Robótica y Edge AI
mediapipe
google-ai-edge/mediapipe
On-device ML libraries, models, and tools for vision, text, and audio across supported platforms.
★ 36,9K⑂ 6,2KC++
ToolAI.io · Canal de GitHub
Proyectos de IA en tendencia en GitHub
Sigue repositorios de AI de código abierto activos en los ámbitos de LLM, agentes, MCP, RAG y programación, con su número de estrellas y datos de proyectos verificados.
Datos del repositorio público
Índice del proyecto
Visión por computadora
ultralytics
ultralytics/ultralytics
Training and inference tools for object detection, segmentation and pose estimation models.
★ 61,3K⑂ 11,7KPython
Visión por computadora
opencv
opencv/opencv
An open-source library for image processing, video analysis and computer vision.
★ 90,7K⑂ 57KC++
Visión por computadora
supervision
roboflow/supervision
Reusable utilities for computer vision data handling, detection annotation and tracking workflows.
★ 49,9K⑂ 4,8KPython
Visión por computadora
photoprism
photoprism/photoprism
A self-hostable photo and video library with automatic labels, face organization, and metadata search.
★ 40,2K⑂ 2,3KGo
Ajuste fino, entrenamiento y datos
LlamaFactory
hiyouga/LlamaFactory
A unified fine-tuning toolkit for large language and vision-language models.
★ 74,6K⑂ 9,1KPython
Visión por computadora
tesseract
tesseract-ocr/tesseract
An open-source OCR engine for converting text in images into machine-readable text.
★ 76,3K⑂ 10,8KC++
Visión por computadora
yolov5
ultralytics/yolov5
A PyTorch-based object detection project with training, inference and export workflows.
★ 58K⑂ 17,5KPython
Visión por computadora
Deep-Live-Cam
hacksider/Deep-Live-Cam
A computer vision tool for real-time face replacement and video processing.
★ 96,5K⑂ 14,1KPython
Visión por computadora
faceswap
deepfakes/faceswap
An open-source toolkit for face processing, model training and video conversion.
★ 57,5K⑂ 13,5KPython
Inferencia, implementación y tiempo de ejecución
Hugging Face Transformers
huggingface/transformers
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal domains, supporting both inference and training.
★ 163,3K⑂ 34,1KPython
AI multimodal
Destacados
whisper — Speech recognition and transcription
openai/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
★ 107,7K⑂ 13,1KPython
Página 1 / 3 · 28 proyectos