{"id":9985,"date":"2024-06-21T10:46:25","date_gmt":"2024-06-21T18:46:25","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=9985"},"modified":"2025-04-24T17:02:45","modified_gmt":"2025-04-24T17:02:45","slug":"computer-vision-libraries-open-source","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/","title":{"rendered":"5 Open-Source Computer Vision Libraries You Need to Know"},"content":{"rendered":"\n<figure class=\"wp-block-image aligncenter wp-image-9995 size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1200\" height=\"798\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg\" alt=\"side view of a pro baseball player mid-swing with the catcher behind him and object detection labels demonstrating the use of Ultralytics YOLOv8 computer vision model\" class=\"wp-image-9995\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg 1200w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics--300x200.jpeg 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics--1024x681.jpeg 1024w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics--768x511.jpeg 768w\" sizes=\"auto, (max-width: 1200px) 100vw, 1200px\" \/><figcaption class=\"wp-element-caption\">Object detection <a href=\"https:\/\/github.com\/dme-compunet\/YOLOv8\/blob\/main\/Assets\/seg-demo.jpg\">example asset<\/a> from the YOLOv8 open-source computer vision library<\/figcaption><\/figure>\n\n\n\n<p>Leveraging machine learning for computer vision use cases has revolutionized a myriad of industries by enabling machines to interpret and respond to visual data. From enhancing medical diagnostics with precise imaging techniques to powering autonomous vehicles with real-time object detection and navigation, the applications of computer vision models are vast and diverse.<!-- notionvc: 02c99bf1-eab2-45d0-b180-57ccbecf7a54 --><\/p>\n\n\n\n<p>Building state-of-the-art CV models for your specific use case can be daunting task. Luckily, the open source community has been creating a plethora of developer-friendly libraries that make it very easy to start training a model on your custom dataset. Here\u2019s a list of 5 open-source computer vision repositories to familiarize yourself with!<!-- notionvc: 43280443-ba94-42de-8e45-002a77ca3a1a --><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Anomalib<\/h2>\n\n\n\n<p><a href=\"https:\/\/www.comet.com\/site\/blog\/powering-anomaly-detection-for-industry-4-0\/\">Anomaly detection<\/a> has an inherent data imbalance problem: the number of anomamalus data points are generally outweighed by the normal data points. This makes it incredibly easy to train a biased model that outputs \u201cno anomaly\u201d and is deemed right 98% of the time. <a href=\"https:\/\/github.com\/openvinotoolkit\/anomalib\">Anomalib<\/a> takes this data imbalance into account and offers 8+ models\/algorithims for users to benchmark on any given dataset. Anomalib can be used for simple classification use cases or to train models that segment where in the image the anomalies occur.<\/p>\n\n\n\n<h1 class=\"wp-block-heading\"><figure><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-9986\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/anomalib-computer-vision-library.png\" alt=\"anomaly detection using Anomalib open source computer vision library \" width=\"926\" height=\"180\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/anomalib-computer-vision-library.png 926w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/anomalib-computer-vision-library-300x58.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/anomalib-computer-vision-library-768x149.png 768w\" sizes=\"auto, (max-width: 926px) 100vw, 926px\" \/><\/figure><\/h1>\n\n\n\n<h2 class=\"wp-block-heading\">Ultralytics<\/h2>\n\n\n\n<p><a href=\"https:\/\/www.comet.com\/site\/blog\/compare-object-detection-models-from-torchvision\/\">Object detection<\/a> is the most popular use case for vision-based machine learning models. The <a href=\"https:\/\/github.com\/ultralytics\/ultralytics\">Ultralytics<\/a> repo implements the powerful YOLOv8 model for object detection but also extends its capabilities to object tracking, instance segmentation, image classification, and pose estimation tasks. This library also makes it really easy to <a href=\"https:\/\/www.comet.com\/site\/blog\/fine-tuning-yolov8-for-image-segmentation-with-comet\/\">fine-tune YOLOv8<\/a> for any use case on your custom data.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter\"><img loading=\"lazy\" decoding=\"async\" width=\"957\" height=\"269\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/ultralytics-object-detection.png\" alt=\"set of images showing objects like scissors, scalpels, people, and cars that have been identified by computer vision models \" class=\"wp-image-9988\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/ultralytics-object-detection.png 957w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/ultralytics-object-detection-300x84.