Skip to content
Projektkategorien

Maschinelles Lernen · GitHub

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

Nützliche GitHub-Projekte

12,804 Projekte

DeepH-dock

kYangLi

43Sterne

DeepH-dock seamlessly integrates deep learning with first-principles calculations. It serves as a modular and extensible bridge, functioning both as the dedicated interface for the DeepH-pack suite and as a standalone tool for coupling deep learning models with computational materials science workflows.

  • Multi-Software Compatibility: Seamlessly bridges major DFT packages (e.g., SIESTA, QE, OpenMX, FHI-aims, ABACUS) with the DeepH deep learning family and downstream tight-binding toolchains.
  • High-Performance Computational Core: Implements high-performance algorithms for automated structure generation, overlap matrix calculation, Hamiltonian symmetrization, and fast diagonalization via KPM/Lanczos.
28Sterne

The documentation of DeepH-pack, the latest iteration of DeepH, unites all the preceding DeepH methodologies into a cohesive package. This advanced version has been meticulously rewritten with JAX, enhancing its efficiency and capabilities.

473Sterne
MultiModalMamba preview

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

Sophia

kyegomez

384Sterne

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Rapid_Seg

l1997i

53Sterne

🔥(ECCV 2024 Oral) RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation

  • 4D Distance Computation: combines geometric and reflectivity components for a comprehensive feature representation.
  • Rigid-Transform Invariance: distances within rigid bodies are preserved under rotation/translation, so RAPiD is robust to viewpoint changes.