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
ProyectoAcerca deCómo clasificamosPrensaServidor MCP
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
NVIDIA-AI-IOT avatar

NVIDIA-AI-IOT/trt_pose

0
View on GitHub↗
1,060 estrellas·298 forks·Python·MIT·12 vistas

Trt Pose

Este proyecto es un framework de visión artificial diseñado para la detección en tiempo real de puntos clave del cuerpo humano y estructuras esqueléticas. Proporciona un kit de herramientas integrado para entrenar, optimizar y ejecutar modelos de estimación de pose específicamente para su despliegue en hardware de computación de borde.

El framework se distingue por utilizar mapeo de campos de afinidad de partes para codificar relaciones espaciales entre articulaciones, que luego se procesan a través de un algoritmo de análisis codicioso para reconstruir esqueletos humanos a partir de datos visuales. Para asegurar una ejecución de alto rendimiento, la biblioteca incorpora cuantización de modelos y motores de inferencia acelerados por hardware que optimizan los grafos computacionales para hardware local específico.

Más allá de la detección central, el proyecto admite flujos de trabajo de extremo a extremo que incluyen el desarrollo de modelos de pose personalizados utilizando esquemas de conjuntos de datos estandarizados. Estas capacidades permiten el ajuste fino de modelos para abordar tareas de detección únicas mientras se mantienen los requisitos de baja latencia necesarios para el análisis de transmisiones de video en vivo.

Features

  • Human Pose Detections - Ships a high-performance inference engine for real-time detection of human skeletal joints in video streams.
  • Pose Estimation Training Pipelines - Supports end-to-end workflows for training specialized pose estimation models using custom dataset schemas.
  • Vision Detection Model Training - Enables fine-tuning of pose estimation models on specialized datasets to improve detection accuracy for unique tasks.
  • Deep Learning Motion Tracking Toolkits - Provides an integrated toolkit for training and deploying pose estimation models on edge devices.
  • Fine-Tuning Dataset Loaders - Provides utilities for importing and formatting custom datasets to fine-tune pose estimation models.
  • TensorRT Engine Compilation - Compiles models into optimized TensorRT engines to achieve low-latency inference on NVIDIA hardware.
  • Edge AI Model Deployment - Optimizes and deploys deep learning models for efficient execution on local edge hardware.
  • Pose Estimation Frameworks - Provides a computer vision framework optimized for real-time human pose estimation on NVIDIA hardware.
  • Quantized Model Implementations - Incorporates model quantization to reduce numerical precision and accelerate inference on edge hardware.
  • Vector Field Estimation - Utilizes part affinity field mapping to encode spatial relationships between body joints for skeletal reconstruction.
  • Pose Parsing Algorithms - Implements a greedy parsing algorithm to reconstruct human skeletons from spatial vector fields.

Historial de estrellas

Gráfico del historial de estrellas de nvidia-ai-iot/trt_poseGráfico del historial de estrellas de nvidia-ai-iot/trt_pose

Búsqueda con IA

Explora más repositorios increíbles

Describe lo que necesitas en lenguaje sencillo: la IA clasifica miles de proyectos open-source curados por relevancia.

Start searching with AI

Colecciones destacadas con Trt Pose

Colecciones seleccionadas manualmente donde aparece Trt Pose.
  • Herramientas de estimación de pose humana

Preguntas frecuentes

¿Qué hace nvidia-ai-iot/trt_pose?

Este proyecto es un framework de visión artificial diseñado para la detección en tiempo real de puntos clave del cuerpo humano y estructuras esqueléticas. Proporciona un kit de herramientas integrado para entrenar, optimizar y ejecutar modelos de estimación de pose específicamente para su despliegue en hardware de computación de borde.

¿Cuáles son las características principales de nvidia-ai-iot/trt_pose?

Las características principales de nvidia-ai-iot/trt_pose son: Human Pose Detections, Pose Estimation Training Pipelines, Vision Detection Model Training, Deep Learning Motion Tracking Toolkits, Fine-Tuning Dataset Loaders, TensorRT Engine Compilation, Edge AI Model Deployment, Pose Estimation Frameworks.

¿Qué alternativas de código abierto existen para nvidia-ai-iot/trt_pose?

Las alternativas de código abierto para nvidia-ai-iot/trt_pose incluyen: tensorboy/pytorch_realtime_multi-person_pose_estimation — This project is a deep learning framework built for detecting and tracking human body keypoints in images and video… zhec/realtime_multi-person_pose_estimation — This is a multi-person pose estimation framework designed for real-time human keypoint detection. It functions as a… leoxiaobin/deep-high-resolution-net.pytorch — This project is a PyTorch implementation of a research architecture designed for high-resolution representation… deeplabcut/deeplabcut — DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion… hrnet/higherhrnet-human-pose-estimation — HigherHRNet is a deep learning framework designed for bottom-up human pose estimation. It functions as a computer… roboflow/rf-detr — RF-DETR is a Python library for training and deploying object detection, instance segmentation, and keypoint detection…

Alternativas open-source a Trt Pose

Proyectos open-source similares, clasificados según cuántas características comparten con Trt Pose.
  • tensorboy/pytorch_realtime_multi-person_pose_estimationAvatar de tensorboy

    tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation

    1,372Ver en GitHub↗

    This project is a deep learning framework built for detecting and tracking human body keypoints in images and video streams. It functions as both a real-time motion tracking system and a machine learning environment for training and evaluating pose estimation models. The system utilizes a two-branch convolutional neural network to predict body part locations and their directional connections simultaneously. It employs multi-stage feature refinement to improve keypoint localization accuracy and uses greedy parsing and bipartite matching algorithms to associate detected parts into individual sk

    Python
    Ver en GitHub↗1,372
  • zhec/realtime_multi-person_pose_estimationAvatar de ZheC

    ZheC/Realtime_Multi-Person_Pose_Estimation

    5,123Ver en GitHub↗

    This is a multi-person pose estimation framework designed for real-time human keypoint detection. It functions as a bottom-up human pose estimator that identifies skeletal joints across all people in a scene without requiring a separate person detector. The system utilizes a convolutional neural network model to generate heatmaps and vector fields for posture analysis. It specifically implements part affinity fields to encode the location and orientation of limbs, allowing the model to connect individual joints into complete skeletons. The project covers computer vision motion analysis and d

    Jupyter Notebookcaffecomputer-visioncpp11
    Ver en GitHub↗5,123
  • leoxiaobin/deep-high-resolution-net.pytorchAvatar de leoxiaobin

    leoxiaobin/deep-high-resolution-net.pytorch

    4,479Ver en GitHub↗

    This project is a PyTorch implementation of a research architecture designed for high-resolution representation learning. It serves as a computer vision framework focused on precise keypoint detection, human pose estimation, and semantic image segmentation. The implementation provides specialized tools for identifying anatomical landmarks on the human body and predicting facial keypoint coordinates to analyze orientation and alignment. It utilizes a system of multi-resolution parallel streams and repeated multi-scale fusion to maintain high-resolution representations throughout the network.

    Cuda
    Ver en GitHub↗4,479
  • deeplabcut/deeplabcutD

    DeepLabCut/DeepLabCut

    5,694Ver en GitHub↗

    DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion tracking system that identifies anatomical keypoints on animals in video sequences without the need for physical markers. The framework utilizes transfer learning and a library of pre-trained weights to accelerate the training of networks for different species. It supports multi-individual identity tracking to maintain unique identities across video sequences and offers real-time pose detection for live video feeds. The system covers a broad range of computer vision capabilities, i

    Python
    Ver en GitHub↗5,694
Ver las 30 alternativas a Trt Pose→