{"componentChunkName":"component---src-templates-blog-detail-tsx","path":"/blog/2020-05-20-poems","result":{"data":{"currentBlog":{"id":"caebf2fd-ebd7-5972-a908-0ac7d00c5bd8","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020520/1589979656824-520.jpg","authors":["Anycodes"],"categories":["user-stories"],"date":"2020-05-20T00:00:00.000Z","title":"Serverless 的 AI 写诗，程序员浪漫起来谁能顶得住啊！","description":"本来来自 Serverless 社区成员的投稿，谢谢，有被撩到 :P","authorslink":["https://zhuanlan.zhihu.com/ServerlessGo"],"translators":null,"translatorslink":null,"tags":["深度学习","Serverless"],"keywords":"Serverless","outdated":true},"wordCount":{"words":172,"sentences":28,"paragraphs":28},"fileAbsolutePath":"/opt/build/repo/content/blog/2020-05-20-poems.md","fields":{"slug":"/blog/2020-05-20-poems/","keywords":["python","serverless","spa","云函数","model","古诗词","serverless","serverlesscloud"]},"html":"

古诗词是中国文化殿堂的瑰宝，记得曾经在韩国做 Exchange Student 的时候，看到他们学习我们的古诗词，有中文的还有翻译版的，自己发自内心的骄傲，甚至也会在某些时候背起一些耳熟能详的诗词。

\n

本文将会通过深度学习为我们生成一些古诗词，并将模型部署到 Serverless 架构上，实现基于 Serverless 的古诗词生成 API。

\n

\n

项目构建

\n

古诗词生成实际上是文本生成，或者说是生成式文本。关于基于深度学习的文本生成，最入门级的读物包括 Andrej Karpathy 的博客。他使用例子生动讲解了 Char-RNN (Character based Recurrent Neural Network) 如何用于从文本数据集里学习，然后自动生成像模像样的文本。

\n

\n

上图直观展示了 Char-RNN 的原理。以要让模型学习写出「hello」为例，Char-RNN 的输入输出层都是以字符为单位。输入「h」，应该输出「e」；输入「e」，则应该输出后续的「l」。

\n

输入层我们可以用只有一个元素为1的向量来编码不同的字符，例如，「h」被编码为「1000」、「e」被编码为「0100」，而「l」被编码为「0010」。使用 RNN 的学习目标是，可以让生成的下一个字符尽量与训练样本里的目标输出一致。在图一的例子中，根据前两个字符产生的状态和第三个输入「l」预测出的下一个字符的向量为 <0.1, 0.5, 1.9, -1.1>，最大的一维是第三维，对应的字符则为「0010」，正好是「l」。这就是一个正确的预测。但从第一个「h」得到的输出向量是第四维最大，对应的并不是「e」，这样就产生代价。

\n

学习的过程就是不断降低这个代价。学习到的模型，对任何输入字符可以很好地不断预测下一个字符，如此一来就能生成句子或段落。

\n

本文项目构建参考了 Github 已有项目：https://github.com/norybaby/poet

\n

通过 Clone 代码，并且安装相关依赖：

\n
pip3 install tensorflow==1.14 word2vec numpy
\n

通过训练：

\n
python3 train.py
\n

可以看到训练结果：

\n

\n

\n

此时会生成多个模型在 output_poem 文件夹下，我们只需要保留最好的即可，例如我的训练之后生成的 json 文件：

\n\n \n 复制代码\n \n \n
{\n  \"best_model\": \"output_poem/best_model/model-20390\",\n  \"best_valid_ppl\": 21.441762924194336,\n  \"latest_model\": \"output_poem/save_model/model-20390\",\n  \"params\": {\n    \"batch_size\": 16,\n    \"cell_type\": \"lstm\",\n    \"dropout\": 0.0,\n    \"embedding_size\": 128,\n    \"hidden_size\": 128,\n    \"input_dropout\": 0.0,\n    \"learning_rate\": 0.005,\n    \"max_grad_norm\": 5.0,\n    \"num_layers\": 2,\n    \"num_unrollings\": 64\n  },\n  \"test_ppl\": 25.83984375\n}
\n

