awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoServidor MCPAcerca deCómo clasificamosPrensa
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

35 repositorios

Awesome GitHub RepositoriesModel Export Formats

Interoperable formats for exporting trained models to different runtimes and production environments.

Distinct from Model Inference Deployment: Focuses on the serialization and export to formats like ONNX, PMML, and CoreML, rather than the deployment orchestration.

Explore 35 awesome GitHub repositories matching devops & infrastructure · Model Export Formats. Refine with filters or upvote what's useful.

Awesome Model Export Formats GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • ultralytics/yolov3Avatar de ultralytics

    ultralytics/yolov3

    10,571Ver en GitHub↗

    This is a real-time object detection framework built on the YOLOv3 architecture, implemented in PyTorch. It provides a complete pipeline for identifying and localizing objects in images and video using a single neural network pass, combining a Darknet-53 backbone with multi-scale feature pyramids and anchor-based bounding box prediction. The framework extends beyond basic detection to include instance segmentation, human pose estimation, and multi-object tracking across video frames. It offers a model export toolkit that converts trained models through ONNX to CoreML, TensorFlow Lite, and Ten

    Exports trained models to ONNX, CoreML, TFLite, and TensorRT for production deployment.

    Pythondeep-learningmachine-learningobject-detection
    Ver en GitHub↗10,571
  • megvii-basedetection/yoloxAvatar de Megvii-BaseDetection

    Megvii-BaseDetection/YOLOX

    10,504Ver en GitHub↗

    YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

    Ships a dedicated export pipeline converting trained detection models to ONNX, TensorRT, ncnn, OpenVINO, and MegEngine formats.

    Pythondeep-learningmegenginencnn
    Ver en GitHub↗10,504
  • lyhue1991/eat_tensorflow2_in_30_daysAvatar de lyhue1991

    lyhue1991/eat_tensorflow2_in_30_days

    9,933Ver en GitHub↗

    This project is a structured learning curriculum and technical reference for mastering deep learning with TensorFlow. It provides a comprehensive guide for building, training, and deploying neural networks, combining theoretical fundamentals with practical implementation examples. The repository distinguishes itself by covering the end-to-end machine learning workflow, from low-level tensor mathematics and linear algebra to the creation of complex model architectures. It includes specific guidance on developing data pipelines for diverse data types, such as images, text, and time-series seque

    Details how to export model weights and parameters into interoperable formats for deployment.

    Pythontensorflowtensorflow-examplestensorflow-tutorial
    Ver en GitHub↗9,933
  • wongkinyiu/yolov9Avatar de WongKinYiu

    WongKinYiu/yolov9

    9,534Ver en GitHub↗

    YOLOv9 is a real-time computer vision framework and deep learning model designed for image classification, object detection, and instance segmentation. It functions as both a vision model and a trainer, allowing for the optimization of neural network weights on custom datasets using single or multiple GPUs. The framework utilizes programmable gradient information to perform high-speed identification and location of multiple objects within images and video streams. It extends beyond bounding box detection to provide instance segmentation and panoptic segmentation, which labels every pixel in a

    Exports trained models into multiple formats like ONNX and TensorRT for diverse hardware deployment.

    Pythonyolov9
    Ver en GitHub↗9,534
  • catboost/catboostAvatar de catboost

    catboost/catboost

    8,808Ver en GitHub↗

    CatBoost is a gradient boosting machine learning library used to train decision tree ensembles for regression, classification, and ranking tasks. It functions as a high-performance framework that provides a categorical data processor for transforming non-numeric features, a distributed trainer for large-scale datasets, and GPU acceleration to speed up model construction. The library distinguishes itself through native handling of categorical data and text features, removing the need for manual encoding. It includes a specialized model interpretability tool that leverages SHAP values and featu

    Exports trained models to ONNX, PMML, or CoreML for high-speed execution in production environments or databases.

    C++big-datacatboostcategorical-features
    Ver en GitHub↗8,808
  • tensorflow/tfjs-coreAvatar de tensorflow

    tensorflow/tfjs-core

    8,437Ver en GitHub↗

    TensorFlow.js is a JavaScript machine learning library and browser-based runtime used to build, train, and execute models. It functions as a WebGL accelerated tensor engine, providing a foundation for high-performance linear algebra operations and an automatic differentiation framework for computing gradients. The project distinguishes itself through its ability to run machine learning directly in web environments, supporting both client-side inference and browser-based training. It enables the deployment of Python-based models by converting Keras or TensorFlow models into compatible formats

    Imports TFLite flatbuffers from URLs or memory buffers into an interpreter for execution.

