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

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
amdegroot avatar

amdegroot/ssd.pytorch

0
View on GitHub↗
5,224 stars·1,724 forks·Python·MIT·13 vues

Ssd.pytorch

Il s'agit d'un framework de détection d'objets PyTorch qui implémente le Single Shot MultiBox Detector pour identifier et localiser plusieurs objets au sein d'images et de vidéos. Le projet fournit une architecture de réseau de neurones conçue pour la détection d'objets en un seul passage (single-shot), qui prédit les boîtes englobantes et les étiquettes de classe en une seule passe.

L'implémentation inclut un détecteur d'objets en temps réel capable de traiter des flux vidéo en direct pour suivre et étiqueter des objets à travers des images séquentielles. Il dispose également d'un pipeline complet d'entraînement en vision par ordinateur pour préparer les jeux de données d'images et entraîner les poids des modèles.

Le framework couvre le workflow de bout en bout pour les tâches de vision, incluant le chargement des jeux de données, l'entraînement de modèles de deep learning avec accélération matérielle, et l'évaluation quantitative de la performance en utilisant des métriques et des scripts dédiés.

Features

  • Single Shot Detectors - Implements a single-shot detector architecture that predicts bounding boxes and class labels in a single pass.
  • Object Detection - Identifies and localizes multiple objects within images by generating bounding boxes and class labels.
  • Real-Time Object Detection - Processes live video streams in real time to identify and track objects across sequential frames.
  • Detection Model Training - Optimizes model weights for object detection using standard datasets, configurable learning rates, and GPU acceleration.
  • Object Detection Training - Provides a training pipeline to teach the model to recognize object classes using labeled datasets and hardware acceleration.
  • PyTorch Tensor Operations - Utilizes PyTorch tensor operations and dynamic computational graphs for efficient gradient descent and hardware acceleration.
  • SSD Implementations - Implements the neural network architecture based on the Single Shot MultiBox Detector protocol for real-time localization.
  • PyTorch Computer Vision Pipelines - Offers a complete PyTorch-based workflow for image dataset preparation, model training, and detection accuracy evaluation.
  • Object Detection Frameworks - Serves as a comprehensive framework for implementing the Single Shot MultiBox Detector for object identification in images and video.
  • Anchor Box Systems - Implements a system for defining reference bounding boxes of various scales and aspect ratios as object detection priors.
  • Multi-Scale Feature Pyramids - Extracts detections from multiple convolutional layers to capture objects across different spatial scales.
  • Smooth L1 Loss Calculators - Uses a Smooth-L1 loss function to robustly regress bounding box coordinates while minimizing outlier influence.
  • Model Evaluation Metrics - Provides tools and metrics to quantitatively measure the performance and quality of trained detection models.
  • Object Detection Evaluators - Includes evaluation scripts to measure the accuracy of predicted bounding boxes against ground truth.
  • Vision Dataset Preparation - Provides utilities for downloading, preparing, and loading image collections into the training pipeline.
  • Vision par ordinateur - Single Shot MultiBox Detector implementation.
  • Computer Vision Models - Implementation of the Single Shot MultiBox Detector.
  • Model Implementations - Single shot multibox detector implementation.
  • Object Detection - Listed in the “Object Detection” section of the The Incredible Pytorch awesome list.

Historique des stars

Graphique de l'historique des stars pour amdegroot/ssd.pytorchGraphique de l'historique des stars pour amdegroot/ssd.pytorch

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Alternatives open source à Ssd.pytorch

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Ssd.pytorch.
  • ultralytics/yolov3Avatar de ultralytics

    ultralytics/yolov3

    10,571Voir sur 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

    Pythondeep-learningmachine-learningobject-detection
    Voir sur GitHub↗10,571
  • eriklindernoren/pytorch-yolov3Avatar de eriklindernoren

    eriklindernoren/PyTorch-YOLOv3

    7,439Voir sur GitHub↗

    This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time object detector and computer vision framework designed to identify and locate multiple objects within images using bounding boxes and class labels. The system allows for both the use of pretrained weights for immediate image analysis and the training of custom models using datasets with bounding box annotations. It provides a programmatic interface to integrate detection capabilities directly into other software applications. The framework includes tools for model evaluation to m

    Python
    Voir sur GitHub↗7,439
  • jwyang/faster-rcnn.pytorchAvatar de jwyang

    jwyang/faster-rcnn.pytorch

    7,859Voir sur GitHub↗

    This project is a PyTorch object detection framework that implements the Faster R-CNN architecture. It serves as a vision model for predicting precise bounding boxes around multiple objects within images and live video feeds. The system is optimized for multi-GPU training to reduce the time required for model convergence. It utilizes a GPU-accelerated design to handle the training and inference of complex detection networks. The framework covers the full object detection lifecycle, including custom network training and inference for static images and real-time video streams. It includes capa

    Python
    Voir sur GitHub↗7,859
  • paddlepaddle/paddledetectionAvatar de PaddlePaddle

    PaddlePaddle/PaddleDetection

    14,243Voir sur GitHub↗

    PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

    Pythonblazefacedeepsortdetr
    Voir sur GitHub↗14,243
Voir les 30 alternatives à Ssd.pytorch→

Questions fréquentes

Que fait amdegroot/ssd.pytorch ?

Il s'agit d'un framework de détection d'objets PyTorch qui implémente le Single Shot MultiBox Detector pour identifier et localiser plusieurs objets au sein d'images et de vidéos. Le projet fournit une architecture de réseau de neurones conçue pour la détection d'objets en un seul passage (single-shot), qui prédit les boîtes englobantes et les étiquettes de classe en une seule passe.

Quelles sont les fonctionnalités principales de amdegroot/ssd.pytorch ?

Les fonctionnalités principales de amdegroot/ssd.pytorch sont : Single Shot Detectors, Object Detection, Real-Time Object Detection, Detection Model Training, Object Detection Training, PyTorch Tensor Operations, SSD Implementations, PyTorch Computer Vision Pipelines.

Quelles sont les alternatives open-source à amdegroot/ssd.pytorch ?

Les alternatives open-source à amdegroot/ssd.pytorch incluent : ultralytics/yolov3 — This is a real-time object detection framework built on the YOLOv3 architecture, implemented in PyTorch. It provides a… eriklindernoren/pytorch-yolov3 — This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time… jwyang/faster-rcnn.pytorch — This project is a PyTorch object detection framework that implements the Faster R-CNN architecture. It serves as a… paddlepaddle/paddledetection — PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of… chenyuntc/simple-faster-rcnn-pytorch — This project is a PyTorch implementation of the Faster R-CNN architecture for object detection. It provides a… meituan/yolov6 — YOLOv6 is a single-stage deep learning framework designed for industrial object detection. It serves as a computer…