hjptriplebee / Chinese_poem_generator
Licence: gpl-3.0
唐诗、宋词生成器,有详细说明
Stars: ✭ 428
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Chinese poem generator
Personality Detection
Implementation of a hierarchical CNN based model to detect Big Five personality traits
Stars: ✭ 338 (-21.03%)
Mutual labels: lstm
Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (-14.25%)
Mutual labels: lstm
Basicocr
BasicOCR是一个致力于解决自然场景文字识别算法研究的项目。该项目由长城数字大数据应用技术研究院佟派AI团队发起和维护。
Stars: ✭ 336 (-21.5%)
Mutual labels: lstm
Thesemicolon
This repository contains Ipython notebooks and datasets for the data analytics youtube tutorials on The Semicolon.
Stars: ✭ 345 (-19.39%)
Mutual labels: lstm
Actionai
custom human activity recognition modules by pose estimation and cascaded inference using sklearn API
Stars: ✭ 404 (-5.61%)
Mutual labels: lstm
Ner Lstm Crf
An easy-to-use named entity recognition (NER) toolkit, implemented the Bi-LSTM+CRF model in tensorflow.
Stars: ✭ 337 (-21.26%)
Mutual labels: lstm
Handwriting Generation
Implementation of handwriting generation with use of recurrent neural networks in tensorflow. Based on Alex Graves paper (https://arxiv.org/abs/1308.0850).
Stars: ✭ 361 (-15.65%)
Mutual labels: lstm
Tensorflow poems
中文古诗自动作诗机器人,屌炸天,基于tensorflow1.10 api,正在积极维护升级中,快star,保持更新!
Stars: ✭ 3,429 (+701.17%)
Mutual labels: lstm
Keras Anomaly Detection
Anomaly detection implemented in Keras
Stars: ✭ 335 (-21.73%)
Mutual labels: lstm
Predictive Maintenance Using Lstm
Example of Multiple Multivariate Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras.
Stars: ✭ 352 (-17.76%)
Mutual labels: lstm
Crnn attention ocr chinese
CRNN with attention to do OCR,add Chinese recognition
Stars: ✭ 315 (-26.4%)
Mutual labels: lstm
Flow Forecast
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
Stars: ✭ 368 (-14.02%)
Mutual labels: lstm
Deep srl
Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next
Stars: ✭ 309 (-27.8%)
Mutual labels: lstm
Cnn lstm ctc tensorflow
CNN+LSTM+CTC based OCR implemented using tensorflow.
Stars: ✭ 343 (-19.86%)
Mutual labels: lstm
Zhihu Text Classification
[2017知乎看山杯 多标签 文本分类] ye组(第六名) 解题方案
Stars: ✭ 392 (-8.41%)
Mutual labels: lstm
Stock Prediction Models
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
Stars: ✭ 4,660 (+988.79%)
Mutual labels: lstm
Chinese_poem_generator
唐诗宋词生成器,MC胖虎,使用LSTM完成,先看几个demo:
一首藏头诗刀山火海送给大家!
胖虎学诗,会对偶,用典故,能作出边塞、田园、离别等多种风格的诗!
依赖
- Python3
- tensorflow1.2+
用法
- "python3 main.py -m {train, test, head}" train训练, test随机写诗, head藏头诗.
- 在对深度学习有一定了解的基础上,可尝试使用evalute.py评估自己训练的模型。
最近一次更新(2018-06-11)
- add coverage
常见问题
Q: 默认写唐诗,如何使胖虎写宋词,歌曲等其他东西?
A: 因为仓库不宜过大,所以只放了词的训练数据而没有放训练好的模型。config.py中默认的type是poetrySong,因而训练数据用的是“./dataset/poetrySong/poetrySong.txt",加载的checkpoint是”./checkpoints/poetrySong/checkpoint“,如想使用其他训练数据,修改config.py,比如:type = songci,然后训练至少10个epoch。
Q: 如何训练自己的数据?
A: 目前的训练数据来源于https://github.com/chinese-poetry/chinese-poetry,我已经将json转换成txt,训练数据格式如下,可以将自己的数据做成这种形式训练模型。将数据按照同样的形式放入dataset下自己新建的目录,修改config.py中的type即可训练。
标题::作者::内容
静夜思::李白::床前看月光,疑是地上霜。举头望山月,低头思故乡。
接下来要做
- 尝试采用双向lstm模型
- 数据预处理步骤需要加强,比如:特殊符号。
- 看图写诗,苦于没有数据集。
- 引入平仄等信息,使网络更容易拟合宋不规整的数据。
- tensorboard
- 写一篇关于整个项目的博文
有时候效果不好,多生成几次一定有比较好的结果。现在看起来有点像人工智障,但是相信胖虎会越来越厉害!
方法比较粗暴,欢迎各位大佬提出建设性意见! 详细的项目实现和代码说明请看这里
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].