Machine Learning Awesome
- LLM
- Diffusion
- NLP
- GAN
- img2img
- Framework
- PyTorch
- by Meta
- tinygrad/tinygrad
- minitorch/minitorch
- micrograd
- Lightning-AI/pytorch-lightning
- Apache-2.0, Python
- JAX
- by Google
- google/maxtext
- simple, performant and scalable Jax LLM
- apple/corenet
- Paddle
- by 百度
- OpenCV
- Tensorflow
- Keras
- AutoKeras
- FastAI
- XGBoost
- LightGBM
- MegEngine
- Scikit-Learn
- microsoft/SynapseML
- MIT, Scala
- Distributed Machine Learning
- caffe
- flashlight/flashlight
- C++ standalone library for machine learning
- from Facebook AI Research Speech team, creators of Torch and Deep Speech
- arrayfire/arrayfire
- BSD-3, C++
- general purpose GPU library
- Binding: Python, Rust, Julia, NIM
- WIP: .NET, Go, Java, Lua, JS, R, Ruby
- google/jax
- Apache-2.0, Python, C++
- Autograd and XLA
- 基础计算框架
- google/flax
- neural network
- deepmind/rlax
- reinforcement learning
- deepmind/optax
- gradient processing and optimization
- deepmind/dm-haiku
- neural network
- deepmind/chex
- PyTorch
- Fineturning
- unslothai/unsloth
- Apache-2.0, Python
- Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
- unslothai/unsloth
- Labeling
- CVAT
- Label Studio
- CVHub520/X-AnyLabeling
- GPLv3, Python
- Deploy/Inference/Serving/Mobile/Optimization
- openvinotoolkit/openvino
- Apache-2.0, C++, Python
- optimizing, deploying AI inference
- by Intel
- hpcaitech/ColossalAI
- Apache-2.0, Python
- microsoft/DeepSpeed
- Apache-2.0, Python, C++
- optimization library that makes distributed training and inference easy, efficient, and effective
- Tencent/ncnn
- BSD-3, C++, C
- neural network inference framework optimized for the mobile platform
johnolafenwa/deepstack- Apache-2.0, Go, Python
- Cross Platform AI Engine for Edge Devices
- openvinotoolkit/openvino
- MLOps
- wandb
- MIT, Python, Go
- wandb
- Voice assistant/voice agent/voice chat/TTS
- VToonify
- music
- upscale
- IBM/MAX-Image-Resolution-Enhancer
- Apache-2.0, Python
- Docker
- upscayl/upscayl
- AGPL-3.0
- 需要 GPU
- App 方式
- Real-ESRGAN
- philz1337x/clarity-upscaler
- AGPLv3, Python
- Magnific Alternative
- Araxeus/PNG-Upscale
- MIT, Java
- 商业
- IBM/MAX-Image-Resolution-Enhancer
- image
- idealo/imagededup
- Apache-2.0, Python
- 图片查重
- CNN, PHash, DHash, WHash, AHash
- https://huggingface.co/datasets/vivym/midjourney-messages
- openai/CLIP
- MIT
- CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
- idealo/imagededup
- video
- blakeblackshear/frigate
- MIT, Python, TS
- NVR with realtime local object detection for IP cameras
- blakeblackshear/frigate
- text to image
- vision
- facebookresearch/dinov2
- Apache-2.0, PyTorch
- 2023-04-14
- DINOv2: Learning Robust Visual Features without Supervision
- 用于特征提取，无监督
- facebookresearch/dino
- Apache-2.0, PyTorch
- 2021
- ViT
- XCiT
- DINO - Self-Supervised Vision Transformers
- PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
- GOT - Generic Object Tracking
- facebookresearch/dinov2
- audio/music/speech/voice/tts
- microsoft/muzic
- yl4579/StyleTTS2
- MIT, Python
- HN
- diagram/Visualizer
- lutzroeder/netron
- https://alexlenail.me/NN-SVG/LeNet.html
- HarisIqbal88/PlotNeuralNet
- Latex code for making neural networks diagrams
- https://www.tensorflow.org/tensorboard/graphs
- stared/keras-sequential-ascii
- ASCII
- https://medium.com/inbrowserai/simple-diagrams-of-convoluted-neural-networks-39c097d2925b
- RT-DETR - Real-Time Detection Transformer
- by Baidu
