# wb14123/seq2seq-couplet

Play couplet with seq2seq model. 用深度学习对对联。

Repository: https://github.com/wb14123/seq2seq-couplet
Canonical: https://ross.abutalabs.com/products/seq2seq-couplet
Homepage: https://ai.binwang.me/couplet
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: seq2seq, deep-learning, machine-learning
Last push: 2024-07-25T02:24:32+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3112, "days_push": 770, "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 5487, forks 1054 (observed 2026-08-28T04:09:19.748000+00:00)

## What it is
A deep learning project that generates Chinese couplets (对联) using a seq2seq model built with TensorFlow. It includes training scripts, a web server for serving the model, and Docker support, with a live demo available online.

## Use cases
- generate the second line of a Chinese couplet from the first line
- train a seq2seq model on Chinese couplet data
- serve a trained couplet model as a web service
- experiment with sequence-to-sequence text generation in TensorFlow
- build a fun AI demo for Chinese poetry

## When to choose
- you want a working seq2seq example for Chinese text generation
- you need a ready-made couplet generation model with training and serving code
- you want to learn how to train and deploy a TensorFlow seq2seq model end to end

## When to avoid
- you need modern framework support (project uses older TensorFlow and Python 3.6)
- you need production-grade NLP generation beyond couplets
- you cannot provide a GPU or the couplet dataset

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, llm-training
- domain: deep-learning, machine-learning
- platform: python
- tags: seq2seq, couplet, tensorflow, chinese-poetry, text-generation, natural-language-processing, linux, docker, web-server

## Member repositories
- wb14123/seq2seq-couplet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.748000+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 2026-08-29T17:56:22.146681+00:00, confidence not recorded.
  - readme: https://github.com/wb14123/seq2seq-couplet (fetched 2026-08-28T04:09:19.748000+00:00, sha cf514bdc5a8b)
  - homepage: https://ai.binwang.me/couplet (fetched 2026-08-29T08:51:36.795585+00:00, sha 3778f59da473)
- Data as of 2026-08-30T08:39:29.467469+00:00.