3 repositorios
Awesome GitHub RepositoriesCustom Point Cloud Dataset Training
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.
Awesome Custom Point Cloud Dataset Training GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- open-mmlab/mmdetection3d
open-mmlab/mmdetection3d
6,273Ver en GitHubMMDetection3D 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.
Python3d-object-detectionobject-detectionpoint-cloud - meta-pytorch/torchtune
meta-pytorch/torchtune
5,774Ver en GitHubTorchtune 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.
Python - sshaoshuai/pcdet
sshaoshuai/PCDet
5,621Ver en GitHubPCDet es una caja de herramientas para la detección de objetos 3D mediante LiDAR y una librería de procesamiento de nubes de puntos construida sobre el framework de deep learning PyTorch. Proporciona un sistema para identificar y localizar objetos tridimensionales dentro de datos de nubes de puntos. El proyecto utiliza un patrón de separación de datos y modelo para desacoplar la lógica de carga del dataset del pipeline de detección principal. Cuenta con un pipeline de fusión multisensor que combina datos de múltiples sensores en una vista espacial compartida y un sistema de entrenamiento distribuido en GPU para escalar las cargas de trabajo a través de múltiples procesadores gráficos. El toolkit cubre varias áreas de capacidad, incluyendo la extracción de características basada en vóxeles y el análisis temporal de nubes de puntos mediante fusión de múltiples fotogramas. También incorpora optimizaciones de rendimiento para la intersección sobre unión 3D acelerada por GPU y la supresión de no máximos rotada.
Supports the integration and training of custom point cloud datasets with specific annotations.
Python
