CINXE.COM
Do you slice your training data to evaluate how well it generalizes for different subsets of your data? - General Discussion - Build with Google AI
<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"> <title>Do you slice your training data to evaluate how well it generalizes for different subsets of your data? - General Discussion - Build with Google AI</title> <meta name="description" content="How deep do you get into evaluating your model performance? Do you slice your data and evaluate the slices? Do you try to measure fairness or accuracy for different subsets of your users or use-cases?"> <meta name="generator" content="Discourse 3.4.0.beta3-dev - https://github.com/discourse/discourse version d880db3b7b748901366d0c94f58dada9096f967f"> <link rel="icon" type="image/png" href="https://canada1.discourse-cdn.com/googleaitrial/optimized/2X/8/8bfe64fc593eb7baba8df149ebba4457c16ca1f9_2_32x32.png"> <link rel="apple-touch-icon" type="image/png" href="https://canada1.discourse-cdn.com/googleaitrial/optimized/2X/8/8bfe64fc593eb7baba8df149ebba4457c16ca1f9_2_180x180.png"> <meta name="theme-color" media="all" content="#1f1f1f"> <meta name="viewport" content="width=device-width, initial-scale=1.0, minimum-scale=1.0, user-scalable=yes, viewport-fit=cover"> <link rel="canonical" href="https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762" /> <link rel="search" type="application/opensearchdescription+xml" href="https://discuss.ai.google.dev/opensearch.xml" title="Build with Google AI Search"> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/color_definitions_google-ai-for-developers_8_2_9664c403088a1d589ded99d7cdbbd8f338343719.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" class="light-scheme"/> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/checklist_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="checklist" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-ai_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-ai" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-akismet_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-akismet" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-cakeday_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-cakeday" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-data-explorer_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-data-explorer" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-details_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-details" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-lazy-videos_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-lazy-videos" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-local-dates_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-local-dates" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-narrative-bot_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-narrative-bot" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-policy_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-policy" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-presence_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-presence" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-reactions_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-reactions" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-solved_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-solved" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-templates_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-templates" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-topic-voting_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-topic-voting" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/footnote_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="footnote" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/hosted-site_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="hosted-site" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/poll_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="poll" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/spoiler-alert_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="spoiler-alert" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-ai_desktop_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-ai_desktop" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-reactions_desktop_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-reactions_desktop" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/discourse-topic-voting_desktop_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="discourse-topic-voting_desktop" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/poll_desktop_5a2434b361468bc0f0245e49d5dee554eebac4e3.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="poll_desktop" /> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_theme_4_7896a10e11b78b3457576dae80aa6a4f54f8c407.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop_theme" data-theme-id="4" data-theme-name="discourse header search"/> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_theme_3_8fbb151033f3941d27908950c0e87f8fb39a38a6.