{"id":6652,"date":"2022-08-27T09:29:00","date_gmt":"2022-08-27T07:29:00","guid":{"rendered":"https:\/\/joapen.com\/blog\/?p=6652"},"modified":"2022-09-28T09:53:35","modified_gmt":"2022-09-28T07:53:35","slug":"aws-sagemaker","status":"publish","type":"post","link":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/","title":{"rendered":"AWS Sagemaker"},"content":{"rendered":"\n<p>These are some notes about the basis of Sagemaker<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Sagemaker services<\/h2>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">SageMaker Neo<\/span><\/strong> optimizes the trained model and compiles it into an executable. Taking the target hardware where the model will be run as input; the compiler uses a ML model to apply performance optimizations on your model.<\/p>\n\n\n\n<p><span style=\"text-decoration: underline;\"><strong>Ground truth<\/strong><\/span> makes easy to label data. It has templates for common labeling tasks.<\/p>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Rekognition<\/span><\/strong> is an artificial intelligence service that enables the image and facial recognition. It&#8217;s a fully managed service based on deep learning. It offers an API to analyze images.<\/p>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">DeepLens<\/span><\/strong> is a pack composed by: <\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>A video camera with storage and CPU that enables to record videos and run a ML model to detect objects, recognize activity or other things.<\/li><li>A software package that enables the ML learner to build its own solutions based on Sagemaker and Lamda.<\/li><li>Templates available for: object detection, activity recognition, face detection, head pose detection, cat \/ dog&#8230;.<\/li><\/ul>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Polly<\/span><\/strong> translates text information into speech. This is an end to end text-to-speech service.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Right now supports 24 languages with different voices.<\/li><li>Uses Speech Synthesis Markup Language (SSML), which is a XML based mark up language.<\/li><li>You can use it for content creation, test in-game dialogs, generated speech as voice response.<\/li><li>With lexicons we can define a specific dictionary for specific topics.<\/li><li>You can add different rates to the text to speech with the mark up language.<\/li><\/ul>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Lex<\/span><\/strong>  powers Amazon Alexa. This service enables conversational interfaces using voice and text. It includes automatic speech recognition (ASR) and Natural language understanding (NLU) to try to recognize the intent of the speech. Lex is not only available for Alexa, but for any developers that wants to build specific solutions.<\/p>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Transcribe<\/span><\/strong> automatic speech-to-text recognition service. It does just the opposite to Polly. It can be continually trained. The result text contains a &#8220;confidence&#8221; level to enable the manual review for specific cases.<\/p>\n\n\n\n<p><span style=\"text-decoration: underline;\"><strong>Translate<\/strong><\/span> enables the translation of text from one language to other.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>This service encodes the input, take into account the semantic representation, attention mechanism and finally decodes the output.<\/li><li>For instance, Amazon uses it for the customer reviews of products done in different languages.<\/li><li>The service divides the text into paragraphs. It uses a neural network model.<\/li><\/ul>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Comprehend<\/span><\/strong> is a natural-language processing (NLP) service that uses machine learning to uncover valuable insights and connections in text. If you give a sentence, it can provide you some of these capabilities:<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Sentiment detection (positive \/ negative)<\/li><li>Entities (organization, location, date, person&#8230;)<\/li><li>Language detection<\/li><li>Key phrases<\/li><li>Topic modeling<\/li><\/ul>\n\n\n\n<p>Some real examples: voice of customer analytics, semantic search, knowledge management \/ discovery.<\/p>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Comprehend medical<\/span><\/strong> focused on the structure and extract valuable patient-care information. For a medical document, comprehend medical highlight key phrases and words that should be noticed by the reader.<\/p>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Forecast<\/span><\/strong> is the service that predicts future points in a time series based on historical data.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Incorporate additional inputs that enable to improve the accuracy of the forecasted results.<\/li><li>Automates feature engineering, algorithm selection and model tuning.<\/li><li>Build on top of Sagemaker, it enables to incorporate algorithms from Sagemaker.<\/li><li><\/li><\/ul>\n\n\n\n<p><span style=\"text-decoration: underline;\"><strong>Elastic Inference (EI)<\/strong><\/span> Inference is run more frequently and the number of executions can be a high consumer in terms of cost. Elastic inference works on the optimization of the inference process, providing a cost saving point for the execution of the models in production.<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>EI lowers inference costs by up to 75%<\/li><\/ul>\n\n\n\n<p><strong><span style=\"text-decoration: underline;\">Marketplace, Machine Learning section<\/span><\/strong>, this section of <a href=\"https:\/\/aws.amazon.com\/marketplace\/\" target=\"_blank\" rel=\"noreferrer noopener\">AWS marketplace<\/a> offers ready to use algorithms used by other users (free and paid).