767 lines
No EOL
29 KiB
HTML
767 lines
No EOL
29 KiB
HTML
|
|
<!doctype html>
|
|
<html lang="en" class="no-js">
|
|
<head>
|
|
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width,initial-scale=1">
|
|
|
|
<meta name="description" content="GreatAI helps you easily transform your prototype AI code into production-ready software.">
|
|
|
|
|
|
<meta name="author" content="András Schmelczer">
|
|
|
|
|
|
<link rel="icon" href="../media/favicon.ico">
|
|
<meta name="generator" content="mkdocs-1.3.0, mkdocs-material-8.3.9">
|
|
|
|
|
|
|
|
<title>Train and deploy a SOTA model - GreatAI documentation</title>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/main.1d29e8d0.min.css">
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/palette.cbb835fc.min.css">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
|
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
|
|
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
|
|
|
|
<script>__md_scope=new URL("..",location),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
|
|
|
|
|
|
|
|
|
|
|
</head>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="" data-md-color-accent="">
|
|
|
|
|
|
|
|
<script>var palette=__md_get("__palette");if(palette&&"object"==typeof palette.color)for(var key of Object.keys(palette.color))document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
|
|
|
|
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
|
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
|
<label class="md-overlay" for="__drawer"></label>
|
|
<div data-md-component="skip">
|
|
|
|
|
|
<a href="#train-and-deploy-a-sota-model" class="md-skip">
|
|
Skip to content
|
|
</a>
|
|
|
|
</div>
|
|
<div data-md-component="announce">
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<header class="md-header" data-md-component="header">
|
|
<nav class="md-header__inner md-grid" aria-label="Header">
|
|
<a href=".." title="GreatAI documentation" class="md-header__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
|
|
|
|
</a>
|
|
<label class="md-header__button md-icon" for="__drawer">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
|
|
</label>
|
|
<div class="md-header__title" data-md-component="header-title">
|
|
<div class="md-header__ellipsis">
|
|
<div class="md-header__topic">
|
|
<span class="md-ellipsis">
|
|
GreatAI documentation
|
|
</span>
|
|
</div>
|
|
<div class="md-header__topic" data-md-component="header-topic">
|
|
<span class="md-ellipsis">
|
|
|
|
Train and deploy a SOTA model
|
|
|
|
</span>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<form class="md-header__option" data-md-component="palette">
|
|
|
|
|
|
|
|
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="" data-md-color-accent="" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_1">
|
|
|
|
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_2" hidden>
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
|
</label>
|
|
|
|
|
|
|
|
|
|
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="" data-md-color-accent="" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_2">
|
|
|
|
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_1" hidden>
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12c0-2.42-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12 20 8.69Z"/></svg>
|
|
</label>
|
|
|
|
|
|
</form>
|
|
|
|
|
|
|
|
<label class="md-header__button md-icon" for="__search">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
|
</label>
|
|
<div class="md-search" data-md-component="search" role="dialog">
|
|
<label class="md-search__overlay" for="__search"></label>
|
|
<div class="md-search__inner" role="search">
|
|
<form class="md-search__form" name="search">
|
|
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
|
<label class="md-search__icon md-icon" for="__search">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
|
|
</label>
|
|
<nav class="md-search__options" aria-label="Search">
|
|
|
|
<button type="reset" class="md-search__icon md-icon" aria-label="Clear" tabindex="-1">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
|
|
</button>
|
|
</nav>
|
|
|
|
</form>
|
|
<div class="md-search__output">
|
|
<div class="md-search__scrollwrap" data-md-scrollfix>
|
|
<div class="md-search-result" data-md-component="search-result">
|
|
<div class="md-search-result__meta">
|
|
Initializing search
|
|
</div>
|
|
<ol class="md-search-result__list"></ol>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<div class="md-header__source">
|
|
<a href="https://github.com/schmelczer/great-ai" title="Go to repository" class="md-source" data-md-component="source">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
|
</div>
|
|
<div class="md-source__repository">
|
|
schmelczer/great-ai
|
|
</div>
|
|
</a>
|
|
</div>
|
|
|
|
</nav>
|
|
|
|
</header>
|
|
|
|
<div class="md-container" data-md-component="container">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<main class="md-main" data-md-component="main">
|
|
<div class="md-main__inner md-grid">
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
|
