Vision payloads and vision-domain operators for ml-pipes
Semi-supervised pose estimation using pytorch lightning
Tools for training neural networks on the CIFAR-10 task with PyTorch and TensorFlow
Modular industrial machine vision environment with an ordered workflow engine and web HMI
Enhanced Transformers library with Omega3 model support - State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Tools of CV(Computer Vision)
A computer vision pipeline for the semantic exploration of maps/images at scale
High-performance dataloader for robot learning datasets. LeRobot format support, hardware-accelerated video decode via VideoToolbox, MLX array output. Zero-copy data pipeline optimized for Apple Silicon and edge robotics.
A tool to extract bird images from videos and train custom species classifiers
Easy Significance Testing for Deep Neural Networks.
Object-oriented machine vision for Python.
Software Development Kit for the Geti™ platform
Agnostic Computer Vision Framework
Training utility library and config manager for Granular Machine Vision research
Image and data files for the Machine Vision Toolbox for Python
Automation of the creation of the architecture of the neural network based on the input
Fast 6DoF Face Alignment and Tracking
Deploy inference models served for Artificial Intelligence solutions including but not limited to Pixano.
Comprehensive AI/ML library integrating machine learning, computer vision, audio processing, and conversational AI
Composable neural network composennents for building models in PyTorch.
AI Adversarial Security Testing for LLM, RAG, Agent, and Vision Models
A modular Explainable AI framework for ML, Deep Learning, and Computer Vision
LLM-based image categorization tool with focus on book cover detection
Semantic image compression for AI training datasets
HuggingFace utilities for Ultralytics/YOLOv8.
CPU image-augmentation pipelines compiled from Python and executed by optimized Rust kernels
Ultralytics YOLO 🚀 for SOTA object detection, instance segmentation, semantic segmentation, depth estimation, classification, pose estimation, oriented object detection, and multi-object tracking.
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
A Python toolbox for easy interaction with various LLMs and Vision models
Self-hostable OpenAI-compatible multi-modality AI server: 23 modalities (chat, image, audio, video, 3D, embeddings, OCR, vectorization), plugin runtimes (PyTorch, diffusers, llama-cpp-python).
Training utility library and config manager for Granular Machine Vision research
Packaged version of the Strongsort repository
A no-code machine learning studio: train, evaluate, explain and export tabular, NLP and image models from your browser.
Packaged version of the ByteTrack repository
GMM-MIGT and MIGT: Mutual Information Guided Training (with Gaussian Mixture Model preprocessing) for representative train/test/validation partitioning of image datasets
ZeroModels: Open-source Keras 3 collection of pretrained models
STMATH: A Zero-Wrapper Unified Mathematical and AI Framework built from First Principles
Annotation Tool for Computer Vision Datasets
Python SDK for AADML Training: call your trained photo and chat models from your own code.
Support for book: Robotics, Vision & Control 3 in Python
Pure-Python implementation of the GigE Vision protocol (GVCP + GVSP).
Make Computers See with SimpleCV, the Python Framework for Machine Vision
Report training runs, epochs, test results, benchmarks and prediction frames to Visin, and read them back.
Comprehensive CLI tool and VS Code extension for vision models, AutoML, and local LLMs
Video streaming inference framework, integrating image algorithms and models for real-time/offline video structuring
Unified AI/ML package providing a consistent API for accessing 205 models and tasks from scikit-learn, PyTorch, TensorFlow, and other popular libraries.
Packaged version of the Yolov7 repository
Deterministic camera sensor and ISP simulation with image-quality metrics.