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

4,743 projets

ScanNet

ScanNet

2,365étoiles+2in 24h

ScanNet is an RGB-D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses, surface reconstructions, and instance-level semantic segmentations.

minimalRL

seungeunrho

3,271étoiles+2in 24h

Implémentations d’algorithmes de base d’apprentissage par renforcement en un minimum de lignes de code (basées sur PyTorch).

DeepCamera

SharpAI

3,141étoiles+2in 24h
DeepCamera preview

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.

Finance

shashankvemuri

4,376étoiles+2in 24h

Boîte à outils Python pour la finance quantitative : analyse d’actions, indicateurs techniques, backtesting de stratégies, optimisation de portefeuille et modélisation financière.

react-native-executorch

software-mansion

1,791étoiles+2in 24h
react-native-executorch preview

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

  • Native Hardware Acceleration: Optimized execution delegates across backends: XNNPACK (CPU), Core ML & MLX (Apple Silicon), and Vulkan (Android GPU).
  • 100% Offline & Private: Zero cloud inference costs and zero network dependency after model download. No user data ever leaves the device.

speechbrain

speechbrain

11,936étoiles+2in 24h

A PyTorch-based Speech Toolkit

  • Training Orchestration: The Brain class serves as a fully customizable tool for managing training and evaluation loops over data. It simplifies training loops while providing the flexibility to override any part of the process.
  • Hyperparameter Management: A YAML-based hyperparameter file specifies all hyperparameters, from individual numbers (e.g., learning rate) to complete objects (e.g., custom models). This elegant solution drastically simplifies the training script.
2,675étoiles+2in 24h
Restormer preview

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

FlashTopK

Tencent-Hunyuan

16étoiles+2in 24h
FlashTopK preview

Fast, exact fused top-k selection for learned sparse attention training and inference, from HyScale (Tencent Hy).

  • Fast: the fastest open-source implementation.
  • Robust: stays fast on trained and untrained indexers. Adaptive key pruning decides per call whether to skip keys by a score bound.

burn

tracel-ai

16,270étoiles+2in 24h
burn preview

Burn est une bibliothèque de tenseurs et un framework de deep learning de nouvelle génération qui ne fait aucun compromis sur la flexibilité, l’efficacité et la portabilité.

TradeMaster

TradeMaster-NTU

3,129étoiles+2in 24h
TradeMaster preview

TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:

Apprentissage automatiqueJupyter NotebookApache-2.0GitHub