# srush/Tensor-Puzzles

Solve puzzles. Improve your pytorch.

Repository: https://github.com/srush/Tensor-Puzzles
Canonical: https://ross.abutalabs.com/products/tensor-puzzles
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: machine-learning, puzzle, torch
Last push: 2024-07-15T20:11:52+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1604, "days_push": 779, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4299, forks 395 (observed 2026-08-28T04:08:41.590630+00:00)

## What it is
A collection of 21 PyTorch/Numpy tensor puzzles designed to teach tensor programming and broadcasting from first principles. Learners reimplement standard library functions in one line using only basic operations like arithmetic, indexing, and broadcasting.

## Use cases
- learn pytorch tensor broadcasting
- practice numpy-style tensor manipulation
- improve tensor programming skills
- teach machine learning students tensor fundamentals
- prepare for deep learning coding interviews
- master indexing and broadcasting rules without library shortcuts

## When to choose
- you want hands-on practice with PyTorch or NumPy tensor operations
- you are learning broadcasting and want exercises
- you are an educator looking for teaching material for tensor programming

## When to avoid
- you need production machine learning code or a library
- you want a comprehensive PyTorch tutorial covering models and training
- you are a complete beginner to Python programming

## Facets
- artifact type: learning-resource
- maturity: stable
- function: machine-learning, developer-tools, testing
- domain: machine-learning, education, tutorials
- platform: python
- tags: pytorch, numpy, broadcasting, puzzles, jupyter-notebook, colab, tensor-programming, web-server

## Member repositories
- srush/Tensor-Puzzles (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.590630+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:51.358876+00:00, confidence not recorded.
  - readme: https://github.com/srush/Tensor-Puzzles (fetched 2026-08-28T04:08:41.590630+00:00, sha 459a843f7397)
- Data as of 2026-08-30T08:39:29.467469+00:00.