vahidk/EffectivePyTorch resource
PyTorch tutorials and best practices. observed · 2026-08-28
Health v2 · maintenance only
38/100
- Activity 13
- Release rhythm 35
- Longevity 100
Flags: no_releases no_license
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2344
- days_rel: n/a
- days_push: 527
- n_releases_24m: 0
Adoption not part of the score
1713 stars · 173 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
EffectivePyTorch is an open ebook of tutorials covering PyTorch fundamentals and best practices, including tensors, modules, TorchScript, data loaders, and mixed precision training. It is a documentation-style learning resource rather than a software library.
Use cases
- learn pytorch basics
- understand pytorch tensor broadcasting pitfalls
- optimize pytorch training with torchscript
- build efficient custom data loaders in pytorch
- speed up training with automatic mixed precision
- learn numerical stability practices in pytorch
When to choose
- you are learning PyTorch from scratch
- you want concise best-practice guidance for PyTorch idioms
- you need a free reference on TorchScript, AMP, or data loaders
When to avoid
- you need runnable library code or a framework
- you want comprehensive structured courses with exercises
- you need official or exhaustive API documentation
Facets
learning-resource · maturity active
machine-learning deep-learning deep-learning machine-learning tutorials python cross-platform pytorch ebook tutorial best-practices neural-networks gpu
1 source
- readme: https://github.com/vahidk/EffectivePyTorch · fetched 2026-08-28 · 52fa4022d66f
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| vahidk/EffectivePyTorch | main | 38 |
For agents
markdown · JSON · MCP: product_card(name="vahidk/EffectivePyTorch")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem