Coding & Development

efficient-gnns is a comprehensive repository offering code and resources for developing scalable and efficient Graph Neural Networks (GNNs). It specifically focuses on knowledge distillation techniques, including novel approaches like Graph Contrastive Representation Distillation, to create resource-efficient GNNs. The repository benchmarks various distillation methods, such as Local Structure Preserving loss and Global Structure Preserving loss, alongside baselines like Logit-based KD. It supports research on large-scale, real-world graph datasets for tasks like graph classification on MOLHIV and node classification on ARXIV and MAG, providing installation and usage instructions for researchers and developers in the field.

eo-learn is an open-source Python framework designed to streamline Earth observation processing and machine learning tasks. It provides a collection of Python packages that facilitate seamless access and automated processing of spatio-temporal image sequences from satellite fleets like Copernicus and Landsat. The framework is modular, allowing users to define sequences of operations for tasks such as cloud masking, image co-registration, feature extraction, and classification. It acts as a bridge between remote sensing and the Python data science ecosystem, making advanced tools accessible to non-experts while bringing state-of-the-art machine learning capabilities to remote sensing professionals. eo-learn uses NumPy arrays for data handling and supports various functionalities through modules like core, coregistration, features, geometry, io, mask, ml-tools, and visualization.

eps is a machine learning library designed for Ruby, enabling developers to build predictive models efficiently. It supports both regression and classification tasks, automatically splitting data into training and validation sets for performance evaluation. A key feature is its ability to serve models created in other languages like Python and R, using standards like PMML. This allows for flexible integration of diverse machine learning workflows into Ruby applications. The library also offers robust feature engineering options for numeric, categorical, and text data, along with various algorithms including LightGBM, Linear Regression, and Naive Bayes. It provides tools for model monitoring and database storage, making it suitable for continuous integration and deployment of machine learning models.

Federated is a collection of Google research projects dedicated to advancing Federated Learning and Federated Analytics. Federated learning enables the training of a shared global model across numerous participating clients while ensuring their training data remains local. Federated analytics, on the other hand, focuses on applying data science methods to analyze raw data stored directly on users’ devices. Many projects within this repository leverage TensorFlow Federated (TFF), an open-source framework designed for machine learning and other computations on decentralized data. The repository serves primarily for reproducing experimental results from related papers, with each project intended as an independent unit rather than a reusable framework.

NeuroBlock is an AI laboratory dedicated to enhancing AI models through the use of high-quality datasets. The platform provides comprehensive enterprise AI consulting services, assisting businesses in integrating and optimizing AI solutions. A key offering includes local and private AI integrations, ensuring data privacy and tailored performance for specific organizational needs. Additionally, NeuroBlock features an OpenData platform, designed to facilitate AI model training by providing access to diverse and curated datasets. The company also develops lead generation tools, leveraging AI to identify and engage potential customers. NeuroBlock aims to deliver AI solutions that are efficient, secure, and customized to client requirements.

Reference is an open-source project offering a comprehensive collection of quick reference cheat sheets specifically designed for developers. It covers a wide array of topics, including numerous programming languages like Python, JavaScript, Go, and C++, as well as essential toolkits such as ChatGPT, VSCode, and Emmet. Additionally, it provides cheat sheets for Linux commands and keyboard shortcuts for popular applications like Adobe Photoshop, Figma, and GitHub. The platform encourages community contributions, allowing users to share their own cheat sheets or improve existing ones, making it a dynamic and continuously evolving resource. The primary and maintained domain for accessing these up-to-date cheat sheets is cheatsheets.zip.

facexlib is an open-source library designed to provide ready-to-use face-related functions, leveraging current state-of-the-art open-source methods. It primarily offers PyTorch reference codes for various face processing tasks, including detection, alignment, recognition, parsing, matting, headpose estimation, and tracking. While it provides a collection of these algorithms, users are directed to the original repositories for training or fine-tuning. The library simplifies the integration of advanced face processing techniques into existing projects, making it a valuable resource for developers and researchers working with facial data. It is released under the MIT license, with individual components referencing their original licenses.

Fewshot_Detection is an open-source implementation of the paper "Few-shot Object Detection via Feature Reweighting," designed for researchers and developers working with computer vision. This tool addresses the challenge of detecting novel objects with limited training data by employing a meta feature learner and a reweighting module within a one-stage detection architecture. It is built upon `pytorch-yolo2` and developed with Python 2.7 and PyTorch 0.3.1. The system extracts meta features generalizable to novel object classes and transforms support examples into reweighting vectors, enhancing detection capabilities. The entire process, including a carefully designed loss function, is trained end-to-end based on an episodic few-shot learning scheme. It demonstrates significant performance improvements over established baselines on multiple datasets and settings.