- SAM/Segment Anything Model
- by Meta
- facebookresearch/segment-anything
- MobileSAM
- FastSAM
- Visual recognition/object detection/segmentation
- facebookresearch/detectron2
- open-mmlab/mmdetection
- google-research/big_vision
- Yolo - You Only Look Once
- YOLO-NAS - Neural Architecture Search
- WongKinYiu/yolov7
- YOLOv7 Breakdown
- CLIP
- lastmile-ai/aiconfig
- MIT, Python
- config-based framework to build generative AI applications
- Dataset
- Foundation
- https://lfaidata.foundation/
- https://ai.meta.com/
- facebookresearch
- https://ai.google/
- https://labs.google/
- https://ai.tencent.com/
- NVlabs
- NVIDIA Research
- THUDM
- 清华 KEG & 数据挖掘
- apps/ios/android
- niedev/RTranslator
- Apache-2.0, C++, Java
- niedev/RTranslator
- PKU-YuanGroup/Video-LLaVA
- GokuMohandas/MadeWithML
- josephmisiti/awesome-machine-learning
- wunderwuzzi23/mlattacks
- tangramdotdev/tangram
- facebookresearch/moco-v3
- facebookresearch/ParlAI
- JianshuZhang/WAP
- salesforce/warp-drive
- isl-org/MiDaS
- NVlabs/stylegan3
- PaddlePaddle/Knover
- google-research-datasets/timedial
- google-research-datasets/disfl-qa
- vijaydwivedi75/gnn-lspe
- microsoft/onnxruntime
- PyTorch 1.10 HN
- facebookresearch/salina
- facebookresearch/ppuda
- wuhaozhe/style_avatar
- facebook/prophet
- producing high quality forecasts for time series data
- facebookresearch/Kats
- analyze time series data
- deepinsight/insightface
- 2D and 3D Face Analysis
- VowpalWabbit/vowpal_wabbit
- frontier of machine learning
- wav2vec
- https://nv-tlabs.github.io/editGAN/
- bryandlee/animegan2-pytorch AnimeGANv2 HN
- yeemachine/kalidokit
- google-research/ibc
- Implicit Behavioral Cloning
- bhky/opennsfw2
- Yahoo Open-NSFW model
- eugeneyan/applied-ml
- PeterL1n/RobustVideoMatting
- yuval-alaluf/hyperstyle
- SysCV/pcan
- tinyfool/VideoRemoveBackground
- open-mmlab/mmhuman3d
- BaltiApps/Pixelify-Google-Photos
- sedthh/pyxelate
- facebookresearch/theseus
- onion-liu/aahq-dataset
- Artstation-Artistic-face-HQ Dataset (AAHQ)
- parrt/tensor-sensor
- mattbradley/dash
- openai/whisper
- https://banmo-www.github.io/
- https://nn-512.com/
- https://hypernerf.github.io/
- babysor/MockingBird
- 5 秒内克隆您的声音并生成任意语音内容
- HN
- https://mlconsole.com/
- AminRezaei0x443/memory-efficient-attention
- Jax, PyTorch
- Perceiver IO: a scalable, fully-attentional model that works on any modality
- mchong6/JoJoGAN
- facebookresearch/SLIP
- Self-supervision meets Language-Image Pre-training
- alibaba/DeepRec
- recommendation engine
- open-mmlab/mmdeploy
- handtracking-io/yoha
- facebookresearch/Detic
- Machine-Learning-Tokyo/Interactive_Tools
- ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code
- kmario23/deep-learning-drizzle
- academic/awesome-datascience
- trekhleb/homemade-machine-learning
- donnemartin/data-science-ipython-notebooks
- https://github.com/facebookresearch/mae
- Masked Autoencoders
- https://github.com/naver-ai/c3-gan
- kaegi/alass
- Automatic Language-Agnostic Subtitle Synchronization
- SubSync: Subtitle Speech Synchronizer
- gnes-ai/gnes
- apache/tvm
- facebookresearch/ConvNeXt
- NVlabs/instant-ngp
- lucidrains/RETRO-pytorch
- libffcv/ffcv
- johnnyzn/DW-GAN
- CAPTCHA
- Kubasinska/MI-EEG-1D-CNN
- google-research/circuit_training
- Justin62628/Squirrel-RIFE
- automl/auto-sklearn
- open-mmlab/mmrotate
- Rotated Object Detection
- google-research/frame-interpolation
- Frame Interpolation for Large Motion
- patrick-kidger/diffrax
