Awesome GitHub RepositoriesAugmentation Pipelines

Albumentations is a computer vision image augmentation library designed to increase training data diversity for deep learning models. It provides a toolset for applying geometric and color transformations to images and annotations, including a specialized collection of 3D operations for volumetric data used in medical and scientific imaging. The library functions as an image mask and bounding box transformer, automatically updating masks, bounding boxes, and keypoints when images undergo geometric changes. This ensures that spatial alterations remain synchronized across images and their assoc

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

This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model that trains visual representations using a momentum teacher and self-distillation without the need for labeled data. The library functions as an image feature extractor and visual attention visualizer, allowing for the generation of high-dimensional vectors and the rendering of self-attention maps as heatmaps or videos to analyze model focus. It provides comprehensive tools for downstream vision evaluation, including linear probe classification, k-nearest neighbor categorizatio

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

This is a PyTorch-based training pipeline designed for reproducible image classification benchmarking on the CIFAR-10 dataset. It integrates GPU-accelerated computation, data augmentation, learning rate scheduling, and checkpointing to produce consistent accuracy measurements across multiple ResNet architectures. The project distinguishes itself by providing a fixed-architecture benchmark suite that trains a predefined set of ResNet variants, from ResNet18 through ResNet152, on CIFAR-10. It implements a step-based learning rate decay schedule at predetermined epochs to stabilize convergence,

nlpaug es una librería de aumento de datos diseñada para generar texto sintético, audio y datos de espectrogramas con el fin de mejorar la robustez de los modelos de machine learning. Funciona como un sintetizador de datos textuales y un aumentador de señales de audio, proporcionando herramientas especializadas para expandir datasets mediante diversos métodos de transformación. El proyecto se distingue por su capacidad para orquestar flujos de trabajo complejos mediante un orquestador de pipelines, que permite encadenar múltiples funciones de aumento de forma secuencial o aleatoria. Soporta síntesis de texto sofisticada mediante back-translation, embeddings de palabras contextuales e integración de modelos de lenguaje pre-entrenados, además de ofrecer aumento de imágenes de espectrogramas mediante enmascaramiento de tiempo y frecuencia. La librería cubre un amplio rango de capacidades, incluyendo modificación de señales de audio con inyección de ruido y pitch shifting, alteraciones de texto basadas en reglas para simular errores tipográficos y ortográficos, y expansión de datasets mediante generación de oraciones y sustitución semántica. También proporciona controles para el volumen de aumento y filtrado de objetivos mediante expresiones regulares para proteger tokens específicos de la modificación.

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,

face.evoLVe is a deep learning library designed for the training and deployment of facial recognition models. It provides a comprehensive framework for converting facial images into numerical feature vectors, enabling identity verification and similarity analysis across large-scale datasets. The project facilitates the entire lifecycle of facial analysis, from dataset preparation and image standardization to distributed model training. It includes utilities for detecting facial landmarks and applying geometric transformations to ensure consistent input orientation, as well as data augmentatio

This is a structured deep learning curriculum for programmers, delivered as a collection of Jupyter notebooks. It teaches the fundamentals of training neural networks for computer vision, natural language processing, tabular data analysis, and collaborative filtering using PyTorch and the fastai library. The course is designed to be hands-on, guiding learners from building a training loop from scratch to fine-tuning pretrained models for a variety of practical tasks. The curriculum distinguishes itself by covering the full lifecycle of a deep learning project, from data preparation and augmen