Awesome GitHub RepositoriesComputer Vision Frameworks

Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and

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

Detectron2 is a PyTorch computer vision framework and visual recognition platform designed for training and deploying models for object detection, image segmentation, and visual recognition. It provides a research-oriented environment for training complex vision models with multi-GPU acceleration. The project includes a specialized object detection library for identifying and locating multiple objects via bounding boxes, as well as an image segmentation toolkit for creating pixel-level masks through instance, semantic, and panoptic segmentation. Additionally, it features a human pose estimati

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

Kornia is a differentiable computer vision library and cross-framework tensor vision toolset. It implements vision operations as differentiable tensors to enable integration into deep learning pipelines and supports the transpilation of operations across PyTorch, TensorFlow, JAX, and NumPy. The project provides specialized toolsets for geometric vision and stereo depth, including algorithms for 3D scene reconstruction, camera calibration, and pose estimation. It further distinguishes itself as a differentiable image augmentation framework, applying random geometric and color transformations w

LAVIS is a multimodal large language model framework and vision-language model library. It provides tools for training and evaluating models that integrate visual, textual, and audio data, serving as a cross-modal feature extractor and a zero-shot visual reasoning engine. The framework distinguishes itself by using frozen-backbone integration, where pretrained encoders remain non-trainable while lightweight adapter layers are updated. It employs cross-modal feature alignment to map different representations into a shared embedding space and utilizes a modular model wrapper to swap vision and

This project is a deep learning style transfer framework designed to apply artistic styles to photographs. It functions as a photorealistic image stylizer that merges the content of one image with the visual characteristics of another while maintaining the original geometry and structural details. The system distinguishes itself through the use of matting Laplacian matrices and semantic segmentation masks to prevent distortion and preserve edge fidelity. These capabilities allow for region-specific styling, where different aesthetics can be applied to distinct objects or areas within a single

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

mmcv is a foundation library for computer vision based on PyTorch. It provides a comprehensive system for constructing convolutional neural networks, a toolkit for image and video preprocessing, and a collection of high-performance deep learning vision operators. The project is distinguished by its hardware-accelerated kernels for complex operations such as deformable convolutions and region pooling. It features a configuration-driven framework that allows for the dynamic instantiation of network layers and the registration of custom modules without modifying code. The library covers a broad

Super-Gradients ist ein PyTorch-Computer-Vision-Framework und eine Trainingsbibliothek, die für den gesamten Lebenszyklus von Vision-Modellen konzipiert ist. Es fungiert als Optimierer für Deep-Learning-Modelle und als Deployment-Toolkit für das Training und die Feinabstimmung von Modellen in den Bereichen Bildklassifizierung, Objekterkennung, semantische Segmentierung und Pose-Estimation. Das Projekt bietet spezifische Tools zur Modelloptimierung, einschließlich Teacher-Student-Knowledge-Distillation und numerischer Präzisionskomprimierung, um Speicher- und Rechenanforderungen zu reduzieren. Es enthält zudem die Implementierung der Yolo-NAS-Architektur für leistungsstarke Objekterkennung. Das Framework deckt eine breite Palette an Funktionen ab, einschließlich verteiltem GPU-Training, modularen Vision-Pipelines und der Automatisierung von Trainingsläufen über strukturierte Rezept-Konfigurationen. Es verwaltet zudem das Laden von Daten, Bild-Augmentierung und den Export trainierter Gewichte in universelle Formate für Produktions-Hardware-Beschleuniger.

Deformable-ConvNets ist ein Computer-Vision-Framework und eine Sammlung von neuronalen Netzwerkkomponenten zur Implementierung von deformierbaren faltenden neuronalen Netzen (CNNs). Es bietet adaptive Convolutional-Layer und Pooling-Implementierungen, die ihre rezeptiven Felder basierend auf Eingabemerkmalen anpassen, um die Geometrie von Objekten in Bildern präziser zu erfassen. Das Projekt ermöglicht den Einsatz von lernbaren Sampling-Offsets und Modulationsmasken, um Convolutional-Grids an die Formen von Zielobjekten auszurichten. Es enthält spezialisierte Tools zur Visualisierung der gelernten Offsets in Convolution- und Pooling-Layern, wodurch analysiert werden kann, wie das Netzwerk sein räumliches rezeptives Feld anpasst. Diese Funktionen werden eingesetzt, um die Genauigkeit der Objekterkennung zu verbessern und die semantische Segmentierung zu verfeinern. Das Framework unterstützt die Extraktion von Merkmalen aus Regionen von Interesse (RoI) durch Deformable Pooling, um Sampling-Bereiche an tatsächliche Objektgrenzen anzupassen. Die Implementierung umfasst eine Trainings-Pipeline zur Ausführung und Evaluierung dieser spezialisierten Netzwerkarchitekturen.

SegFormer is a semantic segmentation framework and transformer-based model designed for pixel-level image classification. It provides a deep learning architecture that assigns class labels to pixels using a hierarchical transformer encoder and a multi-layer perceptron decoder. The framework utilizes a hierarchical transformer encoder to process multi-scale features through a pyramid of blocks and an all-MLP decoder to aggregate these features without complex attention mechanisms. It incorporates overlap patch embedding to preserve local continuity and sequential self-attention reduction to ma

VideoSys: An easy and efficient system for video generation

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Automatic 2D-to-3D Video Conversion with CNNs

Industry-strength Computer Vision workflows with Keras

Microsoft AI for Good Lab — Biodiversity research hub. Open-source AI models, edge devices, and tools for biodiversity monitoring and conservation. Your source for MegaDetector, SPARROW, PytorchWildlife, Bioacoustics, and more.

Python Package for Airborne RGB machine learning

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches