3 repository-uri
Awesome GitHub RepositoriesPerception Dataset Processors
Parallel computing tools for training perception models on massive, partially-labeled datasets.
Distinct from Large-Scale Training Frameworks: Distinct from general training frameworks: focuses on perception-specific dataset processing at scale.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Perception Dataset Processors. Refine with filters or upvote what's useful.
Awesome Perception Dataset Processors GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- google-research/google-research
google-research/google-research
38,139Vezi pe GitHubThis repository serves as a comprehensive research platform and toolkit for advancing machine learning, quantum computing, and large-scale scientific data analysis. It provides foundational frameworks for developing complex algorithmic systems, offering the necessary infrastructure for distributed training, computational graph execution, and high-performance model development. The project distinguishes itself by integrating specialized research domains with robust, privacy-preserving methodologies. It supports diverse scientific discovery through tools for quantum simulation, physics-informed
Utilizes parallel computing clusters to train machine learning models on massive datasets for perception tasks.
Jupyter Notebookaimachine-learningresearch - opendrivelab/uniad
OpenDriveLab/UniAD
4,645Vezi pe GitHubUniAD este un framework unificat de deep learning pentru condus autonom, care integrează percepția, predicția și planificarea într-un singur model end-to-end. Acesta funcționează ca o arhitectură de rețea neuronală care mapează datele brute de la senzori direct în traiectorii de condus și planuri de mișcare. Acest proiect servește drept implementare de cercetare a unei abordări orientate pe planificare, care antrenează simultan module de ocupare, mapare și urmărire a obiectelor. Utilizează un framework de percepție multi-task pentru a optimiza performanța generală de condus. Sistemul acoperă o gamă largă de capabilități, inclusiv pipeline-uri de condus end-to-end, optimizarea mișcării vehiculului și agregarea caracteristicilor vizuale. Acesta coordonează diverse sarcini de condus autonom pentru a rafina întregul proces într-un singur ciclu de antrenament.
Creates stable weights for tracking and mapping by aggregating visual features across multiple video frames.
Pythonautonomous-drivingautonomous-driving-frameworkbev-segmentation - open-mmlab/mmtracking
open-mmlab/mmtracking
3,881Vezi pe GitHubmmtracking is a PyTorch video perception framework designed for training and deploying computer vision models that analyze sequential image data. It provides specialized tools for multi-object tracking, video instance segmentation, and a configuration-driven system for managing deep learning models. The project utilizes a deep learning model registry and a configuration-driven pipeline to swap model backbones and detectors without modifying the core codebase. This modular approach allows for the development of custom perception architectures by combining various components and configurations.
Provides specialized training processes and schedules for optimizing object tracking and video perception modules.
Pythonmulti-object-trackingsingle-object-trackingtracking