<label class="md-nav__title" for="__drawer">
|
|
<a href=".." title="GreatAI documentation" class="md-nav__button md-logo" aria-label="GreatAI documentation" data-md-component="logo">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z"/></svg>
|
|
|
|
</a>
|
|
GreatAI documentation
|
|
</label>
|
|
|
|
<div class="md-nav__source">
|
|
<a href="https://github.com/schmelczer/great-ai" title="Go to repository" class="md-source" data-md-component="source">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
|
</div>
|
|
<div class="md-source__repository">
|
|
schmelczer/great-ai
|
|
</div>
|
|
</a>
|
|
</div>
|
|
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href=".." class="md-nav__link">
|
|
Overview
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_2" type="checkbox" id="__nav_2" checked>
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_2">
|
|
Tutorial
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" aria-label="Tutorial" data-md-level="1">
|
|
<label class="md-nav__title" for="__nav_2">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Tutorial
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--active">
|
|
|
|
<input class="md-nav__toggle md-toggle" data-md-toggle="toc" type="checkbox" id="__toc">
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__link md-nav__link--active" for="__toc">
|
|
Train and deploy a SOTA model
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<a href="./" class="md-nav__link md-nav__link--active">
|
|
Train and deploy a SOTA model
|
|
</a>
|
|
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#overview" class="md-nav__link">
|
|
Overview
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#objectives" class="md-nav__link">
|
|
Objectives
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#summary" class="md-nav__link">
|
|
Summary
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Summary">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#the-training-notebook" class="md-nav__link">
|
|
The training notebook
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#the-deployment-notebook" class="md-nav__link">
|
|
The deployment notebook
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="train/" class="md-nav__link">
|
|
Train your model
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="deploy/" class="md-nav__link">
|
|
Harden and deploy your app
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_3" type="checkbox" id="__nav_3" >
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_3">
|
|
User Guides
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" aria-label="User Guides" data-md-level="1">
|
|
<label class="md-nav__title" for="__nav_3">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
User Guides
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item md-nav__item--nested">
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_3_1" type="checkbox" id="__nav_3_1" >
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_3_1">
|
|
Simple AI lifecycle with classification
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" aria-label="Simple AI lifecycle with classification" data-md-level="2">
|
|
<label class="md-nav__title" for="__nav_3_1">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Simple AI lifecycle with classification
|
|
</label>
|
|
<ul class="md-nav__list" data-md-scrollfix>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../simple/data/" class="md-nav__link">
|
|
Train a domain classifier on the semantic scholar dataset
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../simple/train/" class="md-nav__link">
|
|
Train a domain classifier on the semantic scholar dataset
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../simple/deploy/" class="md-nav__link">
|
|
Train a domain classifier on the semantic scholar dataset
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../reference/" class="md-nav__link">
|
|
Reference
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../explanation/" class="md-nav__link">
|
|
Explanation
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
|
<div class="md-sidebar__scrollwrap">
|
|
<div class="md-sidebar__inner">
|
|
|
|
|
|
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<label class="md-nav__title" for="__toc">
|
|
<span class="md-nav__icon md-icon"></span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#overview" class="md-nav__link">
|
|
Overview
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#objectives" class="md-nav__link">
|
|
Objectives
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#summary" class="md-nav__link">
|
|
Summary
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="Summary">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#the-training-notebook" class="md-nav__link">
|
|
The training notebook
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#the-deployment-notebook" class="md-nav__link">
|
|
The deployment notebook
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<div class="md-content" data-md-component="content">
|
|
<article class="md-content__inner md-typeset">
