Awesome GitHub RepositoriesCustom Dataset Loading

This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

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

Snorkel is a weak supervision system that enables users to programmatically generate training labels for machine learning models without manual annotation. At its core, it provides a framework for writing labeling functions as Python callables that each vote on data points, and then trains a probabilistic graphical model over these multiple weak supervision sources to estimate latent true labels without any ground truth data. The system automatically learns accuracy and correlation parameters between labeling functions by analyzing observed agreement patterns on unlabeled data, converting lab

GDAL es una biblioteca traductora de código abierto con licencia MIT que proporciona un modelo de datos abstracto unificado para leer y escribir datos geoespaciales ráster y vectoriales en cientos de formatos de archivo. Sirve como una biblioteca fundamental de traducción de datos geoespaciales, permitiendo el acceso a diversos formatos de datos geoespaciales a través de una interfaz única y consistente. La biblioteca expone su funcionalidad principal a través de utilidades de línea de comandos que permiten a los usuarios traducir, convertir y procesar datos geoespaciales entre formatos. Un motor de transformación de coordenadas maneja las conversiones entre sistemas de referencia espacial, mientras que un sistema de plugins de controladores de formato carga la lógica de lectura y escritura específica del formato en tiempo de ejecución. La capa del sistema de archivos virtual proporciona acceso de E/S uniforme a través de archivos locales, HTTP, almacenamiento en la nube y archivos comprimidos, y un caché de bloques ráster gestiona el almacenamiento en caché de mosaicos en memoria para reducir las operaciones de E/S. GDAL admite la lectura y escritura de datos geoespaciales tanto ráster como vectoriales, con iteración de características vectoriales que transmite características individualmente sin cargar conjuntos de datos completos en la memoria. El proyecto permite la interoperabilidad geoespacial entre formatos al admitir el intercambio de datos entre diferentes ecosistemas de software geoespacial a través de su amplio soporte de formatos.

Anomalib is a PyTorch-based library for visual anomaly detection, offering a modular framework, a comprehensive model zoo, and a benchmarking suite designed for industrial defect detection. It provides a wide range of algorithms—including generative, discriminative, teacher-student, and vision-language approaches—that support unsupervised, few-shot, and zero-shot settings. The library enables deployment through model export to ONNX and OpenVINO for edge devices, and includes a no-code web application for training and inference. It also features a command-line interface for orchestrating multi

TorchGeo is a PyTorch library designed for deep learning on geospatial data, providing a framework for building and training neural networks for tasks such as semantic segmentation, object detection, and change detection. It serves as a comprehensive pipeline for remote sensing, featuring specialized dataset loaders and multispectral image preprocessing tools. The library is distinguished by a dedicated remote sensing model zoo and extensive support for transfer learning, allowing users to integrate pre-trained weights optimized for specific satellite sensors. It also includes support for sel

PyTorchZeroToAll es un recurso educativo y colección de tutoriales centrados en el deep learning y el framework PyTorch. Proporciona una ruta de aprendizaje estructurada para implementar arquitecturas de redes neuronales, desde la sintaxis básica del lenguaje y fundamentos hasta el diseño de modelos complejos. El proyecto sirve como guía de implementación para construir varios tipos de redes, incluyendo redes lineales, logísticas, convolucionales y recurrentes. Cubre específicamente el flujo de trabajo para el modelado de secuencias mediante el uso de mecanismos de atención y redes a nivel de carácter. El recurso también cubre la preparación de datos para machine learning, incluyendo el uso de cargadores de datasets personalizados, herramientas de procesamiento de texto y la traducción de archivos fuente crudos a tensores para pipelines de entrenamiento.

mmpretrain is a modular PyTorch computer vision framework designed for developing, training, and benchmarking deep learning architectures. It serves as a comprehensive toolkit for vision tasks, providing a specialized platform for multimodal machine learning and self-supervised learning. The project features a computer vision model zoo containing architectural definitions and pre-trained weights for backbones such as ViT, ConvNeXt, and Swin Transformer. It distinguishes itself through a dedicated self-supervised learning toolkit that implements algorithms like MAE and DINO to train models wit

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