    TypeScriptdeep-learningdeep-neural-networksgpu-acceleration
    Ver en GitHub↗8,437
  • paddlepaddle/paddleganAvatar de PaddlePaddle

    PaddlePaddle/PaddleGAN

    8,043Ver en GitHub↗

    PaddleGAN is a generative AI framework and deep learning computer vision library built on the PaddlePaddle framework. It serves as a toolkit for image and video synthesis, providing a collection of generative adversarial network implementations for creating synthetic visual content. The library focuses on advanced synthesis capabilities, including the generation of talking heads through lip motion synchronization and the creation of synthetic videos via motion transfer from driving sequences. It provides tools for domain-to-domain translation, allowing for image style transfer and the transfo

    Converts trained generative models into deployable formats by specifying dimensions and weights.

    Pythonanimeganv2basicvsrpluspluscyclegan
    Ver en GitHub↗8,043
  • linzaer/ultra-light-fast-generic-face-detector-1mbAvatar de Linzaer

    Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB

    7,536Ver en GitHub↗

    Este proyecto proporciona un conjunto de modelos ligeros de detección facial diseñados para inferencia de alta velocidad en dispositivos de computación de borde (edge computing). Se centra en una arquitectura de red neuronal compacta que permite la detección de rostros humanos en entornos caracterizados por recursos de cómputo limitados y restricciones de energía. El sistema cuenta con detectores faciales cuantizados disponibles en múltiples formatos para garantizar la compatibilidad entre diversas arquitecturas de hardware. Incluye utilidades para la exportación y cuantización de modelos, permitiendo que los pesos entrenados se conviertan a formatos estandarizados para un despliegue agnóstico al hardware. El proyecto cubre flujos de trabajo para el entrenamiento de modelos personalizados y el procesamiento de conjuntos de datos de imágenes para ajustar perfiles de precisión y velocidad. Admite tareas de visión artificial en tiempo real mediante el uso de aritmética de solo enteros y un runtime de inferencia basado en C para minimizar la sobrecarga en hardware embebido.

    Includes toolkits to convert trained weights into multiple standardized formats for cross-platform deployment.

    Python
    Ver en GitHub↗7,536
  • h2oai/h2o-3Avatar de h2oai

    h2oai/h2o-3

    7,493Ver en GitHub↗

    h2o-3 is a distributed machine learning platform and automated machine learning framework designed for training and deploying predictive models using distributed in-memory computing. It functions as a deep learning framework and a distributed model scoring engine, capable of operating as a Kubernetes ML cluster to process large datasets in parallel. The platform distinguishes itself through automated machine learning capabilities that automatically select the best algorithms and hyperparameters to optimize model performance. It provides specialized deep learning toolkits for tasks including i

    Exports trained models into serialized formats to enable high-speed predictions in production environments.

    Jupyter Notebookautomlbig-datadata-science
    Ver en GitHub↗7,493
  • peterl1n/backgroundmattingv2Avatar de PeterL1n

    PeterL1n/BackgroundMattingV2

    7,178Ver en GitHub↗

    BackgroundMattingV2 is a deep learning background matting tool and real-time image segmentation framework. It provides a system for isolating foreground subjects from high-resolution images and video feeds in real time. The project includes a deep learning model trainer for optimizing matting models through base convergence and end-to-end refinement. It also functions as a cross-runtime model exporter, converting trained neural networks into interchangeable formats for deployment across different software environments and hardware runtimes. The framework supports streaming processed webcam f

    Converts trained matting models into multiple interchangeable formats like ONNX for cross-platform deployment.

