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

12,805 projets

dynolog

facebookincubator

389étoiles+1in 24h

Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

474étoiles+1in 24h
FaceRecognition-Android preview

Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks

  • Recognition only — Enroll / Identify / Attribute
  • Liveness only — Capture

FlagGems

flagos-ai

1,184étoiles+1in 24h
FlagGems preview

FlagGems is an operator library for large language models implemented in the Triton Language.

  • A large collection of PyTorch compatible operators
  • Hand-optimized performance for selective operators

flexmeasures

FlexMeasures

217étoiles+1in 24h
flexmeasures preview

FlexMeasures is an enterprise-ready & customizable energy optimization engine, for scheduling and forecasting for flexible assets in real-time operations.

  • FlexMeasures has well-documented API endpoints and CLI commands to interact with its model and data
  • You can extend it easily with your own logic by writing plugins

vui

fluxions-ai

782étoiles+1in 24h

Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

  • Vui Nano (219M active, 305M total) — a small, context-aware TTS model trained on real conversations: Llama-style decoder + RQ-Transformer head over the Qwen3-TTS-12Hz codec, Apache 2.0
  • Conversation-conditioned generation — replies are decoded from a KV cache holding the whole dialogue, including the audio of your turn, so prosody carries across turns (~6-minute context)

CADFit

ghadinehme

101étoiles+1in 24h
CADFit preview

Official code repository of "CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization" @ ICML 2026

  • Rich operator set. Extrude, Revolve, Fillet, Chamfer, Union, Cut — far beyond sketch-and-extrude pipelines.
  • IoU-driven optimization, kernel-validated. Every candidate is built through CadQuery; the optimizer maximizes the same volumetric IoU it reports. Invalid Ratio = 0 on every benchmark slice.