Aprendizaje automático · GitHub

Deep probabilistic analysis of single-cell and spatial omics data

RetinaFace: Deep Face Detection Library for Python

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.

Silero Models: pre-trained text-to-speech models made embarrassingly simple

TabICLv2: An open tabular foundation model

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.

Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

Resuelve rompecabezas. Mejora tus conocimientos de PyTorch.

StarDist - Object Detection with Star-convex Shapes

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

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.

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

MCP server for Lacuna, a research map for machine learning: search directions, papers, authors, venues, and AI-generated research proposals.

Burn es una biblioteca de tensores y un marco de aprendizaje profundo de nueva generación que no renuncia a la flexibilidad, la eficiencia ni la portabilidad.

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

Welcome to the Physics-based Deep Learning Book v0.3 - the GenAI Edition

Una biblioteca de Python fácil de usar para la predicción y la detección de anomalías en series temporales.

• Forecasting Models: A large collection of forecasting models for regression as well as classification tasks; from statistical models (such as ARIMA) to deep learning models (such as N-BEATS). See the forecasting models below.
• Multivariate Support: TimeSeries can be multivariate - i.e., contain multiple time-varying dimensions/columns instead of a single scalar value. Many models can consume and produce multivariate series.