Akara Supratak

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

nanochat. The best ChatGPT that $100 can buy.

AISD. Acute ischemic stroke dataset

BiomedCoOp. [CVPR 2025] Official implementation of BiomedCoOp

RadFM. The official code for "Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data".

LLaVA-Med. Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Otter. 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

tabzilla. Code for "TabZilla: When Do Neural Nets Outperform Boosted Trees on Tabular Data?"

LLM101n. LLM101n: Let's build a Storyteller

torchtune. PyTorch native post-training library

LLM-Finetuning. LLM Finetuning with peft

ng-video-lecture. Python

build-nanogpt. Video+code lecture on building nanoGPT from scratch

Emu. Emu Series: Generative Multimodal Models from BAAI

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Flowise. Build AI Agents, Visually

cudf. cuDF - GPU DataFrame Library

TotalSegmentator. Tool for robust segmentation of >100 important anatomical structures in CT and MR images

nnUNet. Python

pydata-book. Materials and IPython notebooks for "Python for Data Analysis" by Wes McKinney, published by O'Reilly Media

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

TorchAL. Official implementation of our paper: Towards Robust and Reproducible Active Learning using Neural Networks, accepted at CVPR 2022.

TypiClust. Active Learning on a Budget - Opposite Strategies Suit High and Low Budgets

modAL. A modular active learning framework for Python

XMem. [ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

deep-high-resolution-net.pytorch. The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

human-pose-estimation.pytorch. The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

github-readme-stats. :zap: Dynamically generated stats for your github readmes

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

Machine-Learning-Specialization-Coursera. Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG

interpret. Fit interpretable models. Explain blackbox machine learning.

fairlearn. A Python package to assess and improve fairness of machine learning models.

nn-zero-to-hero. Neural Networks: Zero to Hero

micrograd. A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

pydub. Manipulate audio with a simple and easy high level interface

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

TransMIL. TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

AttentionDeepMIL. Implementation of Attention-based Deep Multiple Instance Learning in PyTorch

computer-science. 🎓 Path to a free self-taught education in Computer Science!

snorkel-tutorials. A collection of tutorials for Snorkel

snorkel. A system for quickly generating training data with weak supervision

weasel. Weakly Supervised End-to-End Learning (NeurIPS 2021)

VG-GPLMs. The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

PaddleDetection. Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

vision_transformer. Jupyter Notebook

deeplab2. DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.

PRNet. Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

PixelAnnotationTool. Annotate quickly images.

annotation-app. Generic, reusable, image annotation web application

rtdl. Research on Tabular Deep Learning: Papers & Packages

kaggle_moa_winner_hungry_for_gold. Winning Solution of Kaggle Mechanisms of Action (MoA) Prediction.

react-player. A React component for playing a variety of URLs, including file paths, YouTube, Facebook, Twitch, SoundCloud, Streamable, Vimeo, Wistia and DailyMotion

misgan. MisGAN: Learning from Incomplete Data with GANs

create-react-app. Set up a modern web app by running one command.

AugLy. A data augmentations library for audio, image, text, and video.

ViewAL. [CVPR'20] Implementation for the paper "ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation"

blog_code. A repo for holding example code

shap. A game theoretic approach to explain the output of any machine learning model.

monoloco. A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Social-Distancing-AI. Tool to moniter social distancing using CCTV feeds, videos. Can be used at public places and workplace.

AlignedReID. Alignedreid＋+: Dynamically Matching Local Information for Person Re-Identification.

keepsake. Version control for machine learning

PyTorch-StudioGAN. StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

monodepth2. [ICCV 2019] Monocular depth estimation from a single image

Exploit-Unknown-Gradually. CVPR 2018 Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning

GAIN. Codebase for Generative Adversarial Imputation Networks (GAIN) - ICML 2018

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

model_search. Python

deep-vector-quantization. VQVAEs, GumbelSoftmaxes and friends

DeepCTR. Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

recommenders. Best Practices on Recommendation Systems

hyperopt. Distributed Asynchronous Hyperparameter Optimization in Python

resampy. Efficient sample rate conversion in python

icecream. 🍦 Never use print() to debug again.

audiomentations. A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

optuna. A hyperparameter optimization framework

BubbleNets. Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frames

ralis. Code for the paper "Reinforced Active Learning for Image Segmentation"

impyute. Data imputations library to preprocess datasets with missing data

datawig. Imputation of missing values in tables.

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

yolov5. Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

DexiNed. DexiNed: Dense EXtreme Inception Network for Edge Detection

tpot. A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

mediapipe. Cross-platform, customizable ML solutions for live and streaming media.

google-research. Google Research

Deep_reinforcement_learning_Course. Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

imaginaire. NVIDIA's Deep Imagination Team's PyTorch Library

pycaret. Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.

skorch. A scikit-learn compatible neural network library that wraps PyTorch

Complex-YOLOv4-Pytorch. The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"

spark-py-notebooks. Apache Spark & Python (pySpark) tutorials for Big Data Analysis and Machine Learning as IPython / Jupyter notebooks

packing-unpacking-pytorch-minimal-tutorial. Minimal tutorial on packing and unpacking sequences in pytorch

U-2-Net. The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

node. Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data

node. Jupyter Notebook

USRNet. Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch)

Data-Analysis. Data Science Using Python

ECMLDeepAudio. Documented code with instructions to reproduce results of paper submitted to ECML

imbalanced-learn. A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

DeepExplain. A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)

torch-two-sample. A PyTorch library for two-sample tests

pyod. A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

anomaly-detection-resources. Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

siamese-triplet. Siamese and triplet networks with online pair/triplet mining in PyTorch

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

AAE_pytorch. Python

fast-autoaugment. Official Implementation of 'Fast AutoAugment' in PyTorch.

pytorch-normalizing-flows. Normalizing flows in PyTorch. Current intended use is education not production.