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop_theme" data-theme-id="3" data-theme-name="discourse-material-icons"/> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_theme_9_f0575d150ab7e99c44052a5015695044e12c5b03.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop_theme" data-theme-id="9" data-theme-name="global notice custom css"/> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_theme_8_afb04a60a9c25410f7b14d8fa0f3ae4ed9169b51.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop_theme" data-theme-id="8" data-theme-name="temp nav fixes"/> <link href="https://yyz1.discourse-cdn.com/googleaitrial/stylesheets/desktop_theme_2_6b14ef109bd30716a9d1b973997ba1349dda629b.css?__ws=discuss.ai.google.dev" media="all" rel="stylesheet" data-target="desktop_theme" data-theme-id="2" data-theme-name="google ai"/> <link href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:opsz,wght,FILL,GRAD@20..48,100..400,0..1,0&family=Roboto+Mono:ital,wght@0,100..700;1,100..700&family=Roboto:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap" rel="stylesheet"> <link rel="alternate nofollow" type="application/rss+xml" title="RSS feed of 'Do you slice your training data to evaluate how well it generalizes for different subsets of your data?'" href="https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762.rss" /> <meta property="og:site_name" content="Build with Google AI" /> <meta property="og:type" content="website" /> <meta name="twitter:card" content="summary" /> <meta name="twitter:image" content="https://canada1.discourse-cdn.com/googleaitrial/original/2X/8/8bfe64fc593eb7baba8df149ebba4457c16ca1f9.png" /> <meta property="og:image" content="https://canada1.discourse-cdn.com/googleaitrial/original/2X/8/8bfe64fc593eb7baba8df149ebba4457c16ca1f9.png" /> <meta property="og:url" content="https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762" /> <meta name="twitter:url" content="https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762" /> <meta property="og:title" content="Do you slice your training data to evaluate how well it generalizes for different subsets of your data?" /> <meta name="twitter:title" content="Do you slice your training data to evaluate how well it generalizes for different subsets of your data?" /> <meta property="og:description" content="How deep do you get into evaluating your model performance? Do you slice your data and evaluate the slices? Do you try to measure fairness or accuracy for different subsets of your users or use-cases?" /> <meta name="twitter:description" content="How deep do you get into evaluating your model performance? Do you slice your data and evaluate the slices? Do you try to measure fairness or accuracy for different subsets of your users or use-cases?" /> <meta property="og:article:section" content="TensorFlow" /> <meta property="og:article:section:color" content="f66f00" /> <meta property="og:article:section" content="General Discussion" /> <meta property="og:article:section:color" content="f2a346" /> <meta property="og:article:tag" content="community_support" /> <meta property="og:article:tag" content="tfx" /> <meta property="og:article:tag" content="ml_ops" /> <meta name="twitter:label1" value="Reading time" /> <meta name="twitter:data1" value="1 mins 🕑" /> <meta name="twitter:label2" value="Likes" /> <meta name="twitter:data2" value="2 ❤" /> <meta property="article:published_time" content="2021-02-09T01:05:12+00:00" /> <meta property="og:ignore_canonical" content="true" /> </head> <body class="crawler browser-update"> <header> <a href="/"> Build with Google AI </a> </header> <div id="main-outlet" class="wrap" role="main"> <div id="topic-title"> <h1> <a href="/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762">Do you slice your training data to evaluate how well it generalizes for different subsets of your data?</a> </h1> <div class="topic-category" itemscope itemtype="http://schema.org/BreadcrumbList"> <span itemprop="itemListElement" itemscope itemtype="http://schema.org/ListItem"> <a href="/c/tensorflow/general-discussion-6/37" class="badge-wrapper bullet" itemprop="item"> <span class='badge-category-bg' style='background-color: #f66f00'></span> <span class='badge-category clear-badge'> <span class='category-name' itemprop='name'>TensorFlow</span> </span> </a> <meta itemprop="position" content="1" /> </span> <span itemprop="itemListElement" itemscope itemtype="http://schema.org/ListItem"> <a href="/c/tensorflow/general-discussion-6/37" class="badge-wrapper bullet" itemprop="item"> <span class='badge-category-bg' style='background-color: #f2a346'></span> <span class='badge-category clear-badge'> <span class='category-name' itemprop='name'>General Discussion</span> </span> </a> <meta itemprop="position" content="2" /> </span> </div> <div class="topic-category"> <div class='discourse-tags list-tags'> <a href='https://discuss.ai.google.dev/tag/community_support' class='discourse-tag' rel="tag">community_support</a>, <a href='https://discuss.ai.google.dev/tag/tfx' class='discourse-tag' rel="tag">tfx</a>, <a href='https://discuss.ai.google.dev/tag/ml_ops' class='discourse-tag' rel="tag">ml_ops</a> </div> </div> </div> <div itemscope itemtype='http://schema.org/DiscussionForumPosting'> <meta itemprop='headline' content='Do you slice your training data to evaluate how well it generalizes for different subsets of your data?'