Skip to content
Projektkategorien

Maschinelles Lernen · GitHub

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

Nützliche GitHub-Projekte

4,743 Projekte
1,999Sterne+2in 24h
PointTransformerV3 preview

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3). Also a pip-installable PyTorch + Triton package with pretrained Sonata, Concerto, and Utonia encoders.

  • 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.

audio

pytorch

2,965Sterne+2in 24h

Data manipulation and transformation for audio signal processing, powered by PyTorch

Maschinelles LernenPythonBSD-2-ClauseGitHub

examples

pytorch

24,090Sterne+2in 24h

Eine Sammlung von PyTorch-Beispielen für Computer Vision, Textverarbeitung, Reinforcement Learning und mehr.

Maschinelles LernenPythonBSD-3-ClauseGitHub

ignite

pytorch

4,802Sterne+2in 24h
ignite preview

High-Level-Bibliothek zum flexiblen und transparenten Trainieren und Evaluieren neuronaler Netze in PyTorch.

  • Less code than pure PyTorch while ensuring maximum control and simplicity
  • Library approach and no program's control inversion - Use ignite where and when you need
Maschinelles LernenPythonBSD-3-ClauseGitHub

aimet

qualcomm

2,747Sterne+2in 24h
aimet preview

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

nanodet

RangiLyu

6,279Sterne+2in 24h
nanodet preview

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

APKiD

rednaga

2,615Sterne+2in 24h
APKiD preview

Android Application Identifier for Packers, Protectors, Obfuscators and Oddities - PEiD for Android

rllm

rllm-org

5,916Sterne+2in 24h

Democratizing Reinforcement Learning for LLMs

  • Any harness. 10+ CLI harnesses (Claude Code, Codex, Terminus-2, mini-swe-agent, opencode, ...) plus Harbor-compatible task dirs. Or wrap your own agent — LangGraph, OpenAI Agents SDK, openai.OpenAI — with @rllm.rollout.
  • Any sandbox. Docker, Daytona, Modal, or local — with snapshot + warm-pool acceleration to keep rollouts cheap at training-scale.
16Sterne+2in 24h
SuperMimic-Agent-WFArm preview

探索类开源:SuperMimic与MimicAgent联动用于四轮足机械臂的统一协同控制与分层控制的训练方案。欢迎交流与共同探索。

root

root-project

3,344Sterne+2in 24h
root preview

The official repository for ROOT: analyzing, storing and visualizing big data, scientifically