awesome-repositories.com
Blog
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
srush avatar

srush/Tensor-Puzzles

0
View on GitHub↗
4,162 stele·378 fork-uri·Jupyter Notebook·MIT·2 vizualizări

Tensor Puzzles

Tensor-Puzzles este o suită de exerciții educaționale și un tutorial de calcul numeric conceput pentru stăpânirea operațiunilor cu tensori și a regulilor de broadcasting în PyTorch. Funcționează ca un antrenor de implementare unde utilizatorii exersează tranziția formulelor matematice în cod prin reimplementarea primitivelor matematice de deep learning.

Proiectul utilizează o suită de exerciții bazată pe constrângeri care restricționează apelurile de bibliotecă disponibile pentru a forța utilizarea unor primitive specifice de tensori. Aceste provocări sunt structurate ca puzzle-uri secvențiale care necesită ca utilizatorii să rezolve sarcini folosind un model de implementare modular, unde funcțiile complexe sunt descompuse în operațiuni dependente mai simple.

Acuratețea este asigurată printr-un mediu de execuție integrat în PyTorch care utilizează validarea implementării de referință și verificări de toleranță numerică. Sistemul verifică dacă output-urile definite de utilizator corespund rezultatelor de referință și respectă regulile standard de broadcasting pentru array-uri multidimensionale.

Features

  • Tensor Broadcasting - Provides a mechanism for validating that multi-dimensional arrays align according to standard tensor broadcasting rules.
  • Runtime Evaluation Environments - Provides an execution environment that runs user code within a live PyTorch session for validation.
  • PyTorch Tensor Operations - Integrates with PyTorch to execute tensor operations and validate runtime shapes and types.
  • PyTorch Code Exercises - Offers practical exercises and constrained challenges for learning multi-dimensional array manipulation in PyTorch.
  • Machine Learning Mathematics - Teaches the fundamental mathematical operations and logic underlying neural network layers.
  • Automated Exercise Suites - Provides a series of coding tasks bundled with automated verification for tensor operation implementation.
  • API Call Restrictions - Restricts available library calls to force the use of specific tensor primitives during exercises.
  • Reference Implementation Validation - Evaluates user submissions against a hidden gold-standard implementation to ensure mathematical equivalence.
  • Implementation Trainers - Trains users to transition from mathematical formulas to efficient PyTorch code through verified exercises.
  • Progressive Learning Paths - Structures tensor manipulation tasks as a series of progressive puzzles where solutions build on previous concepts.
  • Programming Course Materials - Offers structured sets of interactive lessons for reimplementing deep learning mathematical primitives.
  • Precision-Tolerant Comparisons - Uses epsilon-based precision-tolerant comparisons to handle floating point rounding errors in tensor results.
  • Interactive Tutorials - Serves as a guided set of challenges for understanding tensor broadcasting and linear algebra fundamentals.
  • Runtime Shape Verification - Provides runtime verification to ensure tensor dimensions adhere to broadcasting alignment rules.
  • Numerical Tolerance Checks - Implements a test runner that verifies tensor output correctness using numerical tolerance epsilon checks.

Istoric stele

Graficul istoricului de stele pentru srush/tensor-puzzlesGraficul istoricului de stele pentru srush/tensor-puzzles

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Întrebări frecvente

Ce face srush/tensor-puzzles?

Tensor-Puzzles este o suită de exerciții educaționale și un tutorial de calcul numeric conceput pentru stăpânirea operațiunilor cu tensori și a regulilor de broadcasting în PyTorch. Funcționează ca un antrenor de implementare unde utilizatorii exersează tranziția formulelor matematice în cod prin reimplementarea primitivelor matematice de deep learning.

Care sunt principalele funcționalități ale srush/tensor-puzzles?

Principalele funcționalități ale srush/tensor-puzzles sunt: Tensor Broadcasting, Runtime Evaluation Environments, PyTorch Tensor Operations, PyTorch Code Exercises, Machine Learning Mathematics, Automated Exercise Suites, API Call Restrictions, Reference Implementation Validation.

Care sunt câteva alternative open-source pentru srush/tensor-puzzles?

Alternativele open-source pentru srush/tensor-puzzles includ: shuhuai007/machine-learning-session — This project is a machine learning educational resource and study site focused on the theoretical foundations and… mml-book/mml-book.github.io — This project is an educational resource focused on machine learning mathematics education. It provides a curriculum… datawhalechina/thorough-pytorch — This project is an educational resource and comprehensive guide for implementing and deploying deep learning models… 649453932/bert-chinese-text-classification-pytorch — This project is a PyTorch-based Chinese text classification framework. It provides a transformer-based pipeline… atcold/nyu-dlsp20 — NYU-DLSP20 is a self-paced deep learning course repository that provides a complete educational curriculum covering… amdegroot/ssd.pytorch — This is a PyTorch object detection framework that implements the Single Shot MultiBox Detector for identifying and…

Alternative open-source pentru Tensor Puzzles

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Tensor Puzzles.
  • mml-book/mml-book.github.ioAvatar mml-book

    mml-book/mml-book.github.io

    15,671Vezi pe GitHub↗

    This project is an educational resource focused on machine learning mathematics education. It provides a curriculum for the mathematical foundations required to understand and implement machine learning algorithms, covering linear algebra, calculus, probability, and optimization. The resource includes structured mathematics modules and a foundation curriculum paired with practice exercises, instructor manuals, and solution guides. It offers technical textbook supplementation through downloadable PDF materials and supplementary learning content such as video lectures and presentation slides.

    Jupyter Notebook
    Vezi pe GitHub↗15,671
  • shuhuai007/machine-learning-sessionAvatar shuhuai007

    shuhuai007/Machine-Learning-Session

    5,241Vezi pe GitHub↗

    This project is a machine learning educational resource and study site focused on the theoretical foundations and mathematical derivations of machine learning algorithms. It serves as a study guide for mastering the linear algebra, calculus, and proofs required for predictive modeling. The site functions as a markdown documentation portal and static site generator, converting formatted text and LaTeX formulas into a structured web interface. It utilizes a typesetting engine to render complex academic derivations and mathematical equations clearly within the browser. The platform includes a r

    Vezi pe GitHub↗5,241
  • datawhalechina/thorough-pytorchAvatar datawhalechina

    datawhalechina/thorough-pytorch

    3,684Vezi pe GitHub↗

    This project is an educational resource and comprehensive guide for implementing and deploying deep learning models using the PyTorch framework. It provides a structured learning curriculum consisting of tutorials and notebooks that cover neural network architectures, data pipelines, and model optimization across multiple AI domains. The curriculum includes practical implementation guides for building convolutional networks, transformers, and recurrent models. It specifically focuses on workflows for computer vision, including image classification, object detection, and segmentation, as well

    Jupyter Notebookdeep-learningmachine-learningpython
    Vezi pe GitHub↗3,684
  • 649453932/bert-chinese-text-classification-pytorchAvatar 649453932

    649453932/Bert-Chinese-Text-Classification-Pytorch

    4,425Vezi pe GitHub↗

    This project is a PyTorch-based Chinese text classification framework. It provides a transformer-based pipeline designed to categorize Chinese language sequences into predefined labels using deep learning models. The implementation supports both BERT and ERNIE language models for processing and tagging complex Chinese text. These models are used to perform tasks such as sentiment analysis and general text categorization. The system utilizes transformer-based text encoding and attention-weighted sequence pooling to convert raw characters into document vectors. It employs pre-trained model fin

    Python
    Vezi pe GitHub↗4,425
Vezi toate cele 30 alternative pentru Tensor Puzzles→