PiML-Toolbox (Python Interpretable Machine Learning) is a comprehensive Python toolbox designed for the development and diagnostics of interpretable machine learning models. It offers both low-code interfaces and high-code APIs, supporting a growing list of inherently interpretable ML models such as GLM, GAM, Tree, FIGS, XGB1, XGB2, EBM, GAMI-Net, and ReLU-DNN. The toolbox facilitates various outcome testing, including accuracy, explainability (PFI, PDP, ALE, LIME, SHAP), fairness, weak spot identification, overfitting detection, reliability assessment, robustness, and resilience evaluation. PiML-Toolbox aims to empower model developers and validators with tools for transparent, interpretable, and robust machine learning, particularly in high-stakes regulatory settings.

PyRCA is a Python machine learning library designed to facilitate root cause analysis (RCA) in complex IT environments, particularly those utilizing microservices architectures. It offers a comprehensive suite of state-of-the-art RCA algorithms, primarily focusing on metric-based analysis. Users can identify anomalous metrics using methods like ε-diagnosis or pinpoint root causes based on topology/causal graphs through techniques such as Bayesian inference and Random Walk. The library also provides a convenient tool for building and refining causal graphs from time series data and domain knowledge, simplifying the development of graph-based RCA solutions. PyRCA supports various methods including ε-Diagnosis, Bayesian Inference-based RCA, Random Walk-based RCA, Root Cause Discovery, and Hypothesis Testing-based RCA, with plans to expand to trace and log-based RCA in the future. It also includes a benchmark for evaluating different RCA methods.

REP, or Reproducible Experiment Platform, is an ipython-based environment designed for conducting data-driven research with an emphasis on consistency and reproducibility. It provides a unified Python wrapper for several machine learning libraries, including Sklearn, XGBoost, and Theanets, allowing users to work with a consistent interface. Key features include parallel training of classifiers on clusters, classification/regression reports with interactive plots, and smart grid-search algorithms with parallel execution. REP also supports research versioning using Git and offers pluggable quality metrics for classification. It aims to extend scikit-learn by providing a better user experience and tools for meta-algorithm design, making it a valuable resource for data scientists and researchers.

pointnet.pytorch offers a PyTorch implementation of the PointNet deep learning model, specifically designed for 3D classification and segmentation using point sets. This open-source tool facilitates research and development in 3D data processing, providing a robust and tested framework compatible with PyTorch 1.0. It includes functionalities for downloading and preparing datasets, training classification and segmentation models, and visualizing results. The repository details performance metrics on datasets like ModelNet40 and ShapeNet, allowing users to compare against original implementations. It's a valuable resource for developers and researchers working with 3D point cloud data.

Blynkkr is a revolutionary application designed to consolidate all your social profiles into a single, secure digital identity. It leverages facial recognition AI to seamlessly add new contacts by simply scanning their face, provided they are also on the Blynkkr platform. The application is deeply integrated with blockchain technology, ensuring that your personal data is stored privately and securely, offering a tamper-proof method for managing your digital identity. Blynkkr provides highly accurate facial analysis, comparison, and search capabilities, utilizing Google ML Kit's Vision and Natural Language ML Kit face detection API for real-time processing directly on-device, enhancing user privacy and security. This combination of AI and blockchain offers a streamlined user experience while prioritizing data protection.

QP/C is a real-time event framework (RTEF) and RTOS designed for embedded systems, particularly microcontrollers like ARM Cortex-M MCUs. It implements an asynchronous, event-driven Active Object (Actor) model and supports Hierarchical State Machines (UML statecharts) for specifying behavior. Developers can manually code state machines in C or use the free graphical QM model-based design (MBD) tool for automatic code generation. QP/C is part of the larger QP framework family, offering both open-source (GPLv3) and commercial licensing options. It provides a robust software infrastructure and runtime environment for deterministic, real-time execution of Active Objects, making it suitable for developing complex embedded applications.

R1-V is an open-source project focused on enhancing the super generalization ability of Vision Language Models (VLM) with minimal computational cost. It aims to improve the perception and reasoning capabilities of VLMs through reinforcement learning. The project provides new VLM-RL environments, a comprehensive training codebase, and research papers. R1-V supports various models like Qwen2-VL and Qwen2.5-VL, and offers training datasets for tasks such as item counting and geometry reasoning. It also includes evaluation scripts for benchmarks like SuperClevr and GEOQA, making it a valuable resource for researchers and developers in the VLM domain.

