Skip to content
프로젝트 카테고리

머신러닝 · GitHub

모델 학습, 평가, 추론 프레임워크를 찾고 커뮤니티의 관심도를 비교하세요.

유용한 GitHub 프로젝트

12,832 프로젝트

Run

NVIDIA-NeMo

268스타+1in 24h

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

머신러닝PythonApache-2.0GitHub
1,009스타+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.
머신러닝CudaApache-2.0GitHub
299스타+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.

머신러닝PythonApache-2.0GitHub
3,611스타+1in 24h

NVIDIA GPU에서 Transformer 모델을 가속하는 라이브러리입니다. Hopper, Ada, Blackwell GPU에서 8비트 및 4비트 부동소수점 정밀도(FP8 및 FP4)를 사용할 수 있으며, 학습과 추론 모두에서 메모리 사용량을 줄이면서 더 나은 성능을 제공합니다.

  • FP8 training on NVIDIA Hopper, Ada, Blackwell, and Rubin GPUs.
  • MXFP8 and NVFP4 training on NVIDIA Blackwell GPUs.
머신러닝PythonApache-2.0GitHub

kaolin-wisp

NVIDIAGameWorks

1,505스타+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).

2,255스타+1in 24h
MambaVision preview

[CVPR 2025] MambaVision 공식 PyTorch 구현: Mamba와 Transformer를 결합한 하이브리드 비전 백본

5,049스타+1in 24h
machine_learning_complete preview

다양한 개념, 알고리즘, 기법을 다루는 30개 이상의 노트북을 포함한 종합적인 머신러닝 저장소입니다.

머신러닝Jupyter NotebookMITGitHub
6,056스타+1in 24h

CLIP의 중국어 버전으로, 중국어 교차 모달 검색과 표현 생성을 지원합니다.

머신러닝Jupyter NotebookMITGitHub
979스타+1in 24h

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

머신러닝PythonApache-2.0GitHub

mmaction

open-mmlab

1,877스타+1in 24h

PyTorch 기반 오픈 소스 액션 이해 도구 상자

  • action recognition from trimmed videos
  • temporal action detection (also known as action localization) in untrimmed videos
머신러닝PythonApache-2.0GitHub

mmfewshot

open-mmlab

755스타+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.
머신러닝PythonApache-2.0GitHub

mmskeleton

open-mmlab

3,136스타+1in 24h
mmskeleton preview

사람 자세 추정, 스켈레톤 기반 행동 인식 및 행동 합성을 위한 OpenMMLAB 도구 상자입니다.

  • 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)
머신러닝PythonApache-2.0GitHub

OpenPCDet

open-mmlab

5,774스타+1in 24h
OpenPCDet preview

LiDAR 기반 3D 객체 탐지를 위한 OpenPCDet 툴박스입니다.

  • Support both one-stage and two-stage 3D object detection frameworks
  • Support distributed training & testing with multiple GPUs and multiple machines
머신러닝PythonApache-2.0GitHub

geoai

opengeos

3,480스타+1in 24h
geoai preview

GeoAI: 지리공간 데이터를 위한 인공지능

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