Awesome GitHub RepositoriesAccuracy Calculators

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

This project is a machine learning algorithm reference and implementation guide that provides theoretical foundations and code for supervised learning, deep learning, and natural language processing. It serves as a comprehensive toolkit for implementing predictive models and a technical reference for algorithm engineering. The project focuses on ensemble learning frameworks, including the construction of decision trees, random forests, and gradient boosting models. It also functions as a probabilistic graphical model library and an NLP algorithm reference, with specific implementations for se

This project is an educational framework designed to teach the fundamentals of building core distributed systems and web services from scratch in Go. It provides a collection of modular implementations that demonstrate how to construct essential infrastructure components, including web servers, remote procedure call systems, distributed caches, and database abstraction layers. The framework distinguishes itself by focusing on the internal mechanics of these systems rather than providing a high-level abstraction for production use. It covers the implementation of complex architectural patterns

PyOD is a Python anomaly detection library used to identify outliers in tabular, time series, graph, text, and image data. It provides a collection of algorithms for detecting anomalous data points and includes a unified detector interface that standardizes input and output signatures across its available detection algorithms. The project features a multi-modal outlier detector for identifying anomalies across diverse formats including unstructured text and images, as well as a specialized toolkit for graph-based and time-series anomaly detection. It includes an ensemble framework for combini

Pyannote.audio is a PyTorch toolkit for speaker diarization, speaker identification, and speech activity detection. Its primary purpose is to partition audio recordings into segments and assign each segment to a specific speaker identity to determine who spoke when. The project includes a framework for classifying speaker identities and a pipeline for distinguishing human speech from background noise. It provides specialized tools for handling symmetric-overlap speech, where multiple speakers talk simultaneously, and employs learnable band-pass filters for raw waveform feature extraction. Th

ImageAI is a Python computer vision library providing a suite of tools for image classification, object detection, and video analytics. It functions as an integrated framework for locating and labeling objects in static images and video streams, utilizing deep learning models for identification and categorization. The project includes a model training toolkit that allows for the creation of custom classifiers and detectors through scratch training or transfer learning. It features a GPU-accelerated inference engine to increase processing speed for vision tasks and includes specialized utiliti

This is a scikit-learn automated machine learning framework designed to optimize model selection and hyperparameters. It functions as an automated model selector and hyperparameter optimization tool for classification and regression tasks, utilizing an automated ensemble builder to combine high-performing models for increased predictive accuracy. The system features a distributed search engine that uses Dask for parallel machine learning optimization across CPU cores or clusters. It implements a budget-based evaluation strategy through successive halving to prioritize promising model configur

Facets is a set of interactive software tools for the statistical analysis, distribution visualization, and multidimensional exploration of machine learning datasets. It provides a visual interface for identifying outliers and missing values in numeric and string data, specifically designed for auditing dataset quality and identifying skews between training and validation sets. The system uses multidimensional facet-based visualization and interactive bucketing to map individual data points across multiple feature axes. It employs synchronized view filtering and animated dimension transitions

Este es un plan de estudios educativo integral diseñado para enseñar los fundamentos del aprendizaje automático utilizando el lenguaje de programación Python. Proporciona un curso estructurado que cubre la implementación y la teoría del aprendizaje supervisado, el aprendizaje no supervisado y el aprendizaje profundo. El plan de estudios se imparte a través de notebooks interactivos que combinan código ejecutable con tutoriales técnicos. Incluye guías dedicadas para construir arquitecturas de redes neuronales, implementar modelos de clasificación y regresión, y utilizar técnicas de clustering para el descubrimiento de patrones en datos no etiquetados. Los materiales cubren el flujo de trabajo completo de aprendizaje automático, incluyendo el preprocesamiento de datos y la codificación categórica, el entrenamiento de modelos y el ajuste de hiperparámetros, y la evaluación del rendimiento. También cuenta con herramientas para visualizar el comportamiento del modelo, como el trazado de límites de decisión y diagramas de árboles de decisión.

Surprise is a Python library for building and analyzing recommendation systems. It provides a comprehensive toolkit for implementing collaborative filtering to predict user preferences and generate item suggestions based on historical rating patterns. The library includes dedicated tools for hyperparameter optimization and model evaluation. It allows for searching through parameter sets to find the most effective configurations and utilizes a suite of metrics to measure prediction accuracy. The framework covers the full development workflow, including data loading from various sources, the c

PointNet es una arquitectura de aprendizaje profundo diseñada para procesar y clasificar nubes de puntos 3D crudas directamente sin voxelización. Proporciona un sistema para la clasificación de objetos 3D, frameworks de segmentación semántica para particionar nubes en categorías y herramientas para visualizar formas 3D. El proyecto utiliza una red de transformación para alinear nubes de puntos en un espacio de coordenadas canónico y emplea una agregación basada en funciones simétricas para condensar características punto a punto en vectores globales independientemente del orden de los puntos. También cuenta con una arquitectura de agrupación multiescala para extraer características geométricas jerárquicas a través de diferentes escalas espaciales. El sistema incluye pipelines de datos para convertir datos crudos de análisis de interiores 3D y formas en archivos HDF5 para entrenamiento. Las capacidades de evaluación cubren métricas de precisión de segmentación y el renderizado de nubes de puntos 3D mal clasificadas en imágenes de tres vistas para el análisis de errores.

