Projects sharing features with Lightly Train

Industry-strength Computer Vision workflows with Keras

Supervision is a computer vision toolset for normalizing model outputs, managing datasets, and visualizing annotations. It provides a framework to convert predictions from various classification and detection models into a standardized data format to ensure interoperability across different computer vision pipelines. The library features a post-processor for filtering, counting, and tracking detected objects across image frames and video streams. It includes capabilities for large image tiling to improve the detection of small objects and tools for assigning persistent identities to objects t

CLIP is a neural network architecture designed to map visual and textual data into a shared latent vector space. By utilizing transformer-based feature extraction and multi-modal tokenization, the system aligns images and natural language strings, enabling cross-modal similarity analysis and semantic classification. The project functions as a zero-shot classification engine, identifying image content by calculating the cosine similarity between visual features and arbitrary text labels without requiring task-specific retraining. Beyond inference, it serves as a research toolkit for evaluating

Deformable-ConvNets is a computer vision framework and a collection of neural network components designed to implement deformable convolutional neural networks. It provides adaptive convolutional layers and pooling implementations that modify their receptive fields based on input features to better capture the geometry of objects within images. The project enables the use of learnable sampling offsets and modulation masks to align convolutional grids with target object shapes. It includes specialized tools for visualizing learned offsets in convolutions and pooling layers, allowing for the an

Albumentations is an image augmentation library and computer vision preprocessing tool designed to expand datasets for deep learning models. It provides a collection of transformations that modify pixel values and spatial geometry to increase the diversity of training samples and improve model generalization. The library supports both 2D image augmentation and 3D volumetric data augmentation. It handles a variety of labels alongside images, ensuring that bounding boxes, keypoints, and segmentation masks remain accurately aligned when spatial transformations are applied. The tool incorporates

Build fully-functioning computer vision models with PyTorch

DeepLake is AI data infrastructure consisting of a multimodal data lake, a hybrid search engine, and a serverless vector database. It provides a PostgreSQL-based AI data runtime that combines multimodal storage with streaming pipelines to load and shuffle datasets from cloud storage directly into deep learning training pipelines. The system utilizes lazy indexing to store and slice images, audio, and video without loading entire files into memory. It enables retrieval-augmented generation by persisting high-dimensional embeddings in a serverless vector store and implementing hybrid search tha

An all-in-one toolkit for computer vision

3D Computer Vision Framework

Meshroom is a node-based photogrammetry software designed to transform collections of two-dimensional images into three-dimensional models and scene geometry. It provides a visual interface for constructing and managing modular data pipelines, allowing users to automate complex computer vision tasks such as feature extraction, depth map estimation, and mesh generation. The software distinguishes itself through a distributed computational framework that dispatches resource-intensive tasks across local hardware or remote render farms. By utilizing a directed acyclic graph execution model, it en

FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) Dataset

Darknet is a high-performance C-based inference engine and computer vision library designed for real-time object identification and localization. It serves as a neural network framework for training and deploying detection models using the YOLO architecture, providing a toolset for deep learning training and deployment. The project differentiates itself through a C and CUDA implementation that enables hardware acceleration for matrix multiplication and inference speed optimization. It provides a shared library interface for embedding detection capabilities into external applications and suppo

A collection of computer vision pre-trained models.

Image composition toolbox: everything you want to know about image composition/compositing or object/subject insertion/addition/compositing.

Fast Neural Style for Image Style Transform by Pytorch

Pixel-wise segmentation on the VOC2012dataset dataset using pytorchpytorch.

DroneAid uses machine learning to detect calls for help on the ground placed by those in need. At the heart of DroneAid is a Symbol Language that is used to train a visual recognition model. That model analyzes video from a drone to detect and count specific images. A dashboard can be used to…

Catalyst.Detection

Catalyst.Segmentation

An open-source application for biological image analysis

A computer vision closed-loop learning platform where code can be run interactively online. 学习闭环《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...） 📘 在线电子书 https://charmve.github.io/computer-vision-in-action/ 👇项目主页

DroneNet is Joseph Redmon's YOLO real-time object detection system retrained on 2664 images of DJI drones, labeled. The original and labeled images used for retraining can be found under the image and label folders respectively.

Official Pytorch implementation of CutMix regularizer

OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot landmarks. It functions as a multi-person motion tracker, identifying the spatial coordinates of multiple individuals simultaneously within video streams or static images. Beyond two-dimensional detection, the software acts as a three-dimensional kinematics processor, reconstructing spatial movement data from single or multiple synchronized camera perspectives. The system distinguishes itself through a bottom-up approach that utilizes part-affinity fields to associate body parts across