> <link itemprop='url' href='https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762'> <meta itemprop='datePublished' content='2021-02-09T01:05:12Z'> <meta itemprop='articleSection' content='General Discussion'> <meta itemprop='keywords' content='community_support, tfx, ml_ops'> <div itemprop='publisher' itemscope itemtype="http://schema.org/Organization"> <meta itemprop='name' content='Build with Google AI'> <div itemprop='logo' itemscope itemtype="http://schema.org/ImageObject"> <meta itemprop='url' content='https://canada1.discourse-cdn.com/googleaitrial/original/1X/9c9b743566b5ef0d0701ebba72bf83038f42ea0b.png'> </div> </div> <div id='post_1' class='topic-body crawler-post'> <div class='crawler-post-meta'> <span class="creator" itemprop="author" itemscope itemtype="http://schema.org/Person"> <a itemprop="url" href='https://discuss.ai.google.dev/u/robertcrowe'><span itemprop='name'>robertcrowe</span></a> </span> <link itemprop="mainEntityOfPage" href="https://discuss.ai.google.dev/t/do-you-slice-your-training-data-to-evaluate-how-well-it-generalizes-for-different-subsets-of-your-data/29762"> <span class="crawler-post-infos"> <time datetime='2021-02-09T01:05:12Z' class='post-time'> February 9, 2021, 1:05am </time> <meta itemprop='dateModified' content='2024-11-21T04:42:50Z'> <span itemprop='position'>1</span> </span> </div> <div class='post' itemprop='text'> <p>How deep do you get into evaluating your model performance? Do you slice your data and evaluate the slices? Do you try to measure fairness or accuracy for different subsets of your users or use-cases?</p> </div> <div itemprop="interactionStatistic" itemscope itemtype="http://schema.org/InteractionCounter"> <meta itemprop="interactionType" content="http://schema.org/LikeAction"/> <meta itemprop="userInteractionCount" content="2" /> <span class='post-likes'>2 Likes</span> </div> </div> </div> <div id="related-topics" class="more-topics__list " role="complementary" aria-labelledby="related-topics-title"> <h3 id="related-topics-title" class="more-topics__list-title"> Related topics </h3> <div class="topic-list-container" itemscope itemtype='http://schema.org/ItemList'> <meta itemprop='itemListOrder' content='http://schema.org/ItemListOrderDescending'> <table class='topic-list'> <thead> <tr> <th>Topic</th> <th></th> <th class="replies">Replies</th> <th class="views">Views</th> <th>Activity</th> </tr> </thead> <tbody> <tr class="topic-list-item" id="topic-list-item-26395"> <td class="main-link" itemprop='itemListElement' itemscope itemtype='http://schema.org/ListItem'> <meta itemprop='position' content='1'> <span class="link-top-line"> <a itemprop='url' href='https://discuss.ai.google.dev/t/fx-toy-project-bert-as-a-service/26395' class='title raw-link raw-topic-link'>FX toy project (BERT as a service)</a> </span> <div class="link-bottom-line"> <a href='/c/tensorflow/show-tell/30' class='badge-wrapper bullet'> <span class='badge-category-bg' style='background-color: #5bbae1'></span> <span class='badge-category clear-badge'> <span class='category-name'>Show and Tell</span> </span> </a> <div class="discourse-tags"> <a href='https://discuss.ai.google.dev/tag/tfx' class='discourse-tag'>tfx</a> , <a href='https://discuss.ai.google.dev/tag/gcp' class='discourse-tag'>gcp</a> , <a href='https://discuss.ai.google.dev/tag/learning' class='discourse-tag'>learning</a> , <a href='https://discuss.ai.google.dev/tag/education' class='discourse-tag'>education</a> </div> </div> </td> <td class="replies"> <span class='posts' title='posts'>2</span> </td> <td class="views"> <span class='views' title='views'>1725</span> </td> <td> June 28, 2021 </td> </tr> <tr class="topic-list-item" id="topic-list-item-26183"> <td class="main-link" itemprop='itemListElement' itemscope itemtype='http://schema.org/ListItem'> <meta itemprop='position' content='2'> <span class="link-top-line"> <a itemprop='url' href='https://discuss.ai.google.dev/t/do-you-have-any-models-in-production-or-do-you-plan-to-have-any/26183' class='title raw-link raw-topic-link'>Do you have any models in production, or do you plan to have any?