# datawhalechina/thorough-pytorch

PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/

Repository: https://github.com/datawhalechina/thorough-pytorch
Canonical: https://ross.abutalabs.com/products/thorough-pytorch
Homepage: https://datawhalechina.github.io/thorough-pytorch/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: deep-learning, machine-learning, python, pytorch
Last push: 2026-01-18T10:08:26+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 35, longevity 100
- inputs: {"age_days": 1859, "days_push": 227, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3760, forks 553 (observed 2026-08-28T04:08:17.902552+00:00)

## What it is
An open-source Chinese-language PyTorch tutorial course ('Thorough PyTorch') by DataWhale, delivered as Jupyter notebooks and markdown docs with an online reading site and companion videos. It covers PyTorch fundamentals, model building, advanced training techniques, visualization, ecosystem tools, and model deployment.

## Use cases
- learn pytorch from scratch
- pytorch tutorial for beginners
- understand tensors and autograd in pytorch
- learn advanced pytorch training techniques like fine-tuning and mixed precision
- visualize training with tensorboard or wandb
- deploy pytorch models with onnx
- read source code of resnet and transformer models
- follow a structured pytorch study group curriculum

## When to choose
- you know Python and basic ML and want a structured, hands-on PyTorch course
- you prefer Chinese-language learning materials with notebooks and videos
- you want coverage from basics through fine-tuning, visualization, and ONNX deployment

## When to avoid
- you need official, always-current API documentation
- you want a course in English or on frameworks other than PyTorch
- you need production-grade code rather than educational examples

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, tutorials, education
- platform: python
- tags: pytorch, tutorial, chinese, jupyter-notebook, datawhale, open-course

## Member repositories
- datawhalechina/thorough-pytorch (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:17.902552+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 2026-08-29T18:28:54.121576+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/thorough-pytorch (fetched 2026-08-28T04:08:17.902552+00:00, sha e957f2d9619d)
  - homepage: https://datawhalechina.github.io/thorough-pytorch/ (fetched 2026-08-29T09:22:52.836147+00:00, sha 5e027f63b625)
- Data as of 2026-08-30T08:39:29.467469+00:00.