Skip to content
Catégories de projets

Apprentissage automatique · GitHub

Explorez les outils pour entraîner, évaluer et exécuter des modèles, et comparez leur popularité.

Projets GitHub utiles

12,833 projets
1,399étoiles
neuromancer preview

Framework basé sur PyTorch pour résoudre des problèmes d’optimisation sous contraintes paramétriques, d’identification de systèmes guidée par la physique et de commande prédictive de modèles paramétriques.

  • Symbolic programming interface makes it very easy to define and embed physics equations, domain knowledge, and constraints into those learning paradigms.
  • Comprehensive Learning Tools: Access a wide array of tutorials and example applications—from basic system identification to advanced predictive control—making it easy for users to learn and apply NeuroMANCER to real-world problems.

elegy

poets-ai

470étoiles

A High Level API for Deep Learning in JAX

  • 😀 Easy-to-use: Elegy provides a Keras-like high-level API that makes it very easy to use for most common tasks.
  • 💪‍ Flexible: Elegy provides a Pytorch Lightning-like low-level API that offers maximum flexibility when needed.
2,006étoiles
PointTransformerV3 preview

[CVPR'24 Oral] Dépôt officiel de Point Transformer V3 (PTv3). Fournit également un paquet PyTorch + Triton installable avec pip, qui inclut les encodeurs préentraînés Sonata, Concerto et Utonia.

  • Oct 2026: PTv3 is now a pip package, point-transformer-v3, with optimizations from Pointcept2, our next codebase. It needs no spconv or FlashAttention (plain PyTorch with Triton kernels), runs 1.7-4.7x faster with 18-31% less memory on the GPU, also runs on the CPU, and loads the Sonata, Concerto and Utonia weights. See docs/acceleration.md.
  • Apr 2024: PTv3 is selected as one of the 90 Oral presentations of CVPR'24.