34 مستودعات
Tools that perform element-wise operations and shape manipulations on tensor data structures.
Explore 34 awesome GitHub repositories matching data & databases · Tensor Transformations. Refine with filters or upvote what's useful.
TensorFlow is a comprehensive machine learning framework designed for the construction, training, and deployment of complex mathematical models. It utilizes a graph-based execution model that represents operations as directed acyclic graphs, enabling automatic differentiation and efficient parallel processing. The system provides high-level interfaces for defining neural network architectures, alongside a robust engine for managing multidimensional array structures and tensor mathematics. The framework distinguishes itself through a scalable distributed runtime that orchestrates workloads acr
Applies optimized routines to perform element-wise operations and shape manipulations on multi-dimensional data structures.
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
Converts raw image annotations into standardized tensor formats for consistent model training.
This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex
Converts processed numerical datasets into framework-specific tensor formats for model computation.
This project is a comprehensive educational resource and programming course covering C++ language semantics and features from C++03 through C++26. It provides structured tutorials and technical guides focused on modern C++ development. The material offers specialized instruction on template metaprogramming, including the use of type traits and compile-time computations. It features detailed guides on concurrency and parallelism for multi-core execution, as well as a reference for software design applying SOLID principles and RAII. Additionally, it covers build performance optimization to redu
Provides instruction on representing matrices and tensors using non-owning views that map indices to linear memory.
MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse
Modifies tensor values using element-wise scaling, bias addition, or padding to prepare numerical data for inference.
This is a collection of tutorials and practical demonstrations for implementing machine learning tasks using the HuggingFace Transformers library. It serves as a guide for applying transformer architectures across computer vision, natural language processing, and audio analysis. The repository provides implementation examples for multimodal model deployment, including the combination of text, image, and audio inputs. It includes resources for optimizing pre-trained models through fine-tuning on custom datasets and provides examples for preparing PyTorch datasets by converting raw files into t
Provides examples for converting raw input files into tensors and batches for efficient model processing.
This project is a structured learning curriculum and technical reference for mastering deep learning with TensorFlow. It provides a comprehensive guide for building, training, and deploying neural networks, combining theoretical fundamentals with practical implementation examples. The repository distinguishes itself by covering the end-to-end machine learning workflow, from low-level tensor mathematics and linear algebra to the creation of complex model architectures. It includes specific guidance on developing data pipelines for diverse data types, such as images, text, and time-series seque
Provides comprehensive instructions for performing tensor reshaping, squeezing, and transposing operations.
Einops is a tensor manipulation library that provides a framework-agnostic interface for reshaping, Einstein summation, and multi-dimensional array operations. It serves as an abstraction layer that works across NumPy, PyTorch, TensorFlow, and JAX, allowing for tensor transformations without changing the API. The library distinguishes itself through a declarative notation system that uses readable string patterns to describe tensor rearrangements and reductions. This approach includes an extended Einstein summation interface that supports multi-letter axis names and a named dimension mapping
Combines tensors of varying shapes into a single array and tracks their shapes for later restoration.
Torch7 is a scientific computing environment and tensor computation library used for deep learning research and numerical analysis. It functions as a Lua-based framework for training neural networks and learning agents, providing a toolkit for implementing architectures and training through reinforcement learning algorithms. The project is distinguished by its tight integration with C, utilizing a binding layer to map high-level scripting to low-level C structures for direct memory access. It supports hardware-accelerated computation by offloading linear algebra and convolution operations to
Collects values from each row of a source tensor based on an index tensor.
jc is a tool that transforms plain-text results from command-line utilities, system tools, log formats, and text tables into structured JSON data. It functions as a structured data transformer capable of converting various file formats, including CSV, INI, XML, and YAML, into JSON representations for programmatic use. The project includes a collection of specific parsers for Unix commands and system tools such as df, blkid, and various package managers. It also features specialized converters for web server logs, Common Log Format, and Common Event Format strings. The tool covers broad capab
Transforms ASCII and Unicode text tables into structured JSON objects by mapping column headers to row values.