此时，我只需要保存 output_poem/best_model/model-20390 模型即可。

\n

部署上线

\n

在项目目录下，安装必要依赖：

\n
pip3 install word2vec numpy -t ./
\n

由于 Tensorflow 等是腾讯云云函数内置的package，所以这里无需安装，另外 numpy 这个 package 需要在 CentOS+Python3.6 环境下打包。也可以通过之前制作的小工具打包：https://www.serverlesschina.com/35.html

\n

完成之后，编写函数入口文件：

\n\n \n 复制代码\n \n \n
import uuid, json\nfrom write_poem import WritePoem, start_model\n\nwriter = start_model()\n\n\ndef return_msg(error, msg):\n    return_data = {\n        \"uuid\": str(uuid.uuid1()),\n        \"error\": error,\n        \"message\": msg\n    }\n    print(return_data)\n    return return_data\n\n\ndef main_handler(event, context):\n    # 类型\n    # 1： 自由\n    # 2： 押韵\n    # 3： 藏头押韵\n    # 4： 藏字押韵\n\n    style = json.loads(event[\"body\"])[\"style\"]\n    content = json.loads(event[\"body\"]).get(\"content\", None)\n\n    if style in '34' and not content:\n        return return_msg(True, \"请输入content参数\")\n\n    if style == '1':\n        return return_msg(False, writer.free_verse())\n    elif style == '2':\n        return return_msg(False, writer.rhyme_verse())\n    elif style == '3':\n        return return_msg(False, writer.cangtou(content))\n    elif style == '4':\n        return return_msg(False, writer.hide_words(content))\n    else:\n        return return_msg(True, \"请输入正确的style参数\")
\n

同时需要准备好 Yaml 文件：

\n\n \n 复制代码\n \n \n
getUserIp:\n  component: \"@serverless/tencent-scf\"\n  inputs:\n    name: autoPoem\n    codeUri: ./\n    exclude:\n      - .gitignore\n      - .git/**\n      - .serverless\n      - .env\n    handler: index.main_handler\n    runtime: Python3.6\n    region: ap-beijing\n    description: 自动古诗词撰写\n    namespace: serverless_tools\n    memorySize: 512\n    timeout: 10\n    events:\n      - apigw:\n          name: serverless\n          parameters:\n            serviceId: service-8d3fi753\n            protocols:\n              - http\n              - https\n            environment: release\n            endpoints:\n              - path: /auto/poem\n                description: 自动古诗词撰写\n                method: POST\n                enableCORS: true
\n

此时，我们就可以通过 Serverless Framework CLI 部署项目。部署完成之后，我们可以通过 PostMan 测试我们的接口：

\n

\n

总结

\n

本文通过已有的深度学习项目，在本地进行训练，保存模型，然后将项目部署在腾讯云云函数上，通过与 API 网关的联动，实现了一个基于深度学习的古诗词撰写的 API。

\n

\"运行结果\"