    Pythoncomputer-visionmachine-learningmatting
    Ver en GitHub↗7,178
  • google-research/text-to-text-transfer-transformerAvatar de google-research

    google-research/text-to-text-transfer-transformer

    6,528Ver en GitHub↗

    Este es un framework de machine learning para tratar diversas tareas de procesamiento de lenguaje natural como un problema unificado de texto a texto. Proporciona un toolkit para pre-entrenar y ajustar modelos transformer a gran escala, utilizando un sistema donde tanto las entradas como las salidas se formatean como secuencias de texto crudo. El framework se distingue por su sistema de entrenamiento distribuido, que utiliza estrategias basadas en malla para escalar pesos de modelos y lotes de entrenamiento a través de múltiples núcleos TPU. Soporta aprendizaje multitarea combinando diversos datasets en un único flujo de entrenamiento utilizando tasas de mezcla configurables, permitiendo que un único modelo maneje varias tareas de lenguaje. El sistema cubre una amplia gama de capacidades, incluyendo arquitecturas codificador-decodificador, decodificación de búsqueda de haz (beam-search) para generación de texto y flujos de trabajo de transfer learning. Incluye utilidades para la preparación de datasets de NLP, evaluación del rendimiento del modelo y exportación de checkpoints entrenados para servir en producción. La biblioteca soporta la carga de checkpoints de modelos pre-entrenados de varios tamaños para acelerar el desarrollo.

    Converts trained checkpoints into deployment-ready formats suitable for production environments or container images.

    Python
    Ver en GitHub↗6,528
  • foundationvision/bytetrackAvatar de FoundationVision

    FoundationVision/ByteTrack

    6,492Ver en GitHub↗

    ByteTrack is a multi-object tracking framework that implements the ByteTrack algorithm, an ECCV 2022 method designed to recover occluded objects and reduce trajectory fragmentation. The core innovation of the project is its association algorithm, which processes every detection box—including low-confidence ones—by using separate high and low score thresholds, Kalman filter motion prediction, and Hungarian algorithm matching to produce consistent object identities across video frames. The project distinguishes itself by its comprehensive approach to handling occlusions and fragmented trajector

    Exports tracking models to ONNX, TensorRT, ncnn, and DeepStream formats for production inference.

    Pythondeploymentmulti-object-trackingpytorch
    Ver en GitHub↗6,492
  • ailab-cvc/yolo-worldAvatar de AILab-CVC

    AILab-CVC/YOLO-World

    6,425Ver en GitHub↗

    YOLO-World is a vision-language framework and open-vocabulary object detection model. It identifies objects in images and video based on free-form text prompts without requiring predefined category labels. The system enables the identification of arbitrary objects by fusing image features with text embeddings. It includes a specialized tool for automated image labeling, which generates bounding box annotations for custom datasets using text-based prompts. The project provides a deployment pipeline for converting models into quantized ONNX and TFLite formats, supporting real-time inference on

    Converts models to TFLite format using INT8 quantization for efficient mobile deployment.

    Python
    Ver en GitHub↗6,425
  • dragen1860/tensorflow-2.x-tutorialsAvatar de dragen1860

    dragen1860/TensorFlow-2.x-Tutorials

    6,351Ver en GitHub↗

    This project is a collection of TensorFlow 2.x machine learning tutorials and practical code examples. It serves as a deep learning implementation guide for constructing diverse neural network architectures, including convolutional, recurrent, and generative networks. The repository provides templates and examples for several specialized domains, including computer vision for image classification and object detection, natural language processing for text generation and language understanding, and generative AI for synthesizing data using adversarial networks and autoencoders. It also includes

    Provides interoperable formats for exporting trained models to different runtimes and production environments.

    Jupyter Notebookartificial-intelligencecomputer-visiondeep-learning
    Ver en GitHub↗6,351
  • thtrieu/darkflowAvatar de thtrieu

    thtrieu/darkflow

    6,140Ver en GitHub↗

    Darkflow es un framework de detección de objetos y pipeline de visión artificial que proporciona una interfaz programática para realizar análisis de imágenes y detección de objetos en tiempo real. Funciona como una herramienta para cargar pesos, ajustar modelos y ejecutar inferencia tanto en imágenes estáticas como en feeds de video. El proyecto sirve como un convertidor que traduce configuraciones y pesos de Darknet a grafos de TensorFlow para permitir el reentrenamiento y el despliegue. Incluye un exportador de modelos que guarda los grafos entrenados en archivos protobuf portátiles para su uso en dispositivos móviles y nativos. El sistema cubre capacidades para entrenar y ajustar modelos de detección en datasets personalizados, con puntos de control de progreso para la recuperación del entrenamiento. También proporciona herramientas para la traducción de mapeo de pesos y el procesamiento de datos de imagen crudos a través de operaciones de tensores para producir cajas delimitadoras y puntuaciones de confianza.

