# qiaohaoforever/DeepLearningFromScratch

《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​

Repository: https://github.com/qiaohaoforever/DeepLearningFromScratch
Canonical: https://ross.abutalabs.com/products/deeplearningfromscratch
Language: Python
License: MIT
License Family: permissive
Topics: python, pdf, code, machine-learning
Last push: 2025-11-29T06:46:10+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 54, release rhythm 35, longevity 100
- inputs: {"age_days": 2443, "days_push": 277, "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 1218, forks 281 (observed 2026-08-28T04:04:01.614902+00:00)

## What it is
An electronic edition and companion source code for the Chinese translation of the book 'Deep Learning from Scratch' (Deep Learning from Scratch: Theory and Implementation Based on Python). The code implements neural networks and deep learning fundamentals chapter by chapter using only Python, NumPy, and Matplotlib.

## Use cases
- learn deep learning fundamentals from scratch in Python
- implement neural networks with only NumPy
- follow along with a deep learning book's chapter exercises
- understand backpropagation and training from first principles
- study deep learning theory without heavy frameworks

## When to choose
- you want to learn how neural networks work internally without TensorFlow or PyTorch
- you are reading the 'Deep Learning from Scratch' book and need its code
- you prefer minimal dependencies like NumPy and Matplotlib for education

## When to avoid
- you need a production deep learning framework with GPU acceleration
- you want pretrained models or state-of-the-art architectures
- you need maintained library APIs rather than educational code

## Facets
- artifact type: learning-resource
- maturity: stable
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: deep-learning-from-scratch, book-companion-code, numpy, educational, chinese

## Member repositories
- qiaohaoforever/DeepLearningFromScratch (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.614902+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 2026-08-30T06:17:05.303564+00:00, confidence not recorded.
  - readme: https://github.com/qiaohaoforever/DeepLearningFromScratch (fetched 2026-08-28T04:04:01.614902+00:00, sha ca657a60ead5)
- Data as of 2026-08-30T08:39:29.467469+00:00.