This project is a collection of PyTorch learning resources and educational guides designed to teach the construction and training of neural networks. It serves as a comprehensive deep learning tutorial covering various model architectures and practical implementation strategies. The resources provide specific guidance on implementing computer vision tasks, such as image classification and synthetic imagery generation, as well as reinforcement learning agents using value networks and experience replay. It also covers sequential data modeling through recurrent networks and generative modeling u
Demonstrates how to transform input tensors using mathematical operations to enable complex pattern learning.
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
Implements adaptive pooling to resize feature maps to a target size regardless of input dimensions.
Flashlight هي مكتبة تعلم آلي مستقلة بلغة C++ ومكتبة موترات تستخدم لبناء وتدريب الشبكات العصبية. تعمل كإطار عمل شامل للشبكات العصبية ومحرك للتمايز التلقائي، مما يوفر الأدوات لبناء رسوم بيانية للحساب وحساب التدرجات عبر الانتشار العكسي. يعمل المشروع كإطار عمل للتدريب الموزع، حيث يستخدم عمليات (All-reduce) لمزامنة التدرجات والمعلمات عبر عقد حساب وأجهزة متعددة. يتميز بالتكامل العميق لمعالجة الموترات عالية الأداء، وقابلية التشغيل البيني لذاكرة الجهاز الأصلية، ونظام لمزامنة الأوزان عبر العمال الموزعين لتسريع تدريب النماذج واسعة النطاق. يغطي إطار العمل مجموعة واسعة من قدرات التعلم العميق، بما في ذلك تكوين الطبقات المعيارية لتصميم بنيات معقدة مثل الكتل المتبقية (Residual blocks) والخلايا المتكررة. يوفر أدوات واسعة النطاق لإدارة البيانات للاستيعاب والجلب المسبق، إلى جانب أنظمة التسلسل لحفظ حالات النموذج. بالإضافة إلى ذلك، يتضمن مجموعة من أدوات المراقبة وقابلية المراقبة لتتبع مقاييس التدريب وقياس أخطاء التسلسل. تم تنفيذ المكتبة بلغة C++.
Generates tensors containing identity matrices, sequential ranges, and evenly-spaced values.
Flashlight هي مكتبة تعلم آلي بلغة C++ وإطار عمل للتعلم العميق مصمم لبناء وتدريب الشبكات العصبية. تعمل كمكتبة لمعالجة الموترات (Tensors) ومحرك للتمايز التلقائي يتتبع العمليات لحساب التدرجات عبر الانتشار العكسي (Backpropagation) لتحسين النموذج. يتميز المشروع بدوره كإطار عمل للتدريب الموزع، حيث يستخدم مزامنة التدرج (All-reduce) والبيئات الموزعة لتوسيع نطاق أحمال عمل التعلم الآلي عبر عقد وأجهزة متعددة. يتميز بواجهة ذاكرة غير مرتبطة بالخلفية وإدارة تعتمد على RAII لفصل عمليات الموتر عن الأجهزة الفعلية. يغطي إطار العمل مساحة قدرة واسعة بما في ذلك بناء بنيات الشبكات العصبية مع طبقات تلافيفية وخطية ومتكررة. يوفر أدوات واسعة النطاق لجبر الموترات، وإدارة مجموعات البيانات وتجميعها، وتسلسل ثنائي مرقم لحالات النموذج، وأدوات مراقبة لتتبع مقاييس التدريب واستخدام الذاكرة.
Ships functions for saving and loading tensors and neural network modules to binary files.
llm-viz is a 3D architecture visualizer and inference simulator for large language models. It provides a visual representation of network topology and the mathematical operations used during the process of generating a response. The tool enables the exploration of internal weight distributions and the layout of layers within a neural network. It facilitates model interpretability and inference debugging by tracking the step-by-step movement of data through the architecture. The system utilizes GPU-accelerated 3D rendering to visualize tensor flow and spatial mappings of weights. It includes
Visualizes the movement and transformation of data tensors as they pass through different model layers during inference.
