# Honlan/DeepInterests

深度有趣

Repository: https://github.com/Honlan/DeepInterests
Canonical: https://ross.abutalabs.com/products/deepinterests
License Family: other
Topics: mit-license, python, deep-learning, computer-vision, natural-language-processing, artificial-intelligence, tensorflow, keras
Last push: 2020-08-20T08:34:51+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": 3089, "days_push": 2204, "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 2285, forks 404 (observed 2026-08-28T04:06:34.048102+00:00)

## What it is
DeepInterests is a Chinese-language collection of hands-on deep learning projects built with Python3, TensorFlow 1.9, and Keras 2.2, accompanied by a 182-page course document and optional paid video lessons. It covers roughly 30 projects spanning GANs, autoencoders, image classification and style transfer, object detection, word vectors, machine translation, speech recognition, and DQN reinforcement learning.

## Use cases
- learn deep learning through practical projects
- implement GANs for face and anime avatar generation
- practice image style transfer with TensorFlow
- build seq2seq machine translation models
- train word embeddings and compute sentence similarity
- get started with object detection and speech recognition
- learn DQN reinforcement learning with FlappyBird

## When to choose
- you want a broad, project-based introduction to deep learning with TensorFlow and Keras
- you prefer Chinese-language tutorials with accompanying documentation and code
- you want to sample many classic DL techniques (GANs, VAE, seq2seq, DQN) in one collection

## When to avoid
- you need a production-ready library or maintained tool rather than educational code
- you require up-to-date TensorFlow 2.x or PyTorch examples
- you need English-language materials or active community support

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, nlp, speech-recognition, image-processing
- domain: deep-learning, machine-learning, computer-vision, tutorials, artificial-intelligence
- platform: python, cross-platform
- tags: tensorflow, keras, gan, autoencoder, chinese, course-projects, reinforcement-learning, seq2seq, natural-language-processing

## Member repositories
- Honlan/DeepInterests (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:34.048102+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 2026-08-30T02:41:03.791886+00:00, confidence not recorded.
  - readme: https://github.com/Honlan/DeepInterests (fetched 2026-08-28T04:06:34.048102+00:00, sha d4d442419e01)
- Data as of 2026-08-30T08:39:29.467469+00:00.