- dynamite-ready/movie-parser
- Nixtla/neuralforecast
- forecasting algorithms for time series data
- ouhenio/stylegan3-projector
- StyleGAN3 + Inversion
- victordibia/handtrack.js
- facebookincubator/gloo
- horovod/horovod
- Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet
- facebookresearch/contriever
- https://bishopfox.com/blog/unredacter-tool-never-pixelation
- unmask
- jokenox/Goopt
- 文本内容生成
- fastai/fastcore
- GroupViT: Semantic Segmentation Emerges from Text Supervision
- TorchStudio/torchstudio
- replicate/cog Containers for machine learning
- https://www.nvidia.com/en-us/studio/canvas/
- https://pimeyes.com/
- Parti: Pathways Autoregressive Text-to-Image Model
- kuprel/min-dalle
- DALL E Mini PyTorch
- borisdayma/dalle-mini
- Keytap3: check if your keyboard can be eavesdropped through a microphone
- iperov/DeepFaceLive
- TencentARC/GFPGAN
- Real-world Face Restoration
- google-research/multinerf
- Mip-NeRF 360, Ref-NeRF, and RawNeRF
- Running your own A.I. Image Generator with Latent-Diffusion
- Anjok07/ultimatevocalremovergui
- 移除人声
- NVIDIAGameWorks/kaolin-wisp
- PyTorch library powered by NVIDIA Kaolin Core to work with neural fields
- NeRFs, NGLOD, instant-ngp and VQAD
- nnaisense/evotorch
- Musico: AI Generated Music
- Adventure game graphics with DALL-E 2
Institute
- OpenAI
- DeepMind
- Microsoft Research
- SAIL - Stanford AI Lab
- Carnegie Mellon University Robotics Institute
- Google AI
- CSAIL - MIT Computer Science and Artificial Intelligence Laboratory
- FAIR - Facebook AI Research
- IBM Research
国内
- BAAI - Beijing Academy of Artificial Intelligence - 智源研究院
- baaivision
- BEG - BAAI General Embedding
- FlagOpen/FlagEmbedding
- Retrieval and Retrieval-augmented LLMs
- FlagOpen/FlagEmbedding
- https://huggingface.co/BAAI
- https://baai.ac.cn/
- 百度研究院
- 阿里巴巴达摩院
- 腾讯 - https://yuanbao.tencent.com/
- 商汤科技
- 旷视科技
- 云从科技
UI/Desktop/GUI/WebUI
- omnimodel
- Yonom/assistant-ui
- React Components for AI Chat
- lobehub/lobe-chat
- Apache-2.0, TypeScript
- JetBrains/KotlinDL
- Kotlin DSL for ML
Library
- js/ts/nodejs
- dexaai/openai-fetch
- vercel/ai
Learn
- google-research/google-research
- https://ai.googleblog.com/
- https://www.kdnuggets.com/
- https://stanford.edu/~shervine/teaching/
- DEEP LEARNING COURSE https://fleuret.org/dlc/
- https://github.com/y33-j3T/Coursera-Deep-Learning
- 中文
Books
- Probabilistic Machine Learning: An Introduction
- An Introduction to Applied Bayesian Modeling https://www.bayesrulesbook.com/
- Practical Deep Learning for Coders 2022
- dair-ai/ML-YouTube-Courses
- ML and NLP Research Highlights of 2021
- Machine Learning Algorithms Cheat Sheet
- https://probml.github.io/pml-book/
- https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
- Neural network from scratch
- Distributional Reinforcement Learning
- A visual introduction to machine learning
- Evaluating Syntactic Abilities of Language Models
- RLDS: An Ecosystem to Generate, Share, and Use Datasets in Reinforcement Learning
- https://learnaifromscratch.github.io/ai.html
- microsoft/ML-For-Beginners
- microsoft/Data-Science-For-Beginners
- LabML Neural Networks
- PyTorch
- Reinforcement Learning: Theory and Algorithms
- How to replace estimations and guesses with a Monte Carlo simulation HN
- Neural Networks from Scratch
- How to train large deep learning models as a startup HN
- Red Hot: The 2021 Machine Learning, AI and Data (MAD) Landscape
- Guide for building an End-to-End Logistic Regression Model