\n
\n
\n
\n
\n

传送门：

\n\n
\n

欢迎访问：Serverless 中文网，您可以在 最佳实践 里体验更多关于 Serverless 应用的开发！

","tableOfContents":""},"previousBlog":{"id":"a76c7573-dd0d-58ca-b60e-10642b13690f","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020720/1595233426309-1589442691416-%E6%B5%B7%E6%8A%A5%281%29-sketch_%E5%89%AF%E6%9C%AC%20%281%29.jpg","authors":["Serverless 社区"],"categories":["meetup"],"date":"2020-05-22T00:00:00.000Z","title":"Serverless 应用级监控能力 + SSR｜在线分享第二期","description":"本期直播，腾讯云高级产品经理将为您揭秘 Serverless 应用级监控能力的详细设计思路与应用","authorslink":["https://zhuanlan.zhihu.com/ServerlessGo"],"translators":null,"translatorslink":null,"tags":["Serverless","Meetup"],"keywords":"Serverless;Serverless监控","outdated":null},"wordCount":{"words":65,"sentences":9,"paragraphs":9},"fileAbsolutePath":"/opt/build/repo/content/blog/2020-05-22-ssr-dashboard-meetup.md","fields":{"slug":"/blog/2020-05-22-ssr-dashboard-meetup/","keywords":["serverless","Serverless","serverless","监控","serverlesscloud","应用","腾讯"]}},"nextBlog":{"id":"7cdbd3fc-5cc1-50eb-a9ac-21fb5de1cfeb","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020512/1589268598969-haibao.jpg","authors":["Serverless 社区"],"categories":["news"],"date":"2020-05-12T00:00:00.000Z","title":"大咖集结 | 首届 ServerlessDays · China 嘉宾阵容曝光","description":"大会不仅有 ServerlessDays 组织者 Ant Stanley、Serverless 白皮书作者 Johann Schleier-Smith 等全球顶级意见领袖分享 Serverless 前瞻，也有 Google、IBM、腾讯云等国内外一线厂商带来 Serverless 技术新风向，更有 BBC、滴滴、爱奇艺等企业的最佳实践指导！","authorslink":["https://zhuanlan.zhihu.com/ServerlessGo"],"translators":null,"translatorslink":null,"tags":["ServerlessDays","Meetup"],"keywords":"Serverless,ServerlessDays,ServerlessChina","outdated":null},"wordCount":{"words":84,"sentences":13,"paragraphs":13},"fileAbsolutePath":"/opt/build/repo/content/blog/2020-05-12-serverlessdays-poster.md","fields":{"slug":"/blog/2020-05-12-serverlessdays-poster/","keywords":["serverless","云原生","Serverless","ServerlessDays","serverless","serverlesscloud","技术"]}},"recommendBlogs":{"edges":[{"node":{"id":"4300b21c-7209-5256-86ff-0d38e3daec9b","frontmatter":{"thumbnail":"https://main.qcloudimg.com/raw/14f1c8eed372e76c1b139703b2f6d0fa.jpg","authors":["KieranMcCarthy"],"categories":["user-stories","engineering-culture"],"date":"2018-01-09T00:00:00.000Z","title":"我是如何在四年时间里，从厨师转行为 Serverless 应用开发者","description":"我是厨师出身，现在成为了一名 Serverless 应用开发者。","authorslink":["https://serverless.com/author/kieranmccarthy/"],"translators":["Aceyclee"],"translatorslink":["https://www.zhihu.com/people/Aceyclee"],"tags":["应用开发","Serverless"],"keywords":"Serverless 应用开发,Serverless 管理,厨师转行为 Serverless 应用开发者","outdated":null},"wordCount":{"words":285,"sentences":38,"paragraphs":36},"fileAbsolutePath":"/opt/build/repo/content/blog/2018-01-09-from-chef-to-serverless-developer-in-4-years.md","fields":{"slug":"/blog/2018-01-09-from-chef-to-serverless-developer-in-4-years/","keywords":["无服务器","无服务器开发","云函数","学习","Serverless","构建","Framework","开发者","服务器","应用","学位","简历"]}}},{"node":{"id":"713a0563-4bf9-5721-bacb-3b4ef609fe4a","frontmatter":{"thumbnail":"https://s3-us-west-2.amazonaws.com/assets.blog.serverless.com/camp-fire/camp-fire-housing-thumb.jpg","authors":["EricWyne"],"categories":["guides-and-tutorials","user-stories"],"date":"2018-12-05T00:00:00.000Z","title":"Serverless