Skip to content
프로젝트 카테고리

머신러닝 · GitHub

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

유용한 GitHub 프로젝트

12,809 프로젝트

EasyML

ICT-BDA

1,975스타
EasyML preview

Easy Machine Learning is a general-purpose dataflow-based system for easing the process of applying machine learning algorithms to real world tasks.

머신러닝JavaApache-2.0GitHub

DataScienceUtils

idanmoradarthas

37스타
DataScienceUtils preview

Data Science Utils: Frequently Used Methods for Data Science

  • income_category_Low - income_category_Medium - 1.0 - 0.1182165609358650 - 0.11821656093586504
  • term_ 36 months - term_ 60 months - 1.0 - 0.1182165609358650 - 0.11821656093586504
4,116스타
Fengshenbang-LM preview

Fengshenbang-LM(封신방 대규모 모델)은 IDEA 연구원의 인지 컴퓨팅 및 자연어 연구 센터가 주도하는 대규모 모델 오픈 소스 생태계로, 중국어 AIGC와 인지 지능의 기반이 되었습니다.

머신러닝PythonApache-2.0GitHub

detrex

IDEA-Research

2,314스타
detrex preview

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

머신러닝PythonApache-2.0GitHub

DINO

IDEA-Research

2,863스타
DINO preview

[ICLR 2023] "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection" 논문의 공식 구현

머신러닝PythonApache-2.0GitHub

HumanSD

IDEA-Research

304스타
HumanSD preview

[ICCV 2023] The official implementation of paper "HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation"

머신러닝PythonApache-2.0GitHub

voxwright

ideapacket

31스타

Offline voice-agent application layer: session core with byte-deterministic replay, spoken-LLM adapters (scripted/replay/loopback-mock), injection-safe function-call grammar, slot grounding, workflow engine with compensation and resume, permissioned tool sandbox, repair-dialog policies, task-success and latency evaluation. NumPy core, torch extra.

bob

idiap

262스타

Bob is a free signal-processing and machine learning toolbox originally developed by the Biometrics group at Idiap Research Institute, in Switzerland.

RustiFlow

idlab-discover

28스타
RustiFlow preview

Flow feature extraction tool built in Rust using eBPF

  • High Throughput: Utilizes Rust and the Aya library for eBPF program compilation and execution, ensuring exceptional performance and resource efficiency.
  • Versatile Feature Sets: Offers a variety of pre-defined feature sets (flows) and the flexibility to create custom feature sets tailored to specific requirements. An example of the custom flow is shown here.

idrlnet

idrl-lab

253스타

IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural Network (PINN) systematically.

머신러닝PythonApache-2.0GitHub
226스타

The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"

sacred

IDSIA

4,380스타

Sacred는 IDSIA에서 개발한 실험을 구성하고, 정리하고, 기록하고, 재현할 수 있도록 돕는 도구입니다.