# NELSONZHAO/zhihu

This repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natural Language Processing and Computer Vision projects, such as text generation, machine translation, deep convolution GAN and other actual combat code.

Repository: https://github.com/NELSONZHAO/zhihu
Canonical: https://ross.abutalabs.com/products/zhihu
Homepage: https://zhuanlan.zhihu.com/zhaoyeyu
Language: Jupyter Notebook
License Family: other
Topics: deep-learning, tensorflow-examples, convolutional-neural-networks, recurrent-neural-networks, autoencoder, gan, style-transfer, natural-language-processing, machine-translation
Last push: 2021-06-14T08:33:33+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3387, "days_push": 1906, "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 3522, forks 2097 (observed 2026-08-28T04:08:07.980787+00:00)

## What it is
A collection of Jupyter Notebook tutorials accompanying the author's Zhihu column '机器不学习', implementing deep learning projects in TensorFlow and Keras. It covers NLP tasks like text generation, word embeddings, machine translation, and sentiment analysis, plus CV projects like CNN classification, autoencoders, and GANs.

## Use cases
- learn deep learning with tensorflow through worked examples
- implement seq2seq machine translation with attention
- train a gan to generate mnist digits
- build a character-level lstm text generator
- understand word2vec skip-gram implementation
- compare dnn lstm and cnn for sentiment analysis
- denoise images with convolutional autoencoders

## When to choose
- you want tutorial-style code paired with detailed Chinese blog explanations
- you are learning TensorFlow 1.x or Keras fundamentals
- you need reference implementations of classic models like DCGAN, seq2seq, and skip-gram

## When to avoid
- you need production-ready or maintained code
- you use TensorFlow 2.x or PyTorch exclusively
- you need a license permitting reuse

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, nlp, machine-learning, image-processing
- domain: deep-learning, computer-vision, tutorials
- platform: python
- tags: tensorflow, keras, jupyter-notebook, gan, seq2seq, word2vec, autoencoder, text-generation, machine-translation, sentiment-analysis, style-transfer, chinese-blog-companion, natural-language-processing

## Member repositories
- NELSONZHAO/zhihu (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.980787+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 2026-08-29T18:35:12.180627+00:00, confidence not recorded.
  - readme: https://github.com/NELSONZHAO/zhihu (fetched 2026-08-28T04:08:07.980787+00:00, sha 4b60ac12ea5c)
- Data as of 2026-08-30T08:39:29.467469+00:00.