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking the target hardware where the model will be run as input; the compiler uses a ML model to apply performance optimizations on your model. Ground truth makes easy to label data. &#8230; <a title=\"AWS Sagemaker\" class=\"read-more\" href=\"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/\" aria-label=\"Read more about AWS Sagemaker\">Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[66,151],"tags":[],"class_list":["post-6652","post","type-post","status-publish","format-standard","hentry","category-aws","category-machine-learning"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>AWS Sagemaker -<\/title>\n<meta name=\"description\" content=\"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AWS Sagemaker -\" \/>\n<meta property=\"og:description\" content=\"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects\" \/>\n<meta property=\"og:url\" content=\"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/\" \/>\n<meta property=\"og:site_name\" content=\"joapen projects\" \/>\n<meta property=\"article:published_time\" content=\"2022-08-27T07:29:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-09-28T07:53:35+00:00\" \/>\n<meta name=\"author\" content=\"joapen\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"joapen\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/\"},\"author\":{\"name\":\"joapen\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"headline\":\"AWS Sagemaker\",\"datePublished\":\"2022-08-27T07:29:00+00:00\",\"dateModified\":\"2022-09-28T07:53:35+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/\"},\"wordCount\":582,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"articleSection\":[\"AWS\",\"Machine Learning\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/\",\"url\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/\",\"name\":\"AWS Sagemaker -\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#website\"},\"datePublished\":\"2022-08-27T07:29:00+00:00\",\"dateModified\":\"2022-09-28T07:53:35+00:00\",\"description\":\"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/2022\\\/08\\\/27\\\/aws-sagemaker\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/joapen.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AWS Sagemaker\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/joapen.com\\\/blog\\\/\",\"name\":\"joapen projects\",\"description\":\"Just a place to write\",\"publisher\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/joapen.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\",\"name\":\"joapen\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"url\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"contentUrl\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"width\":400,\"height\":400,\"caption\":\"joapen\"},\"logo\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\"},\"sameAs\":[\"http:\\\/\\\/www.joapen.com\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AWS Sagemaker -","description":"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/","og_locale":"en_US","og_type":"article","og_title":"AWS Sagemaker -","og_description":"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects","og_url":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/","og_site_name":"joapen projects","article_published_time":"2022-08-27T07:29:00+00:00","article_modified_time":"2022-09-28T07:53:35+00:00","author":"joapen","twitter_misc":{"Written by":"joapen","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/#article","isPartOf":{"@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/"},"author":{"name":"joapen","@id":"https:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"headline":"AWS Sagemaker","datePublished":"2022-08-27T07:29:00+00:00","dateModified":"2022-09-28T07:53:35+00:00","mainEntityOfPage":{"@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/"},"wordCount":582,"commentCount":0,"publisher":{"@id":"https:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"articleSection":["AWS","Machine Learning"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/","url":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/","name":"AWS Sagemaker -","isPartOf":{"@id":"https:\/\/joapen.com\/blog\/#website"},"datePublished":"2022-08-27T07:29:00+00:00","dateModified":"2022-09-28T07:53:35+00:00","description":"These are some notes about the basis of Sagemaker Sagemaker services SageMaker Neo optimizes the trained model and compiles it into an executable. Taking - joapen projects","breadcrumb":{"@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/joapen.com\/blog\/2022\/08\/27\/aws-sagemaker\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/joapen.com\/blog\/"},{"@type":"ListItem","position":2,"name":"AWS Sagemaker"}]},{"@type":"WebSite","@id":"https:\/\/joapen.com\/blog\/#website","url":"https:\/\/joapen.com\/blog\/","name":"joapen projects","description":"Just a place to write","publisher":{"@id":"https:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/joapen.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217","name":"joapen","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","url":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","contentUrl":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","width":400,"height":400,"caption":"joapen"},"logo":{"@id":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg"},"sameAs":["http:\/\/www.joapen.com"]}]}},"_links":{"self":[{"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/6652","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/comments?post=6652"}],"version-history":[{"count":6,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/6652\/revisions"}],"predecessor-version":[{"id":6671,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/6652\/revisions\/6671"}],"wp:attachment":[{"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/media?parent=6652"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/categories?post=6652"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/tags?post=6652"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}