|
|
|
|
|
|
|
|
|
|
|
|
<a href="https://github.com/schmelczer/great-ai/edit/main/docs/tutorial/index.md" title="Edit this page" class="md-content__button md-icon">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25Z"/></svg>
|
|
</a>
|
|
|
|
|
|
|
|
<h1 id="train-and-deploy-a-sota-model">Train and deploy a SOTA model<a class="headerlink" href="#train-and-deploy-a-sota-model" title="Permanent link">#</a></h1>
|
|
<h2 id="overview">Overview<a class="headerlink" href="#overview" title="Permanent link">#</a></h2>
|
|
<p>You are going to train a field of study (domain) classifier for scientific sentences. The exact task was proposed by the <a href="https://arxiv.org/abs/1903.10676">SciBERT paper</a> in which SciBERT <a href="https://paperswithcode.com/sota/sentence-classification-on-paper-field">achieved an F1-score of 0.6571</a>. We are going to outperform it using a trivial text classification model: a <a href="https://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html">Linear SVM</a>.</p>
|
|
<p>We use the same synthetic dataset derived from the <a href="https://www.microsoft.com/en-us/research/project/microsoft-academic-graph/">Microsoft Academic Graph</a>. The dataset is <a href="https://github.com/allenai/scibert/tree/master/data/text_classification/mag">available here</a>.</p>
|
|
<h2 id="objectives">Objectives<a class="headerlink" href="#objectives" title="Permanent link">#</a></h2>
|
|
<ol>
|
|
<li>You will see how the <code>great_ai.utilities</code> can integrate into your Data Science workflow.</li>
|
|
<li>You will use <code>great_ai.large_file</code> to version and store your trained model</li>
|
|
<li>You will use <code>GreatAI</code> to prepare your model for a robust and responsible deployment</li>
|
|
</ol>
|
|
<div class="admonition success">
|
|
<p class="admonition-title">Success</p>
|
|
<p>You are ready to start the tutorial. Feel free to come back to the <a href="#summary">summary</a> section once you're finished.</p>
|
|
</div>
|
|
<div style="display: flex; justify-content: space-evenly;">
|
|
<p><a class="md-button md-button--primary" href="train/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc.--><path d="M160 80c0-26.51 21.5-48 48-48h32c26.5 0 48 21.49 48 48v352c0 26.5-21.5 48-48 48h-32c-26.5 0-48-21.5-48-48V80zM0 272c0-26.5 21.49-48 48-48h32c26.5 0 48 21.5 48 48v160c0 26.5-21.5 48-48 48H48c-26.51 0-48-21.5-48-48V272zM400 96c26.5 0 48 21.5 48 48v288c0 26.5-21.5 48-48 48h-32c-26.5 0-48-21.5-48-48V144c0-26.5 21.5-48 48-48h32z"/></svg></span> Train it</a></p>
|
|
<p><a class="md-button md-button--secondary" href="deploy/"><span class="twemoji"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M6 20a6 6 0 0 1-6-6c0-3.09 2.34-5.64 5.35-5.96A7.496 7.496 0 0 1 12 4a7.5 7.5 0 0 1 7.35 6A5.02 5.02 0 0 1 24 15a5 5 0 0 1-5 5H6M9.09 8.4 4.5 13l4.59 4.6 1.41-1.42L7.32 13l3.18-3.18L9.09 8.4m5.82 0L13.5 9.82 16.68 13l-3.18 3.18 1.41 1.42L19.5 13l-4.59-4.6Z"/></svg></span> Deploy it</a></p>
|
|
</div>
|
|
<h2 id="summary">Summary<a class="headerlink" href="#summary" title="Permanent link">#</a></h2>
|
|
<h3 id="the-training-notebook">The <a href="train/">training notebook</a><a class="headerlink" href="#the-training-notebook" title="Permanent link">#</a></h3>
|
|
<p>We load and preprocess the dataset while relying on <code>great_ai.utilities.clean</code> for the heavy-lifting. Additionally, the preprocessing is parallelised using <code>great_ai.utilities.simple_parallel_map</code>.</p>
|
|
<p>After training and evaluating a model, it is exported using <code>great_ai.save_model</code>.</p>
|
|
<details class="tip">
|
|
<summary>Using the cloud</summary>
|
|
<p>To store your model remotely, you need to set your credentials before calling <code>save_model</code>.</p>
|
|
<p>For example, to use <a href="https://aws.amazon.com/s3/">AWS S3</a>:
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a><span class="kn">from</span> <span class="nn">great_ai.large_file</span> <span class="kn">import</span> <span class="n">LargeFileS3</span>
|
|
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>
|
|
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a><span class="n">LargeFileS3</span><span class="o">.</span><span class="n">configure</span><span class="p">(</span>
|
|
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a> <span class="n">aws_region_name</span><span class="o">=</span><span class="s1">'eu-west-2'</span><span class="p">,</span>
|
|
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a> <span class="n">aws_access_key_id</span><span class="o">=</span><span class="s1">'MY_AWS_ACCESS_KEY'</span><span class="p">,</span>
|
|
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a> <span class="n">aws_secret_access_key</span><span class="o">=</span><span class="s1">'MY_AWS_SECRET_KEY'</span><span class="p">,</span>
|
|
<a id="__codelineno-0-7" name="__codelineno-0-7" href="#__codelineno-0-7"></a> <span class="n">large_files_bucket_name</span><span class="o">=</span><span class="s1">'my_bucket_for_models'</span>
|
|
