#589 · Primary category： Education & Research
Tensor-Puzzles
Solve puzzles. Improve your pytorch.
Project last updated：07/15/24
GitHub Stars
4.3K
Forks
395
Contributors
3
License
MIT
Why we included this project
Twenty-one puzzles ask you to reimplement a NumPy function using only broadcasting, indexing, and a few allowed operations, each in a single line of code under 80 characters. That constraint forces you to think in terms of shapes and broadcasting rather than reaching for a standard-library shortcut, which is exactly the instinct you need when writing real tensor code. If you build models or process arrays in PyTorch, working through these exercises will make that mental model feel natural. It also works as a self-contained workshop for a team that wants to get more comfortable with NumPy and PyTorch.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
JavaGuide
Java Interview & Backend General Interview Guide, covering computer fundamentals, databases, distributed systems, high concurrency, system design, and AI application development.
system-prompts-and-models-of-ai-tools
A curated collection of system prompts, internal tools, and AI models from popular AI assistants and coding agents.
30-seconds-of-code
Coding articles to level up your development skills
generative-ai-for-beginners
21 Lessons, Get Started Building with Generative AI