SAHI es un framework de inferencia segmentada y pipeline de visión artificial diseñado para detectar objetos pequeños en imágenes de alta resolución. Proporciona un sistema para dividir imágenes grandes en parches superpuestos para evitar la pérdida de detalle que ocurre típicamente durante la reducción de escala estándar del modelo, junto con una utilidad de mosaico de imágenes y un kit de herramientas de conjunto de datos COCO. El proyecto se distingue por ofrecer un wrapper de predicción agnóstico al modelo que estandariza diferentes frameworks de aprendizaje automático en una interfaz unificada. Esto le permite implementar inferencia segmentada y detección de objetos a través de varios backends de modelos mientras mantiene un formato de salida consistente. Más allá de la inferencia, el framework cubre la gestión de conjuntos de datos para formatos COCO y YOLO, incluyendo herramientas para el corte de imágenes anotadas, remapeo de categorías y fusión de conjuntos de datos. También incluye una suite para la evaluación y monitoreo del rendimiento del modelo, con cálculo de métricas para precisión y recall, análisis de errores de detección y visualización de resultados. El conjunto de herramientas es accesible a través de una interfaz de línea de comandos para automatizar flujos de trabajo de inferencia a través de directorios de imágenes y flujos de video.

This project is an object detection evaluation library and benchmarking tool designed to calculate precision, recall, and average precision for computer vision models. It provides a suite of utilities for parsing bounding box coordinates from text files and calculating spatial overlap to determine detection accuracy. The toolkit features a command line interface for comparing ground truth files against model predictions. It includes a precision-recall curve generator to visualize the relationship between precision and recall across different confidence thresholds and an intersection over unio

DeepLearningZeroToAll is a comprehensive educational resource and implementation collection focused on deep learning and machine learning. It provides a structured learning path using TensorFlow to move from foundational linear models to complex neural network architectures. The project is distinguished by its practical implementations of various network types, including multilayer perceptrons for logic problems, convolutional neural networks for spatial data and image recognition, and recurrent neural networks using LSTM cells for time-series forecasting and character sequence prediction. It

Tiny Universe is an educational monorepo that delivers multiple independent implementations of core AI subsystems as self-contained Jupyter notebooks. It provides from-scratch constructions of foundational architectures including a complete Transformer model built from the original paper specification, a denoising diffusion probabilistic model for image generation, and a ReAct-style autonomous agent framework that equips an LLM with tools for planning and multi-step task execution. The project distinguishes itself by covering the full lifecycle of modern AI systems through hands-on implementa

VLMEvalKit is a vision-language model evaluation framework and inference engine designed to run standardized benchmarks and measure model accuracy across diverse visual datasets. It serves as a multimodal model benchmark and performance toolkit for calculating metrics and comparing model responses. The toolkit includes a specialized visual reasoning evaluator that uses adversarial samples to distinguish actual image understanding from reliance on language patterns. It also provides capabilities for image generation evaluation, testing a model's ability to create or modify visuals based on tex

Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable

This project is a collection of structured study notes and notebooks serving as an educational resource for deep learning and neural network fundamentals. It provides a technical reference for implementing machine learning theory, covering everything from basic network design to the construction of advanced architectures. The material specifically focuses on the implementation of convolutional neural networks for computer vision and sequence models for natural language processing. It includes detailed guidance on building object detection systems, face recognition, and speech transcription mo

Este proyecto sirve como recurso educativo y práctico para dominar flujos de trabajo de machine learning utilizando Python. Proporciona una colección integral de ejemplos de código y ejercicios diseñados para guiar a los usuarios a través de la implementación de sistemas predictivos, desde algoritmos fundamentales hasta arquitecturas de aprendizaje profundo. El repositorio se distingue por ofrecer un enfoque estructurado tanto para el machine learning clásico como para el entrenamiento de redes neuronales. Cubre el ciclo de vida completo del desarrollo de modelos, incluyendo la orquestación de pipelines de transformación de datos reutilizables, estrategias de conjunto avanzadas como el apilamiento y el entrenamiento secuencial, y técnicas para manejar conjuntos de datos a gran escala mediante procesamiento incremental. El material abarca una amplia superficie de capacidades, incluyendo clasificación, regresión, clustering y reducción de dimensionalidad. Proporciona herramientas para una evaluación rigurosa de modelos, como análisis de errores y métricas de rendimiento, junto con técnicas de optimización como el ajuste de hiperparámetros, regularización y controles de entrenamiento automatizados para garantizar la fiabilidad y generalización del modelo. El contenido está organizado como una serie de tutoriales y ejercicios prácticos, convirtiéndose en una referencia para construir y desplegar sistemas inteligentes con frameworks estándar de la industria.