<a id="__codelineno-0-8" name="__codelineno-0-8" href="#__codelineno-0-8"></a><span class="p">)</span>
|
|
<a id="__codelineno-0-9" name="__codelineno-0-9" href="#__codelineno-0-9"></a>
|
|
<a id="__codelineno-0-10" name="__codelineno-0-10" href="#__codelineno-0-10"></a><span class="kn">from</span> <span class="nn">great_ai</span> <span class="kn">import</span> <span class="n">save_model</span>
|
|
<a id="__codelineno-0-11" name="__codelineno-0-11" href="#__codelineno-0-11"></a>
|
|
<a id="__codelineno-0-12" name="__codelineno-0-12" href="#__codelineno-0-12"></a><span class="n">save_model</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s1">'my-domain-predictor'</span><span class="p">)</span>
|
|
</code></pre></div></p>
|
|
</details>
|
|
<h3 id="the-deployment-notebook">The <a href="deploy/">deployment notebook</a><a class="headerlink" href="#the-deployment-notebook" title="Permanent link">#</a></h3>
|
|
<p>We create an inference function that can be hardened by wrapping it in a <code>great_ai.GreatAI</code> instance.</p>
|
|
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a><span class="kn">from</span> <span class="nn">great_ai</span> <span class="kn">import</span> <span class="n">GreatAI</span><span class="p">,</span> <span class="n">use_model</span>
|
|
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a><span class="kn">from</span> <span class="nn">great_ai.utilities</span> <span class="kn">import</span> <span class="n">clean</span>
|
|
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a>
|
|
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a><span class="nd">@GreatAI</span><span class="o">.</span><span class="n">create</span>
|
|
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a><span class="nd">@use_model</span><span class="p">(</span><span class="s1">'my-domain-predictor'</span><span class="p">)</span> <span class="c1">#(1)</span>
|
|
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a><span class="k">def</span> <span class="nf">predict_domain</span><span class="p">(</span><span class="n">sentence</span><span class="p">,</span> <span class="n">model</span><span class="p">):</span>
|
|
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a> <span class="n">inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">clean</span><span class="p">(</span><span class="n">sentence</span><span class="p">)]</span>
|
|
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a> <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">inputs</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
|
|
</code></pre></div>
|
|
<ol>
|
|
<li><code>@use_model</code> loads and injects your model into the <code>predict_domain</code> function's <code>model</code> argument.
|
|
You can freely reference it knowing that it is always given to the function.</li>
|
|
</ol>
|
|
<p>Finally, we deploy the model, inference function, and the GreatAI wrapping all of these. For that we either use: <code>great-ai deploy.ipynb</code> or build a Docker image.</p>
|
|
|
|
<hr>
|
|
<div class="md-source-file">
|
|
<small>
|
|
|
|
Last update:
|
|
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date">July 9, 2022</span>
|
|
|
|
|
|
</small>
|
|
</div>
|
|
|
|
|
|
|
|
</article>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
</main>
|
|
|
|
<footer class="md-footer">
|
|
|
|
|
|
<nav class="md-footer__inner md-grid" aria-label="Footer" >
|
|
|
|
|
|
<a href=".." class="md-footer__link md-footer__link--prev" aria-label="Previous: Overview" rel="prev">
|
|
<div class="md-footer__button md-icon">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
|
|
</div>
|
|
<div class="md-footer__title">
|
|
<div class="md-ellipsis">
|
|
<span class="md-footer__direction">
|
|
Previous
|
|
</span>
|
|
Overview
|
|
</div>
|
|
</div>
|
|
</a>
|
|
|
|
|
|
|
|
<a href="train/" class="md-footer__link md-footer__link--next" aria-label="Next: Train your model" rel="next">
|
|
<div class="md-footer__title">
|
|
<div class="md-ellipsis">
|
|
<span class="md-footer__direction">
|
|
Next
|
|
</span>
|
|
Train your model
|
|
</div>
|
|
</div>
|
|
<div class="md-footer__button md-icon">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11H4Z"/></svg>
|
|
</div>
|
|
</a>
|
|
|
|
</nav>
|
|
|
|
<div class="md-footer-meta md-typeset">
|
|
<div class="md-footer-meta__inner md-grid">
|
|
<div class="md-copyright">
|
|
|
|
|
|
Made with
|
|
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
|
Material for MkDocs
|
|
</a>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
<div class="md-dialog" data-md-component="dialog">
|
|
<div class="md-dialog__inner md-typeset"></div>
|
|
</div>
|
|
<script id="__config" type="application/json">{"base": "..", "features": ["content.code.annotate", "content.tooltips"], "search": "../assets/javascripts/workers/search.b97dbffb.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.placeholder": "Search", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version.title": "Select version"}}</script>
|
|
|
|
|
|
<script src="../assets/javascripts/bundle.6c7ad80a.min.js"></script>
|
|
|
|
|
|
</body>
|
|
</html> |