Twitter 机器人帮助为坎普山火受灾者安置住房","description":"加利福尼亚州的坎普山火致使数千人流离失所，为此，我构建了一个简单的 Serverless Twitter 机器人来帮助将受灾者安置在临时住房！","authorslink":["https://serverless.com/author/ericwyne/"],"translators":["Aceyclee"],"translatorslink":["zhihu.com/people/Aceyclee"],"tags":null,"keywords":null,"outdated":null},"wordCount":{"words":157,"sentences":26,"paragraphs":26},"fileAbsolutePath":"/opt/build/repo/content/blog/2018-12-05-serverless-twitter-camp-fire.md","fields":{"slug":"/blog/2018-12-05-serverless-twitter-camp-fire/","keywords":["serverless","无服务器","云函数","Serverless","org","住房","Twitter","函数","受灾","机器人","山火"]}}},{"node":{"id":"98602143-b837-5f50-a24f-3b1ec76044d7","frontmatter":{"thumbnail":"https://s3-us-west-2.amazonaws.com/assets.blog.serverless.com/sqquid/sqquid-serverless-thumb.jpg","authors":["RonPeled"],"categories":["user-stories"],"date":"2018-12-17T00:00:00.000Z","title":"SQQUID：100% 无服务器初创公司","description":"SQQUID 将 AWS Lambda 和无服务器框架用于其核心产品和营销网站。我们来看看一个完全无服务器的初创公司是怎样的。","authorslink":null,"translators":null,"translatorslink":null,"tags":null,"keywords":null,"outdated":null},"wordCount":{"words":266,"sentences":42,"paragraphs":42},"fileAbsolutePath":"/opt/build/repo/content/blog/2018-12-17-sqquid-one-hundred-percent-serverless.md","fields":{"slug":"/blog/2018-12-17-sqquid-one-hundred-percent-serverless/","keywords":["go","serverless","无服务器","无服务器架构","服务器","架构","Lambda","集成","FaaS","串行","系统"]}}},{"node":{"id":"29dc2e58-d2ba-56f9-aee1-d21b0bc62e0e","frontmatter":{"thumbnail":"https://s3-us-west-2.amazonaws.com/assets.blog.serverless.com/ao-com-story/ao-serverless-thumbnail.png","authors":["NickGottlieb"],"categories":["user-stories"],"date":"2019-04-24T00:00:00.000Z","title":"AO.com：逐渐转向无服务器优先","description":"AO.com 的 SCV 团队率先尝试无服务器服务。折服于无服务器框架的快速周转时间和低维护成本，整个团队逐渐转向无服务器优先。","authorslink":null,"translators":null,"translatorslink":null,"tags":null,"keywords":null,"outdated":null},"wordCount":{"words":236,"sentences":42,"paragraphs":35},"fileAbsolutePath":"/opt/build/repo/content/blog/2019-04-24-ao-serverless-first.md","fields":{"slug":"/blog/2019-04-24-ao-serverless-first/","keywords":["serverless","无服务器","服务器","团队","Lambda","功能","构建"]}}},{"node":{"id":"752d08d1-387a-5bde-acf3-98141baab294","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020414/1586871710979-%E5%85%AC%E5%85%B1%E7%94%A8.png","authors":["Anycodes"],"categories":["user-stories"],"date":"2019-06-20T00:00:00.000Z","title":"如何用 Serverless 为 Python 云函数打包依赖","description":"在使用无服务器云函数SCF时通常会遇到导入第三方库的问题，很多小伙伴比较头疼是：应该如何打包进去？