3 Repos
Train and evaluate 3D detection models on user-provided point cloud datasets with custom annotations.
Distinct from Training Dataset Processing: Distinct from Training Dataset Processing: focuses on supporting custom point cloud datasets specifically, not general dataset batching.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Custom Point Cloud Dataset Training. Refine with filters or upvote what's useful.
MMDetection3D is an open-source toolbox for 3D perception, providing a unified framework for detecting and segmenting objects in three-dimensional environments. It supports a range of core tasks including monocular 3D object detection from single camera images, LiDAR-based 3D object detection from raw point clouds, and multi-modal fusion that combines camera images with LiDAR data. The toolbox also covers point cloud semantic segmentation, assigning class labels to every point in a scan for scene understanding. The project distinguishes itself through a config-driven pipeline that orchestrate
Provides a pipeline for training 3D detection models on custom point cloud datasets with user-provided annotations.
Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip
Supports fine-tuning on custom instruct, chat, and preference datasets with full-parameter or LoRA methods.
PCDet ist eine Toolbox für LiDAR-3D-Objekterkennung und eine Bibliothek zur Punktwolkenverarbeitung, die auf dem Deep-Learning-Framework PyTorch basiert. Es bietet ein System zur Identifizierung und Lokalisierung dreidimensionaler Objekte innerhalb von Punktwolkendaten. Das Projekt nutzt ein Daten-Modell-Trennungs-Muster, um die Logik zum Laden von Datensätzen von der Kern-Erkennungs-Pipeline zu entkoppeln. Es verfügt über eine Multi-Sensor-Fusions-Pipeline, die Daten von mehreren Sensoren in einer gemeinsamen räumlichen Ansicht kombiniert, sowie ein verteiltes GPU-Trainingssystem zur Skalierung von Workloads über mehrere Grafikprozessoren. Das Toolkit deckt verschiedene Funktionsbereiche ab, darunter voxelbasierte Merkmalsextraktion und zeitliche Punktwolkenanalyse durch Multi-Frame-Fusion. Es integriert zudem Leistungsoptimierungen für GPU-beschleunigte 3D Intersection-over-Union und Rotated Non-Maximum Suppression.
Supports the integration and training of custom point cloud datasets with specific annotations.