Skip to content
프로젝트 카테고리

머신러닝 · GitHub

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

유용한 GitHub 프로젝트

12,806 프로젝트

cleverhans

cleverhans-lab

6,459스타

공격을 구성하고 방어를 구축하며 둘 모두를 벤치마킹하기 위한 적대적 예제 라이브러리.

머신러닝Jupyter NotebookMITGitHub
134스타
ClimaAtmos.jl preview

GPU-capable global atmosphere model of the CliMA Earth System Model, designed for calibration with data assimilation and machine learning

  • Global and single-column configurations: cubed-sphere grids with topography for global simulations; boxes, planes, and columns for process studies (BOMEX, DYCOMS, RICO, and other standard cases)
  • Turbulence and convection: TKE-based eddy diffusion and the PROPHET scheme (an extended, prognostic eddy-diffusivity mass-flux (EDMF) scheme), designed for calibration with data assimilation and machine learning
머신러닝JuliaApache-2.0GitHub
74스타

Modular, GPU-capable land surface model of the CliMA Earth System Model, designed for data-driven parameterizations

머신러닝JuliaApache-2.0GitHub
37스타

Centralized parameter and physical-constant management for the CliMA Earth system modeling ecosystem

  • Centralized management: one authoritative file of constants and parameters for the whole ecosystem, so shared values cannot drift between components.
  • Typed retrieval: each parameter declares its type, and values are converted to Float32/Float64, Int, String, Bool, or DateTime on read, with a float type chosen per simulation.
머신러닝JuliaApache-2.0GitHub
131스타
EnsembleKalmanProcesses.jl preview

Derivative-free parameter calibration and uncertainty quantification for expensive models using ensemble Kalman methods

  • Derivative-free: no gradients of the forward model G are required — you only need to run it at different parameter values.
  • Language-agnostic: G does not need to be written in Julia.
머신러닝JuliaApache-2.0GitHub

ClimateVision

Climate-Vision

378스타

Open-source ML platform for detecting deforestation, ice melt, and flooding from Sentinel-2 / Landsat imagery.

machineJS

ClimbsRocks

401스타

[UNMAINTAINED] Automated machine learning- just give it a data file! Check out the production-ready version of this project at ClimbsRocks/auto_ml

Fabrik

Cloud-CV

1,132스타
Fabrik preview

:factory: Collaboratively build, visualize, and design neural nets in browser

머신러닝PythonGPL-3.0GitHub

PyAGC

Cloudy1225

33스타
PyAGC preview

[NeurIPS 2026] Attributed Graph Clustering Library for PyTorch

  • 📊 Diverse Dataset Collection — 12 graphs from 2.7K to 111M nodes across Citation, Social, E-commerce, and Web domains, featuring both textual and tabular attributes with varying homophily levels.
  • 🧩 Unified Algorithm Framework — 20+ SOTA methods organized under the Encode-Cluster-Optimize taxonomy with modular, interchangeable encoders, cluster heads, and optimization strategies.