这里，推荐几个不错的方法。","authorslink":["https://zhuanlan.zhihu.com/ServerlessGo"],"translators":null,"translatorslink":null,"tags":["云函数","Serverless"],"keywords":"Serverless,Serverless应用,无服务器云函数","outdated":null},"wordCount":{"words":81,"sentences":43,"paragraphs":43},"fileAbsolutePath":"/opt/build/repo/content/blog/2019-06-20-for-python-cloud-functions.md","fields":{"slug":"/blog/2019-06-20-for-python-cloud-functions/","keywords":["java","serverless","无服务器","无服务器云函数","云函数","serverlesscloud","安装","serverless","pillowtest"]}}},{"node":{"id":"2dc78814-9d77-555b-a1bb-ad202c8ec2d1","frontmatter":{"thumbnail":"https://s3-us-west-2.amazonaws.com/assets.blog.serverless.com/cloudforecast/thumbnail.png","authors":["FrancoisLagier"],"categories":["user-stories"],"date":"2019-08-07T00:00:00.000Z","title":"Serverless：初创企业的理想选择？（CloudForecast 案例分析）","description":"CloudForecast 是 2018 年成立的一家独立初创企业，本文将介绍他们决定选择 Serverless 的原因。","authorslink":["https://serverless.com/author/francoislagier/"],"translators":["Aceyclee"],"translatorslink":["zhihu.com/people/Aceyclee"],"tags":null,"keywords":null,"outdated":null},"wordCount":{"words":211,"sentences":29,"paragraphs":29},"fileAbsolutePath":"/opt/build/repo/content/blog/2019-08-07-serverless-for-startups.md","fields":{"slug":"/blog/2019-08-07-serverless-for-startups/","keywords":["serverless","云函数","serverless","函数","Serverless","utm","Framework","blog","CloudForecast","cloudforecast"]}}},{"node":{"id":"97450b07-658b-5207-8216-1c7b9b51b115","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020114/1578988490344-v2-8b2cd2c5275aa2c5a3c5083a148a7a9f_1200x500.jpg","authors":["Anycodes"],"categories":["user-stories"],"date":"2019-09-01T00:00:00.000Z","title":"如何通过 Serverless 与自然语言处理，让搜索引擎「看」到你的博客","description":"Serverless 与自然语言处理结合的一个小应用","authorslink":["https://www.zhihu.com/people/liuyu-43-97"],"translators":null,"translatorslink":null,"tags":["个人博客","serverless"],"keywords":"Serverless 自然语言处理","outdated":null},"wordCount":{"words":106,"sentences":34,"paragraphs":34},"fileAbsolutePath":"/opt/build/repo/content/blog/2019-09-01-search-engine-blog.md","fields":{"slug":"/blog/2019-09-01-search-engine-blog/","keywords":["serverless","云函数","keywords","serverlesscloud","summary"]}}},{"node":{"id":"ae4fd2f8-515c-5aec-b584-38427ef33f7e","frontmatter":{"thumbnail":"https://img.serverlesscloud.cn/2020114/1578989800047-part-00492-780.jpg","authors":["Anycodes"],"categories":["guides-and-tutorials","user-stories"],"date":"2019-09-16T00:00:00.000Z","title":"突破传统 OJ 瓶颈，「判题姬」接入云函数","description":"通过 Serverless 实现在线编程","authorslink":["https://www.zhihu.com/people/liuyu-43-97"],"translators":null,"translatorslink":null,"tags":["在线编程","云函数"],"keywords":"Serverless 在线编程,Serverless OJ","outdated":null},"wordCount":{"words":169,"sentences":30,"paragraphs":30},"fileAbsolutePath":"/opt/build/repo/content/blog/2019-09-16-online-Judge.md","fields":{"slug":"/blog/2019-09-16-online-Judge/","keywords":["python","serverless","云函数","代码","函数","serverless"]}}}],"totalCount":64}},"pageContext":{"isCreatedByStatefulCreatePages":false,"blogId":"caebf2fd-ebd7-5972-a908-0ac7d00c5bd8","previousBlogId":"a76c7573-dd0d-58ca-b60e-10642b13690f","nextBlogId":"7cdbd3fc-5cc1-50eb-a9ac-21fb5de1cfeb","categories":["user-stories"]}}}