How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
LibrePhotos is a self-hosted photo management system designed for organizing, tagging, and searching photos and videos stored on personal servers. It functions as an AI-powered media organizer and a multi-user media server, providing isolated accounts and secure permissions so multiple people can manage private collections on a single system. The project differentiates itself through a semantic image search engine that allows for natural language queries based on deep metadata analysis. It incorporates computer vision to automatically detect faces and identify objects, while utilizing geospat
Lightly is a self-supervised learning framework and computer vision data curation tool designed to manage large image datasets and train models on unlabeled data. It functions as a PyTorch vision library and dataset management SDK, providing tools to convert raw images into high-dimensional vectors for similarity search, visualization, and feature extraction. The project implements a variety of self-supervised architectures, including MoCo, SimCLR, VICReg, Barlow Twins, and masked image modeling. It distinguishes itself by combining these learning frameworks with active learning capabilities,
FiftyOne is a visual tool for curating, analyzing, and managing image and video datasets for machine learning model training. It serves as a platform for identifying annotation errors, refining ground truth labels, and evaluating vision model performance by comparing predictions against ground truth to identify failure modes. The system functions as a containerized data platform that supports team collaboration on large-scale visual datasets in a cloud environment. It includes specialized capabilities for exploring high-dimensional embeddings to discover data clusters and retrieve correspondi
imagededup is a Python library used for finding exact and near-duplicate images. It provides utilities for generating image fingerprints, computing neural embeddings, and evaluating the precision of deduplication processes.
The main features of idealo/imagededup are: Perceptual Visual Fingerprinting, Image Encoder Embedding Extractions, High-Dimensional Text Embeddings, Perceptual Image Deduplication, Exact Image Deduplications, Image Duplicate Detection, Image Encoding Generation, Vector Distance Metrics.
Open-source alternatives to idealo/imagededup include: librephotos/librephotos — LibrePhotos is a self-hosted photo management system designed for organizing, tagging, and searching photos and videos… lightly-ai/lightly — Lightly is a self-supervised learning framework and computer vision data curation tool designed to manage large image… voxel51/fiftyone — FiftyOne is a visual tool for curating, analyzing, and managing image and video datasets for machine learning model… kornia/kornia — Kornia is a differentiable computer vision library and cross-framework tensor vision toolset. It implements vision… johannesbuchner/imagehash — ImageHash. obss/sahi — SAHI is a sliced inference framework and computer vision pipeline designed to detect small objects in high-resolution…