- SELF-PARKING CAR IN 500 LINES OF CODE
- facebookresearch/minihack
- Using Machine Learning to Denoise Images for Better OCR Accuracy
- Introduction to AutoEncoder and Variational AutoEncoder
- SimVLM: Simple Visual Language Model Pre-training with Weak Supervision
- Training a DCGAN in PyTorch
- Self-Supervised Reversibility-Aware Reinforcement Learning
- https://arxiv.org/pdf/2109.02869.pdf
- https://arxiv.org/abs/2106.01345
- http://proceedings.mlr.press/v139/vicol21a.html
- https://arxiv.org/abs/2010.01412
- Machine Learning Research Papers Released In 2021
- Interesting Algorithms Released By Google AI In 2021
- A visual introduction to machine learning
- https://brilliant.org/courses/intro-neural-networks/introduction-65/
Framework
- tensorflow/lingvo
- building sequence models neural networks in Tensorflow
- ASR, MT
- dlib
- clab/dynet
- CNTK
- mlpack
- SHARK
- Armadillo
- Faisis
- OpenNN
- FANN
- bennylp/awesome-cpp-ml
- Boosting
- XGBoost
- ThunderGBM
- LightGBM
- CatBoost
- Web
- BrainJS/brain.js
- MIT, TS
- GPU accelerated Neural networks in JavaScript for Browsers and Node.js
- @tensorflow/tfjs
- https://www.tensorflow.org/js/
- tfjs-vis
- @tensorflow/tfjs-node
- @tensorflow/tfjs-node-gpu - Linux
- tensorflow/tfjs-models
- spencermountain/compromise
- MIT, JS
- modest NLP
- ml5js/ml5-library
- 基于 TensorFlow.js
- Blue Oak Model License 1.0.0 modified
- NaturalNode/natural
- MIT, JS
- Tokenizer
- String Distance
- Stemmer
- Bayesian & Logistic Regression Classifier
- Maximum Entropy Classifier
- Sentiment Analysis
- WordNet - moos/wordnet-db
- 无 中文 支持
- NaturalNode/node-sylvester
- vector, matrix, geometry for JS
- NaturalNode/node-nltools
- retextjs/retext
- linonetwo/segmentit
- 中文分词
- wagenaartje/neataptic
- neuro-evolution & backpropagation
- 不在维护
- cazala/synaptic
- 不在维护
- BrainJS/brain.js
- POS Tagger - part-of-speech tagger
- Eric Brill
Intrested
- ZHKKKe/MODNet
- 背景消除
- tonybeltramelli/pix2code
- GUI Screenshot -> Code
Models
- BERT
- Tacotron
- Wavenet/Waveglow/WaveRNN
- Eesen, Espresso, Kaldi, Wav2letter, NeMo
- VGG’16
- VGG’19
- ResNet50
- ResNet101
- ResNet152
- ResNet50v2
- ResNet101v2
- ResNet152v2
- MobileNet
- MobileNetv2
- https://modelplace.ai/models
- OpenBMB/BMList
STT
- snakers4/silero-models
- alphacep/vosk-api
- Offline speech recognition API
- Python, Java, C#, Node
- 支持中文
- alphacep/vosk-asterisk
- res-speech-vosk - Asterisk 集成
- alphacep/vosk-android-demo
- Offline speech recognition for Android with Vosk library
- kaldi-asr/kaldi
- Speech Recognition Toolkit
- julius-speech/julius
- Open-Source Large Vocabulary Continuous Speech Recognition Engine
- daanzu/kaldi-active-grammar
- Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time
- espnet/espnet
- End-to-End Speech Processing Toolkit
- flashlight/wav2letter
- Facebook AI Research's Automatic Speech Recognition Toolkit
- Nvidia/NeMo
- toolkit for conversational AI
- ASR, NLP, TTS
- PaddlePaddle/PaddleSpeech
- ASR toolkit
- 百度 Deep Speech: Scaling up end-to-end speech recognition
- mozilla/DeepSpeech
- 基于 Tensorflow
- arjo129/uSpeech
- Speech recognition toolkit for the arduino
- coqui-ai
- TTS
- STT - 没有中文模型
- synesthesiam/voice2json
- 命令行工具
- 中文模型基于 pocketsphinx
- HN
- NATSpeech/NATSpeech
- Non-Autoregressive Text-to-Speech (NAR-TTS) framework
- cmusphinx
- 工作已经开始转移到 Kaldi, Vosk
- cmusphinx/pocketsphinx
Hardware Platform
- RTX
- Colab Pro
- Paperspace Pro