Danfo.js هي مكتبة لتحليل البيانات والمعالجة المسبقة لـ JavaScript توفر هياكل بيانات مصنفة عالية الأداء. تنفذ إطارات البيانات (DataFrames) والسلاسل لتمكين تحليل البيانات المعقد، والحوسبة الإحصائية، ومعالجة البيانات الجدولية المهيكلة. تعمل المكتبة كمكتبة للمعالجة المسبقة لتعلم الآلة، حيث تقدم أدوات لتشفير التسميات الفئوية، والتشفير الأحادي (One-hot encoding)، وتوسيع نطاق الميزات الرقمية وتوحيدها. تسهل بشكل خاص تحويل هياكل البيانات المصنفة إلى tensors لتدريب النماذج وتقييمها. تغطي المكتبة مجموعة واسعة من القدرات بما في ذلك الإحصاءات الوصفية، والعمليات العلائقية مثل الدمج والربط، ومعالجة السلاسل الزمنية. تتضمن أدوات لتنظيف البيانات، والتصفية، والتجميع، بالإضافة إلى واجهة مرئية لإنشاء مخططات ورسوم بيانية تفاعلية مباشرة من إطارات البيانات. يدعم النظام استيراد وتصدير البيانات عبر تنسيقات CSV وJSON وExcel.
Provides utilities to transform structured data frames into tensors for compatibility with machine learning frameworks.
This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep learning and natural language processing. It uses real datasets and multiple frameworks within a structured, hands-on curriculum that combines concise explanations with executable code cells, built-in datasets, and embedded exercise checkpoints. Learning progresses through data preparation and exploration, classical machine learning workflows, computer vision with convolutional neural networks, and natural language processing with deep learning, all delivered as a cohesive progressi
Provides operations for concatenating, stacking, or dividing tensors and arrays along specified dimensions.
This repository is a comprehensive educational program and deep learning framework designed to teach practical deep learning using PyTorch through notebooks and code examples. It serves as a high-level library for building, training, and deploying neural networks, acting as a model training orchestrator that coordinates PyTorch models, optimizers, and loss functions. The project provides specialized toolkits for computer vision, natural language processing, and tabular data preprocessing. It distinguishes itself through advanced training controls such as discriminative learning rates, a two-w
Provides utilities to recursively move tensors and data collections between different hardware devices.
ArrayFire هو إطار عمل حوسبة مستقل عن الأجهزة ومحرك مصفوفات مجمع فورياً (JIT) مصمم للحوسبة الرقمية عالية الأداء. يعمل كمكتبة حوسبة رقمية لوحدات معالجة الرسومات ومجموعة أدوات معالجة إشارات متوازية تجرد خلفيات الأجهزة، مما يسمح لنفس الكود بالتنفيذ عبر معماريات GPU و CPU مختلفة. يتميز المشروع بمحرك JIT يستخدم تجميع التعبيرات لدمج العمليات وتقليل عبء الذاكرة. يستخدم رسماً بيانياً للتنفيذ المؤجل لتحسين سلاسل الحسابات ويوفر أساسيات التشغيل البيني لمشاركة البيانات وسياقات التنفيذ مع منصات حوسبة خارجية مثل CUDA و OpenCL. تغطي المكتبة مجموعة واسعة من القدرات، بما في ذلك الجبر الخطي المتوازي، ومعالجة الإشارات الرقمية، ورؤية الحاسوب المسرعة. توفر أدوات لتنفيذ التعلم الآلي، ومحاكاة النمذجة المالية، وحل المعادلات التفاضلية الجزئية لمحاكاة الأنظمة الفيزيائية. يتعامل نظام إدارة المصفوفات الخاص بها مع تخصيص المصفوفات متعددة الأبعاد، والتقطيع، ونقل البيانات بين المضيف والجهاز.
Extracts specific rows, columns, or subarrays using sequences, spans, and strides.
Ignite is a high-level training framework for PyTorch neural networks that serves as a training engine and deep learning lifecycle manager. It provides a structured system for organizing and automating training and evaluation loops, managing data iterators and triggering event handlers at specific milestones during the model training process. The project distinguishes itself through a comprehensive suite of tools for distributed training and model evaluation. It includes utilities for synchronizing gradients and coordinating collective communication across multiple GPUs or nodes, as well as a
Collects tensors or strings from all participating processes and aggregates them into a single list.