</a> </span> <div class="link-bottom-line"> <a href='/c/tensorflow/general-discussion-6/37' class='badge-wrapper bullet'> <span class='badge-category-bg' style='background-color: #f2a346'></span> <span class='badge-category clear-badge'> <span class='category-name'>General Discussion</span> </span> </a> <div class="discourse-tags"> <a href='https://discuss.ai.google.dev/tag/tfx' class='discourse-tag'>tfx</a> , <a href='https://discuss.ai.google.dev/tag/ml_ops' class='discourse-tag'>ml_ops</a> </div> </div> </td> <td class="replies"> <span class='posts' title='posts'>6</span> </td> <td class="views"> <span class='views' title='views'>2776</span> </td> <td> July 1, 2021 </td> </tr> <tr class="topic-list-item" id="topic-list-item-32407"> <td class="main-link" itemprop='itemListElement' itemscope itemtype='http://schema.org/ListItem'> <meta itemprop='position' content='3'> <span class="link-top-line"> <a itemprop='url' href='https://discuss.ai.google.dev/t/tfx-model-monitoring/32407' class='title raw-link raw-topic-link'>TFX Model Monitoring</a> </span> <div class="link-bottom-line"> <a href='/c/tensorflow/general-discussion-6/37' class='badge-wrapper bullet'> <span class='badge-category-bg' style='background-color: #f2a346'></span> <span class='badge-category clear-badge'> <span class='category-name'>General Discussion</span> </span> </a> <div class="discourse-tags"> <a href='https://discuss.ai.google.dev/tag/tfx' class='discourse-tag'>tfx</a> , <a href='https://discuss.ai.google.dev/tag/ml_ops' class='discourse-tag'>ml_ops</a> </div> </div> </td> <td class="replies"> <span class='posts' title='posts'>2</span> </td> <td class="views"> <span class='views' title='views'>2158</span> </td> <td> June 2, 2021 </td> </tr> <tr class="topic-list-item" id="topic-list-item-29208"> <td class="main-link" itemprop='itemListElement' itemscope itemtype='http://schema.org/ListItem'> <meta itemprop='position' content='4'> <span class="link-top-line"> <a itemprop='url' href='https://discuss.ai.google.dev/t/performance-overhead-of-tensorflow-custom-ops/29208' class='title raw-link raw-topic-link'>Performance overhead of tensorflow custom ops</a> </span> <div class="link-bottom-line"> <a href='/c/tensorflow/general-discussion-6/37' class='badge-wrapper bullet'> <span class='badge-category-bg' style='background-color: #f2a346'></span> <span class='badge-category clear-badge'> <span class='category-name'>General Discussion</span> </span> </a> <div class="discourse-tags"> <a href='https://discuss.ai.google.dev/tag/serving' class='discourse-tag'>serving</a> , <a href='https://discuss.ai.google.dev/tag/help_request' class='discourse-tag'>help_request</a> , <a href='https://discuss.ai.google.dev/tag/tfcore' class='discourse-tag'>tfcore</a> </div> </div> </td> <td class="replies"> <span class='posts' title='posts'>1</span> </td> <td class="views"> <span class='views' title='views'>1325</span> </td> <td> October 29, 2021 </td> </tr> <tr class="topic-list-item" id="topic-list-item-28425"> <td class="main-link" itemprop='itemListElement' itemscope itemtype='http://schema.org/ListItem'> <meta itemprop='position' content='5'> <span class="link-top-line"> <a itemprop='url' href='https://discuss.ai.google.dev/t/some-impressive-tutorial-to-learning-tfx/28425' class='title raw-link raw-topic-link'>Some impressive tutorial to learning TFX</a> </span> <div class="link-bottom-line"> <a href='/c/tensorflow/general-discussion-6/37' class='badge-wrapper bullet'> <span class='badge-category-bg' style='background-color: #f2a346'></span> <span class='badge-category clear-badge'> <span class='category-name'>General Discussion</span> </span> </a> <div class="discourse-tags"> <a href='https://discuss.ai.google.dev/tag/tfx' class='discourse-tag'>tfx</a> , <a href='https://discuss.ai.google.dev/tag/learning' class='discourse-tag'>learning</a> , <a href='https://discuss.ai.google.dev/tag/education' class='discourse-tag'>education</a> </div> </div> </td> <td class="replies"> <span class='posts' title='posts'>2</span> </td> <td class="views"> <span class='views' title='views'>2115</span> </td> <td> May 23, 2021 </td> </tr> </tbody> </table> </div> </div> </div> <footer class="container wrap"> <nav class='crawler-nav'> <ul> <li itemscope itemtype='http://schema.org/SiteNavigationElement'> <span itemprop='name'> <a href='/' itemprop="url">Home </a> </span> </li> <li itemscope itemtype='http://schema.org/SiteNavigationElement'> <span itemprop='name'> <a href='/categories' itemprop="url">Categories </a> </span> </li> <li itemscope itemtype='http://schema.org/SiteNavigationElement'> <span itemprop='name'> <a href='/guidelines' itemprop="url">Guidelines </a> </span> </li> <li itemscope itemtype='http://schema.org/SiteNavigationElement'> <span itemprop='name'> <a href='https://policies.google.com/terms' itemprop="url">Terms of Service </a> </span> </li> <li itemscope itemtype='http://schema.org/SiteNavigationElement'> <span itemprop='name'> <a href='https://policies.google.com/privacy' itemprop="url">Privacy Policy </a> </span> </li> </ul> </nav> <p class='powered-by-link'>Powered by <a href="https://www.discourse.org">Discourse</a>, best viewed with JavaScript enabled</p> </footer> <div class="buorg"><div>Unfortunately, <a href="https://www.discourse.org/faq/#browser">your browser is unsupported</a>. Please <a href="https://browsehappy.com">switch to a supported browser</a> to view rich content, log in and reply.</div></div> </body> </html>