Skip to content
Projektkategorien

Maschinelles Lernen · GitHub

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

Nützliche GitHub-Projekte

4,866 Projekte

DLSS

NVIDIA

1,664Sterne

NVIDIA DLSS ist ein neues und verbessertes neuronales Deep-Learning-Netzwerk, das die Bildrate erhöht und schöne, scharfe Bilder für deine Spiele erzeugt.

ttf-ternary

oguzeldereli

43Sterne

Two-timescale threshold flips (TTF): training and converting ternary {-1,0,1} LLMs without full-precision master weights. ~1 byte of optimizer state per weight; 23B trains on a 16 GB GPU, Qwen3.8-27B converted and recovered on one 24 GB card.

datumaro

open-edge-platform

700Sterne

Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.

  • CIFAR-10/100 (classification)
  • COCO (image_info, instances, person_keypoints, captions, labels, panoptic, stuff)

kliff

openkim

41Sterne

KIM-based Learning-Integrated Fitting Framework for interatomic potentials.

  • Interacting seamlessly with KIM, the fitted model can be readily used in simulation codes such as LAMMPS and ASE via the KIM API
  • Creating mixed PM and NN models
121Sterne

The Harmonic Algorithm by Oscar South - A Project Spanning Music Analysis, Functional Programming & Machine Learning. Check out the website below for docs, demonstrations and articles, Please leave a star on the repo above if you think this thing looks cool :)

outerloop

outerloop-science

43Sterne

Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

PaddleMaterials

PaddlePaddle

130Sterne
PaddleMaterials preview

An End-to-End Deep Learning Toolkit for Materials Science

  • Property Prediction (PP) - Predict material properties from structure - Forward design or predict formation energy, band gap, elastic moduli etc.
  • Structure Generation (SG) - Generate novel crystal structures - Inverse design or structure generation

DLpisoFoam

pauloacs

26Sterne
DLpisoFoam preview

Machine Learning enhanced CFD solvers: isothermal & thermal fluid flow

  • 🚀 Accelerated simulations: Up to 40% less iterations required to convergence when compared to standard OpenFOAM solvers
  • 🧠 ML-powered: Machine Learning surrogate models enhance pressure Poisson solver