Skip to content

A curated list of awesome AI resources—including papers, datasets, projects, and more—organized by field.

Notifications You must be signed in to change notification settings

MetythornPenn/awesome-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 

Repository files navigation

Awesome AI Resources

A curated list of awesome AI resources—including papers, datasets, projects, and more—organized by field.

Table of Contents

Computer Vision

Frameworks and Libraries

  • OpenCV - Open Source Computer Vision Library.
  • TensorFlow - An end-to-end open-source platform for machine learning.
  • PyTorch - An open-source machine learning library.
  • Keras - Deep learning API written in Python.
  • Caffe - A deep learning framework made with expression, speed, and modularity in mind.
  • MXNet - A flexible and efficient library for deep learning.
  • Detectron2 - Facebook AI Research's next-generation software system for object detection and segmentation.
  • Albumentations - Fast image augmentation library.
  • SimpleCV - An open-source framework for building computer vision applications.
  • MMDetection - Open-source object detection toolbox based on PyTorch.

Notable Projects

  • YOLO (You Only Look Once) - Real-time object detection system.
  • Mask R-CNN - Implementation of Mask R-CNN on Python and Keras.
  • DeepLab - Semantic image segmentation with deep learning.
  • OpenPose - Real-time multi-person keypoint detection library.
  • StyleGAN - Official TensorFlow implementation of the StyleGAN generator.
  • CycleGAN - Unpaired image-to-image translation.
  • DeepDream - Neural network art project.
  • FaceNet - A unified embedding for face recognition and clustering.
  • DensePose - Dense human pose estimation in the wild.
  • DALL·E - Creating images from text descriptions.

Tutorials and Courses

Natural Language Processing (NLP)

Frameworks and Libraries

  • NLTK - Natural Language Toolkit.
  • spaCy - Industrial-strength NLP in Python.
  • Gensim - Topic modeling for humans.
  • Stanford CoreNLP - A suite of core NLP tools.
  • OpenNMT - Open-source toolkit for neural machine translation.
  • AllenNLP - An open-source NLP research library.
  • Flair - A simple framework for state-of-the-art NLP.
  • TextBlob - Simplified text processing.
  • Polyglot - Multilingual text processing toolkit.
  • Stanza - A collection of accurate and efficient tools for the linguistic analysis of many human languages.

Notable Projects

  • BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding.
  • GPT-3 - OpenAI's Generative Pre-trained Transformer 3.
  • ELMo - Deep contextualized word representations.
  • Word2Vec - Efficient estimation of word representations in vector space.
  • fastText - Library for efficient learning of word representations and sentence classification.
  • Universal Sentence Encoder - Encoding sentences into embedding vectors.
  • Transformer-XL - Attentive language models beyond a fixed-length context.
  • OpenAI Codex - An AI system that translates natural language to code.
  • ULMFiT - Universal Language Model Fine-tuning.

Tutorials and Courses

Transformers and LLMs

Frameworks and Libraries

Notable Projects

Tutorials and Courses

Reinforcement Learning

Frameworks and Libraries

  • OpenAI Gym - A toolkit for developing and comparing reinforcement learning algorithms.
  • Stable Baselines3 - Set of reliable implementations of reinforcement learning algorithms.
  • RLlib - Scalable Reinforcement Learning library.
  • TensorForce - A TensorFlow library for applied reinforcement learning.
  • Keras-RL - Deep reinforcement learning with Keras.

Notable Projects

Tutorials and Courses

Papers

Datasets

Khmer Datasets

  • khmer text data - Khmer unicode text data for unsupervised learning language model

Global Dataset

Projects

Khmer AI Projects

  • wav2vec2-khmer-openslr - Wav2Vec2 with OpenSLR 42 (Khmer language)

  • Fast Khmer Dictionary - Fast khmer dictionary

  • tha - 📢 Tha (ថា) - A Khmer Text Normalization and Verbalization Toolkit

  • khmer line breaker - The lightweight Khmer line breaker with no dependencies. (10.4 kB)

  • khmer2number - A Khmer word to number converter.