    Saves trained graphs and weights into portable binary formats like Protobuf for deployment on mobile devices.

    Python
    Ver en GitHub↗6,140
  • ofa-sys/chinese-clipAvatar de OFA-Sys

    OFA-Sys/Chinese-CLIP

    5,942Ver en GitHub↗

    Chinese-CLIP es un framework multimodal y modelo de visión-lenguaje diseñado para la recuperación intermodal y la generación de representaciones utilizando texto e imágenes en chino. Emplea una arquitectura de aprendizaje contrastivo para mapear datos visuales y textuales en un espacio vectorial compartido para cálculos de similitud. El sistema permite la búsqueda bidireccional, facilitando la recuperación de texto a imagen e imagen a texto. También proporciona clasificación de imágenes zero-shot, que identifica objetos dentro de imágenes sin requerir entrenamiento específico para la tarea. El proyecto incluye herramientas para el ajuste fino (fine-tuning) de modelos preentrenados en conjuntos de datos especializados mediante entrenamiento distribuido y aprendizaje contrastivo. También proporciona utilidades para exportar pesos de modelos a formatos optimizados para aumentar la velocidad de inferencia en entornos de producción.

    Includes utilities to export model weights into optimized formats for faster production inference.

    Jupyter Notebook
    Ver en GitHub↗5,942
  • open-edge-platform/anomalibAvatar de open-edge-platform

    open-edge-platform/anomalib

    5,871Ver en GitHub↗

    Anomalib is a PyTorch-based library for visual anomaly detection, offering a modular framework, a comprehensive model zoo, and a benchmarking suite designed for industrial defect detection. It provides a wide range of algorithms—including generative, discriminative, teacher-student, and vision-language approaches—that support unsupervised, few-shot, and zero-shot settings. The library enables deployment through model export to ONNX and OpenVINO for edge devices, and includes a no-code web application for training and inference. It also features a command-line interface for orchestrating multi

    Converts trained models to ONNX, OpenVINO IR, or PyTorch for production deployment.

    Pythonanomaly-detectionanomaly-localizationanomaly-segmentation
    Ver en GitHub↗5,871
  • microsoft/mmdnnAvatar de Microsoft

    Microsoft/MMdnn

    5,804Ver en GitHub↗

    MMdnn es un conversor y migrador de modelos de deep learning diseñado para traducir arquitecturas y pesos de redes neuronales entre diferentes frameworks como TensorFlow, PyTorch y Keras. Utiliza una representación intermedia estandarizada para desacoplar las estructuras de red y los pesos de las implementaciones específicas de cada framework, permitiendo la transformación de modelos preentrenados entre distintos entornos. El proyecto destaca por generar código de reconstrucción nativo en Python a partir de sus representaciones intermedias, lo que permite reconstruir y ajustar modelos en los entornos de destino. También incluye herramientas especializadas para el despliegue de modelos en dispositivos móviles, transformando modelos de deep learning a formatos compatibles como CoreML y TensorFlow Lite. El sistema ofrece un conjunto más amplio de capacidades, incluyendo la visualización de arquitecturas de redes neuronales para inspeccionar estructuras de grafos y metadatos, así como la ejecución de inferencia para validar que los modelos convertidos mantengan su comportamiento y precisión originales. Otras utilidades gestionan la recuperación de pesos preentrenados desde repositorios remotos y el ensamblaje de checkpoints de modelos desplegables.

    Synthesizes original framework-specific model binaries by combining generated architecture code and binary weight data.

    Python
    Ver en GitHub↗5,804
  • roboflow/rf-detrAvatar de roboflow

    roboflow/rf-detr

    5,643Ver en GitHub↗

    RF-DETR is a Python library for training and deploying object detection, instance segmentation, and keypoint detection models built on a vision transformer architecture. It provides a unified command-line interface and Python API for the full workflow, from fine-tuning pretrained checkpoints on custom datasets to running inference on images, video files, and live camera streams. The project supports training on datasets in COCO or YOLO format, with automatic format detection and configurable augmentation pipelines. Models can be exported to ONNX, TFLite, or TensorRT for deployment across edge

    Converts trained detection models to ONNX and TFLite for production deployment.