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

faiss. A library for efficient similarity search and clustering of dense vectors.

caffe-segnet. Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling

RepDistiller. [ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

SegSort. SegSort: Segmentation by Discriminative Sorting of Segments

pysheeet. Python Cheat Sheet

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Switchable-Normalization. Code for Switchable Normalization from "Differentiable Learning-to-Normalize via Switchable Normalization", https://arxiv.org/abs/1806.10779

uda. Unsupervised Data Augmentation (UDA)

antialiased-cnns. pip install antialiased-cnns to improve stability and accuracy

slides.

STEAL. STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)

Awesome-Edge-Detection-Papers. :books: A collection of edge/contour/boundary detection papers and toolbox.

BDCN. The code for the CVPR2019 paper Bi-Directional Cascade Network for Perceptual Edge Detection

segmentation_models. Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

mit-deep-learning. Tutorials, assignments, and competitions for MIT Deep Learning related courses.

tensorflow-yolo-v3. Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)

tensorflow-yolov3. 🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

Deep-Learning-Coursera. Deep Learning Specialization by Andrew Ng, deeplearning.ai.

darknet. YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

keras-yolo3. A Keras implementation of YOLOv3 (Tensorflow backend)

zoom-learn-zoom. computational zoom from raw sensor data

Faster-RCNN_TF. Faster-RCNN in Tensorflow

next-prediction. Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

tensorflow-face-detection. A mobilenet SSD based face detector, powered by tensorflow object detection api, trained by WIDERFACE dataset.

ffmpeg-python. Python bindings for FFmpeg - with complex filtering support

PlotNeuralNet. Latex code for making neural networks diagrams

fastai. The fastai deep learning library

course-v3. The 3rd edition of course.fast.ai

deep-learning-drizzle. Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!

ludwig. Low-code framework for building custom LLMs, neural networks, and other AI models

robot-surgery-segmentation. Wining solution and its improvement for MICCAI 2017 Robotic Instrument Segmentation Sub-Challenge

cs230-code-examples. Code examples in pyTorch and Tensorflow for CS230

Kubernetes-GPU-Guide. This guide should help fellow researchers and hobbyists to easily automate and accelerate there deep leaning training with their own Kubernetes GPU cluster.

places365. The Places365-CNNs for Scene Classification

Augmentor. Image augmentation library in Python for machine learning.

imgaug. Image augmentation for machine learning experiments.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

neural_collaborative_filtering. Neural Collaborative Filtering

hed. code for Holistically-Nested Edge Detection

holy-edge. Holistically-Nested Edge Detection

test-tube. Python library to easily log experiments and parallelize hyperparameter search for neural networks

trfl. TensorFlow Reinforcement Learning

sngan_projection. GANs with spectral normalization and projection discriminator

neural-template-gen. Python

learnopencv. Learn OpenCV : C++ and Python Examples

gdrive. Google Drive CLI Client

chatbot-retrieval. Dual LSTM Encoder for Dialog Response Generation

Awesome-Chatbot. Awesome Chatbot Projects,Corpus,Papers,Tutorials.Chinese Chatbot =>:

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Tensorflow-Dataset-Tutorial. Notebook for my medium article about how to use Dataset API in TensorFlow

compare_gan. Compare GAN code.

acai. Code for "Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer"

gitignore. A collection of useful .gitignore templates

scikit-learn-videos. Jupyter notebooks from the scikit-learn video series

facenet. Face recognition using Tensorflow

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

vat_tf. Virtual adversarial training with Tensorflow

iTerm2-Color-Schemes. Over 450 terminal color schemes/themes for iTerm/iTerm2. Includes ports to Terminal, Konsole, PuTTY, Xresources, XRDB, Remmina, Termite, XFCE, Tilda, FreeBSD VT, Terminator, Kitty, MobaXterm, LXTerminal, Microsoft's Windows Terminal, Visual Studio, Alacritty, Ghostty, and many more

nlp_thai_resources. More than 50+ collections of Thai Natural Language Processing libraries. Update daily.

pythainlp. Thai natural language processing in Python

GloVe. Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings

glove-python. Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/

ReferringRelationships. Python

reinforcement-learning. Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

YAD2K. YAD2K: Yet Another Darknet 2 Keras

ladder. Ladder network is a deep learning algorithm that combines supervised and unsupervised learning

probtorch. Probabilistic Torch is library for deep generative models that extends PyTorch

ssl_bad_gan. Good Semi-Supervised Learning That Requires a Bad GAN

kaggle-web-traffic. 1st place solution

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

soft-dtw. Python implementation of soft-DTW.

trpo. Trust Region Policy Optimization with TensorFlow and OpenAI Gym

sac. Soft Actor-Critic

SNNs. Tutorials and implementations for "Self-normalizing networks"

SyncNet. Targeting EEG/LFP synchrony with neural nets

onnx. Open standard for machine learning interoperability

bayesgan. Tensorflow code for the Bayesian GAN (https://arxiv.org/abs/1705.09558) (NIPS 2017)

UNIT. Unsupervised Image-to-Image Translation

DistanceGAN. Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017