  • sosab - 🗣️ sosap(សូរសព្ទ) Python binding for Phonetisaurus

  • khmerpronounce - Khmer Pronounciation Toolkit

  • khmersegment - A Khmer word segmentation tool built for NIPTICT (now CADT) Khmer Word Segmentation CRF model.

  • kfa - A fast Khmer Forced Aligner powered by Wav2Vec2CTC and Phonetisaurus

  • khmercut - A (fast) Khmer word segmentation toolkit.

  • pykhmernlp - Collections of Khmer language toolkit.

  • autocrop_kh - Automatic Document Segmentation and Cropping for Khmer IDs, Passport and Documents

  • ocr_toolkits - Collection of functions to work with ocr and synthetic data generator

  • sdab - Khmer Speech to Text Inference with Pretrained Model

Global AI Projects

  • fast.ai - Simplifying AI and making it accessible.
  • DeepMind Lab - A 3D learning environment for agent-based AI research.
  • Keras - Deep learning for humans.
  • PyTorch - An open-source machine learning library.
  • TensorFlow Models - Models and examples built with TensorFlow.
  • AllenNLP - An open-source NLP research library.
  • Caffe - A deep learning framework made with expression, speed, and modularity in mind.
  • Horovod - Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
  • OpenAI Gym - A toolkit for developing and comparing reinforcement learning algorithms.
  • OpenAI Baselines - High-quality implementations of reinforcement learning algorithms.
  • CLIP (Contrastive Language–Image Pretraining) - Connects text and images.
  • DALL·E - Creating images from text descriptions.
  • OpenAI Codex - An AI system that translates natural language to code.
  • OpenAI Microscope - Visualization of neurons in neural networks.

+ Text to speech

  • fish speech - Brand new TTS solution
  • vits - Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
  • vits2 - Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

+ Optical Character Recognition

  • Donut - Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
  • deep text recognition - Text recognition (optical character recognition) with deep learning methods, ICCV 2019
  • craft - Official implementation of Character Region Awareness for Text Detection (CRAFT)
  • EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
  • SAM2 - Segment Anything Model 2 (SAM 2) is a foundation model towards solving promptable visual segmentation in images and videos.
  • Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
  • Mask_RCNN Pytorch - Mask R-CNN for object detection and instance segmentation on Pytorch

+ Facial Recognition

  • insightface - State-of-the-art 2D and 3D Face Analysis Project
  • InsightFace Pytorch - Pytorch0.4.1 codes for InsightFace
  • facenet - Face Recoginition using Tensorflow
  • facenet pytorch - Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
  • facenet pytorch glint360k - A PyTorch implementation of the 'FaceNet' paper for training a facial recognition model with Triplet Loss using the glint360k dataset. A pre-trained model using Triplet Loss is available for download.
  • openface - Face recognition with deep neural networks.
  • face_recognition - The world's simplest facial recognition api for Python and the command line
  • DeepFace - A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
  • Retinaface - RetinaFace: Deep Face Detection Library for Python

+ Large Language Model

  • litgpt - 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
  • litdata - Transform datasets at scale. Optimize datasets for fast AI model training.
  • dify - Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
  • LLaMA-Factory - Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Books

Conferences and Journals

Blogs and Websites

Tools and Platforms

  • Weights & Biases - Experiment tracking, model management, and dataset versioning.
  • TensorBoard - Visualization toolkit for TensorFlow.
  • Docker - Container platform for building and deploying applications.
  • Kaggle - Platform for data science competitions.
  • Google Colab - Free Jupyter notebook environment.
  • Azure Machine Learning - Cloud platform for machine learning.
  • Amazon SageMaker - Build, train, and deploy ML models at scale.
  • MLflow - Open-source platform for the machine learning lifecycle.

Contributing

Contributions are welcome! Please submit a pull request or open an issue to add new resources.

License

MIT

About

A curated list of awesome AI resources—including papers, datasets, projects, and more—organized by field.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published