    Pythoncomputer-visiondetrinstance-segmentation
    Ver en GitHub↗5,643
  • mosaicml/composerAvatar de mosaicml

    mosaicml/composer

    5,485Ver en GitHub↗

    Composer es un framework de entrenamiento distribuido para PyTorch diseñado para escalar modelos a gran escala en clústeres de GPU multi-nodo. Funciona como un entrenador de modelos de lenguaje de gran tamaño (LLM), un optimizador de modelos distribuidos y un gestor del ciclo de vida de entrenamiento. El proyecto se diferencia como una biblioteca de regularización para deep learning, proporcionando técnicas de optimización especializadas como Sharpness Aware Minimization, MixUp y CutMix para mejorar la generalización del modelo. Además, distingue su flujo de entrenamiento mediante el uso de warmup de longitud de secuencia, congelación progresiva de capas y checkpointing de estado fragmentado (sharded-state) para la recuperación de modelos a gran escala. El framework cubre una amplia superficie de capacidades, incluyendo la orquestación de entrenamiento distribuido, la gestión de hardware de precisión mixta y el streaming de datos cloud-native. También proporciona herramientas extensas de monitoreo y observabilidad para diagnósticos de memoria de GPU, detección de divergencia en el entrenamiento y seguimiento del rendimiento (throughput). El proyecto incluye un lanzador de línea de comandos para automatizar la ejecución de trabajos de entrenamiento multi-GPU entre nodos.

    Converts trained models into portable formats optimized for production deployment and storage.

    Python
    Ver en GitHub↗5,485
Ant.12Siguiente
  1. Home
  2. DevOps & Infrastructure
  3. Deployment Management
  4. Model Export Formats

Explorar subetiquetas

  • CoreML Export TranslatorsSpecialized utilities for translating deep learning models into the CoreML format. **Distinct from Model Export Formats:** Specific to the CoreML target format, distinct from general model export formats.
  • Detection Model ExportersTools that serialize trained detection models into production-ready formats for deployment on diverse hardware platforms. **Distinct from Model Export Formats:** Distinct from Model Export Formats: focuses on the export pipeline for detection models specifically, not general model serialization formats.
  • MCP Format ConvertersConverts registered tools into the standard format used by the Model Context Protocol. **Distinct from Model Export Formats:** Distinct from Model Export Formats: focuses on converting tool definitions for MCP, not exporting trained models.
  • Multi-Format Exporters1 sub-etiquetaToolkits that convert trained models to ONNX, CoreML, TFLite, and TensorRT formats for cross-platform deployment. **Distinct from Model Export Formats:** Distinct from Model Export Formats: focuses on the export pipeline supporting multiple target formats (ONNX, CoreML, TFLite, TensorRT) rather than a single format.
  • ONNX and TFLite Model ExportersUtilities for converting machine learning models into both ONNX and TFLite formats for cross-platform deployment. **Distinct from TFLite Exports:** Covers both ONNX and TFLite export paths in a single pipeline, whereas candidates focus on either TFLite or ONNX exclusively.
  • Single-Command Model ExportsExporting models to optimized formats using a unified CLI or configuration file. **Distinct from Model Export Formats:** Distinct from Model Export Formats: focuses on the one-command export workflow rather than the serialization format itself.
  • System Architecture ExportersUtilities for converting internal system models into standard deployment formats like JSON or modular code. **Distinct from Model Export Formats:** Distinct from Model Export Formats: focuses on exporting entire system architectures for deployment, not just individual ML model weights.
  • TFLite ExportsConverting models to TFLite format for deployment on mobile devices, microcontrollers, and edge hardware. **Distinct from Model Export Formats:** Distinct from Model Export Formats: specifically targets TFLite format for mobile and edge deployment, not general export formats like ONNX or CoreML.
  • TFLite InterpretersRuntimes that import and execute TFLite flatbuffers. **Distinct from TFLite Exports:** Distinct from TFLite exports which focus on conversion; this focuses on the interpretation and execution of the format.