Skip to content
프로젝트 카테고리

머신러닝 · GitHub

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

유용한 GitHub 프로젝트

12,802 프로젝트

HUST-CS

Nuyoahwjl

157스타
HUST-CS preview

华中科技大学计算机学院23级课程存档:C语言程序设计、计算思维、微积分、新生实践课、数据结构、程序设计综合课程设计、概率论与数理统计、离散数学、C++、大学物理、电路理论、人工智能导论、大数据分析、机器学习、算法设计与分析、计算机系统基础、计算机组成原理、逻辑与计算机系统设计、数据库系统原理、信息论基础、深度学习、计算机视觉、硬件综合训练、并行数据结构及算法、计算机通信与网络、操作系统、编译原理、计算机系统结构……

머신러닝Jupyter NotebookMITGitHub

gigapose

nv-nguyen

299스타

[CVPR 2024] PyTorch implementation of GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

models

NVIDIA-Merlin

305스타

Merlin Models is a collection of deep learning recommender system model reference implementations

머신러닝PythonApache-2.0GitHub

Transformers4Rec

NVIDIA-Merlin

1,284스타
Transformers4Rec preview

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

머신러닝PythonApache-2.0GitHub

cnmem

NVIDIA

299스타

A simple memory manager for CUDA designed to help Deep Learning frameworks manage memory

머신러닝C++BSD-3-ClauseGitHub
452스타

cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural networks. Also includes kernels for accelerated structure prediction.

DALI

NVIDIA

5,796스타

고도로 최적화된 데이터 처리 빌딩 블록과 실행 엔진을 제공하여 딥러닝 학습 및 추론 애플리케이션을 가속하는 GPU 가속 라이브러리입니다.

  • Easy-to-use functional style Python API.
  • Multiple data formats support - LMDB, RecordIO, TFRecord, COCO, JPEG, JPEG 2000, WAV, FLAC, OGG, H.264, VP9 and HEVC.
머신러닝C++Apache-2.0GitHub

DLSS

NVIDIA

1,675스타

NVIDIA DLSS는 새롭게 개선된 딥러닝 신경망으로, 게임의 프레임 레이트를 높이고 아름답고 선명한 이미지를 생성합니다.

3,452스타
physicsnemo preview

최첨단 Physics-ML 방법을 사용해 딥러닝 모델을 구축하고 학습 및 파인튜닝할 수 있는 오픈 소스 딥러닝 프레임워크

머신러닝PythonApache-2.0GitHub

tacotron2

NVIDIA

5,305스타
tacotron2 preview

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

머신러닝Jupyter NotebookBSD-3-ClauseGitHub
3,609스타

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

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

vid2vid

NVIDIA

8,699스타
vid2vid preview

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

warp

NVIDIA

7,323스타
warp preview

시뮬레이션, 로보틱스, 머신러닝을 GPU로 가속하는 Python 프레임워크입니다.

머신러닝PythonApache-2.0GitHub