TensorFlow Hub (hub) is a Python library designed to facilitate transfer learning by enabling the reuse of pre-trained TensorFlow models. It allows developers to easily download and integrate SavedModels into their TensorFlow programs with minimal code. While the tfhub.dev platform has transitioned to Kaggle Models, the `tensorflow_hub` library continues to support downloading models that were initially uploaded to tfhub.dev. This tool is particularly useful for accelerating development by leveraging existing, high-quality models for tasks like image classification and text classification, reducing the need to train models from scratch. It includes comprehensive documentation, examples, and guidelines for contributing to the library.

scikit-learn-mooc is the official source code repository for the Machine Learning in Python with scikit-learn MOOC. This comprehensive course offers educational material designed to teach machine learning concepts using the popular scikit-learn library in Python. The MOOC provides a rich learning experience with features like quizzes, executable notebooks, and a discussion forum for interactive learning. It is hosted on the FUN-MOOC platform and is completely free, ensuring accessibility for a wide audience interested in data science and machine learning. Users can enroll for the full MOOC experience or browse a static version of the course online, with options to launch online notebook environments or run notebooks locally.

seq2seq-signal-prediction is an open-source project designed to teach users how to implement Sequence-to-Sequence (seq2seq) Recurrent Neural Networks (RNNs) for time series forecasting using TensorFlow. The project includes a series of four exercises of increasing difficulty, starting with deterministic signal prediction and progressing to more complex tasks like denoising and Bitcoin price forecasting. It provides a Jupyter notebook and a Python script version, with instructions for running the code locally or on Google Colab with GPU support. The exercises guide users through adjusting hyperparameters and modifying network architectures to achieve accurate predictions, making it a practical learning resource for those with some prior knowledge of RNNs.

jetson-inference is an open-source guide and library designed for deploying deep-learning inference networks and deep vision primitives on NVIDIA Jetson devices. It leverages TensorRT to run optimized networks on GPUs, offering support for a range of vision tasks including image classification (imageNet), object detection (detectNet), semantic segmentation (segNet), pose estimation (poseNet), and action recognition (actionNet). The project provides examples for streaming from live camera feeds, creating web applications with WebRTC, and integrates with ROS/ROS2. It includes tutorials for running inference, transfer learning with PyTorch, collecting custom datasets, and deploying trained models.

imgclsmob is an open-source repository designed as a sandbox for training deep learning networks, with a primary focus on convolutional networks for computer vision tasks. It offers a comprehensive collection of (re)implementations of various models for classification, segmentation, detection, and human pose estimation. The tool includes scripts for training, evaluating, and converting these models across multiple deep learning frameworks such as MXNet/Gluon, PyTorch, Chainer, Keras, and TensorFlow 1.x/2.x. It supports models pretrained on diverse datasets like ImageNet-1K, CIFAR-10/100, SVHN, Pascal VOC2012, ADE20K, and COCO, with automatic loading of pretrained weights. This makes it an invaluable resource for researchers and developers working on deep learning projects.

TensorFlowASR is an open-source toolkit for automatic speech recognition (ASR) built on TensorFlow 2. It provides implementations of various advanced ASR architectures, including DeepSpeech2, Jasper, RNN Transducer, ContextNet, and Conformer. A key feature is the ability to convert these models to TFLite, which significantly reduces memory and computation requirements, making them suitable for deployment on devices with limited resources. The framework supports multiple languages, including English and Vietnamese, and offers functionalities for feature extraction and augmentations. It's designed for developers and researchers looking to build, train, and deploy high-performance speech recognition systems.

SapientML is an open-source AutoML technology designed to accelerate and enhance AI model creation. It learns from a corpus of existing datasets and human-written pipelines to efficiently generate high-quality machine learning pipelines for new predictive tasks. Key features include high speed, as it evaluates only the most plausible pipelines, and transparency, providing an easy-to-understand generated machine learning program with explanations. It also boasts high accuracy, leveraging past knowledge from programs that built highly accurate AI models. Users can install SapientML via pip and utilize its APIs to generate machine learning pipelines, making it accessible for developers and data scientists looking to streamline their AI development workflow.

This GitHub repository offers a comprehensive tutorial for training, converting, and running TensorFlow Lite object detection models on various edge devices, including Android phones and the Raspberry Pi. It guides users through the process of creating custom TensorFlow Object Detection models, optimizing them for TensorFlow Lite, and deploying them for real-time applications. The tutorial provides Python code for performing object detection on images, videos, web streams, or webcam feeds. It also highlights the benefits of using Google Colab for training, offering a free GPU-enabled virtual machine, and includes step-by-step setup guides for different devices. The resource emphasizes faster inference times and reduced processing power requirements compared to standard TensorFlow models.

TextGAN-PyTorch is a comprehensive PyTorch framework designed for Generative Adversarial Networks (GANs) based text generation models. It supports both general and category-specific text generation, making it a versatile tool for researchers and developers. The framework serves as a benchmarking platform, facilitating the evaluation and comparison of various GAN-based text generation models. It is particularly beneficial for those familiar with PyTorch, enabling them to quickly engage with the text generation field. The repository includes implementations of several prominent models like SeqGAN, LeakGAN, and RelGAN, along with detailed instructions for setup and usage, including real data experiments and visualization tools.