Skip to content
Projektkategorien

Maschinelles Lernen · GitHub

Finde Frameworks zum Trainieren, Bewerten und Ausführen von Modellen und vergleiche das Community-Interesse.

Nützliche GitHub-Projekte

12,832 Projekte

Run

NVIDIA-NeMo

268Sterne+1in 24h

A tool to configure, launch and manage your machine learning experiments.

1,009Sterne+1in 24h
cudnn-frontend preview

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

  • Unified Graph API: Create reusable, persistent cudnn_frontend::graph::Graph objects to describe complex subgraphs.
  • Ease of Use: Simplified C++ and Python bindings (via nanobind) that abstract away the boilerplate of the backend API.
299Sterne+1in 24h
TensorRT-Model-Connect preview

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible user experience.

3,611Sterne+1in 24h

Eine Bibliothek zur Beschleunigung von Transformer-Modellen auf NVIDIA-GPUs. Auf Hopper-, Ada- und Blackwell-GPUs unterstützt sie unter anderem 8- und 4-Bit-Gleitkommagenauigkeit (FP8 und FP4), um sowohl beim Training als auch bei der Inferenz eine bessere Leistung bei geringerem Speicherverbrauch zu bieten.

  • FP8 training on NVIDIA Hopper, Ada, Blackwell, and Rubin GPUs.
  • MXFP8 and NVFP4 training on NVIDIA Blackwell GPUs.

kaolin-wisp

NVIDIAGameWorks

1,505Sterne+1in 24h
kaolin-wisp preview

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).

2,255Sterne+1in 24h
MambaVision preview

[CVPR 2025] Offizielle PyTorch-Implementierung von MambaVision: ein hybrider Mamba-Transformer-Backbone für Computer Vision

6,056Sterne+1in 24h

Chinesische Version von CLIP für die chinesische modalitätsübergreifende Suche und die Generierung von Repräsentationen.

Maschinelles LernenJupyter NotebookMITGitHub
979Sterne+1in 24h

A TensorFlow based wake word detection training framework using synthetic sample generation suitable for certain microcontrollers.

mmaction

open-mmlab

1,877Sterne+1in 24h

Eine Open-Source-Toolbox für Action Understanding auf Basis von PyTorch

  • action recognition from trimmed videos
  • temporal action detection (also known as action localization) in untrimmed videos

mmfewshot

open-mmlab

755Sterne+1in 24h
mmfewshot preview

OpenMMLab FewShot Learning Toolbox and Benchmark

  • Support multiple tasks in Few Shot Learning MMFewShot provides unified implementation and evaluation of few shot classification and detection.
  • Modular Design We decompose the few shot learning framework into different components, which makes it much easy and flexible to build a new model by combining different modules.

mmskeleton

open-mmlab

3,136Sterne+1in 24h
mmskeleton preview

Eine OpenMMLAB-Toolbox zur Schätzung menschlicher Posen, zur skelettbasierten Aktionserkennung und zur Aktionssynthese.

  • High extensibility MMSkeleton provides a flexible framework for organizing codes and projects systematically, with the ability to extend to various tasks and scale up to complex deep models.
  • skeleton-based action recognition (ST-GCN)

OpenPCDet

open-mmlab

5,774Sterne+1in 24h
OpenPCDet preview

OpenPCDet-Toolbox für die LiDAR-basierte 3D-Objekterkennung.

  • Support both one-stage and two-stage 3D object detection frameworks
  • Support distributed training & testing with multiple GPUs and multiple machines

geoai

opengeos

3,480Sterne+1in 24h
geoai preview

GeoAI: Künstliche Intelligenz für Geodaten

  • Change detection with AI-enhanced feature extraction
  • Object detection in aerial and satellite imagery