago

Updated 1 week ago

pytorch-CortexNet by Atcold

PyTorch implementation of the CortexNet predictive model

lantiga:

Created 8 years ago

Updated 6 years ago

OpenNMT-py by OpenNMT

PyTorch framework for neural machine translation and LLM experimentation

osanseviero:

hammer:

codekansas:

shizhediao:

Created 8 years ago

Updated 6 months ago

pytorch-a3c by ikostrikov

PyTorch implementation of A3C reinforcement learning algorithm

aravindsrinivas:

glample:

jekbradbury:

lantiga:

Created 8 years ago

Updated 6 years ago

gym-starcraft by alibaba

OpenAI Gym environment for StarCraft AI research

apsdehal:

Created 8 years ago

Updated 8 years ago

text by pytorch

PyTorch library for NLP tasks

luiscape:

eugeneyan:

artidoro:

hammer:

Created 8 years ago

Updated 1 week ago

examples by pytorch

PyTorch examples for diverse AI tasks

lilianweng:

hammer:

tjbck:

ari-holtzman:

Created 9 years ago

Updated 2 weeks ago

openai-gemm by openai

GEMM kernels for single/half precision

jrk:

jiamings:

s9xie:

deshraj:

Created 9 years ago

Updated 2 years ago

ganhacks by soumith

GAN training tips and tricks

aravindsrinivas:

lilianweng:

ebursztein:

stefanv:

Created 8 years ago

Updated 3 years ago

Neural-Photo-Editor by ajbrock

Photo editor for generative neural network research

bcherny:

cvalenzuela:

s9xie:

agermanidis:

Created 9 years ago

Updated 8 years ago

gym by openai

RL toolkit for reinforcement learning algorithm development

aravindsrinivas:

fchollet:

bcherny:

ValentaTomas:

Created 9 years ago

Updated 11 months ago

stat212b by joanbruna

DL course material (UC Berkeley, Spring 2016)

AntonOsika:

adityaramesh:

lantiga:

lukemetz:

Created 9 years ago

Updated 8 years ago

speech_recognition by Uberi

Python SDK for speech recognition, supporting online/offline engines and APIs

quincylarson:

khou22:

AntonOsika:

bfirsh:

Created 11 years ago

Updated 4 days ago

awesome-torch by carpedm20

Curated list of Torch tutorials, projects, and communities

deshraj:

jwyang:

lantiga:

Created 10 years ago

Updated 7 years ago

wer_are_we by syhw

Tracking speech recognition state-of-the-art

hammer:

trishume:

hanlint:

cournape:

Created 10 years ago

Updated 3 years ago

faster-rnnlm by yandex

Faster RNN Language Modeling Toolkit

Created 10 years ago

Updated 3 years ago

Feedback? Help us improve.