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/ultralytics-object-detection-768x216.png 768w\" sizes=\"auto, (max-width: 957px) 100vw, 957px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Pythae<\/h2>\n\n\n\n<p>Autoencoders take high-dimensional inputs, like an image, and learn how to encode it to a much smaller latent space. These powerful models are used for many different applications: image denoising, <a href=\"https:\/\/www.comet.com\/site\/blog\/sam-stable-diffusion-for-text-to-image-inpainting\/\">image inpainting<\/a>, super-resolution, and feature extraction. <a href=\"https:\/\/github.com\/clementchadebec\/benchmark_VAE\">Pythae<\/a> implements over 15 different autoencoders for users to train on their own data.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter\"><img loading=\"lazy\" decoding=\"async\" width=\"1485\" height=\"731\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/image-autoencoding.png\" alt=\"image autoencoding \" class=\"wp-image-9989\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/image-autoencoding.png 1485w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/image-autoencoding-300x148.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/image-autoencoding-1024x504.png 1024w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/image-autoencoding-768x378.png 768w\" sizes=\"auto, (max-width: 1485px) 100vw, 1485px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Albumentations<\/h2>\n\n\n\n<p>Augmenting your image data with transformations helps improve the generalizability of computer vision models. <a href=\"https:\/\/github.com\/albumentations-team\/albumentations\">Albumentations<\/a> implements more than 70 image transformations including blurring, cropping, and modifying brightness. Users have the ability specify the frequency they want a specific image transformation to occur when they are defining their image augmentation pipeline.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter\"><img loading=\"lazy\" decoding=\"async\" width=\"942\" height=\"292\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/albumentations-image-transformations.png\" alt=\"four copies of a photo of a parrot, each with a different image transformation to improve the generalizability of computer vision models \" class=\"wp-image-9990\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/albumentations-image-transformations.png 942w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/albumentations-image-transformations-300x93.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/albumentations-image-transformations-768x238.png 768w\" sizes=\"auto, (max-width: 942px) 100vw, 942px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Kangas<\/h2>\n\n\n\n<p>Pandas is a great tool for performing exploratory data analysis (EDA) on tabular datasets. <a href=\"https:\/\/github.com\/comet-ml\/kangas\">Kangas<\/a> extends Pandas capabilities to multimedia datasets. Use Kangas to create DataGrids (akin to Pandas Dataframes) that log your datasets and use it to debug your model\u2019s predictions at the sample level.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><figure><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-9991\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/kangas-datagrid-sample-debugging.png\" alt=\"pandas datagrid for debugging a computer vision model at the sample level \" width=\"1503\" height=\"660\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/kangas-datagrid-sample-debugging.png 1503w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/kangas-datagrid-sample-debugging-300x132.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/kangas-datagrid-sample-debugging-1024x450.png 1024w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/kangas-datagrid-sample-debugging-768x337.png 768w\" sizes=\"auto, (max-width: 1503px) 100vw, 1503px\" \/><\/figure><br>\nTrack, Compare, &amp; Visualize Your CV Model Training Runs for Free<\/h2>\n\n\n\n<p>These five open-source computer vision libraries provide powerful foundation to start training CV models for your specific use case. But when it comes to actively training and iterating on a model, sharing results with your team, and achieving production-ready reproducibility, there\u2019s more work to be done from a machine learning operations standpoint.<\/p>\n\n\n\n<p>Comet\u2019s <a href=\"https:\/\/www.comet.com\/site\/\">MLOps platform<\/a> allows you to track, debug, compare, visualize, and reproduce your model training runs. Comet is <strong>free to try, and free forever for individuals and academics<\/strong>, making it a perfect pairing for the open source CV libraries above. Check out the example below of how a CV Project might be tracked in Comet, and <a href=\"https:\/\/www.comet.com\/site\/pricing\/\">try Comet for free<\/a> today.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full wp-image-9998\"><img loading=\"lazy\" decoding=\"async\" width=\"1506\" height=\"740\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-experiment-tracking.gif\" alt=\"computer vision experiment tracking dashboard showing object detection frames and data visualization \" class=\"wp-image-9998\"\/><figcaption class=\"wp-element-caption\">Example of computer vision experiment tracking with Comet<\/figcaption><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Leveraging machine learning for computer vision use cases has revolutionized a myriad of industries by enabling machines to interpret and respond to visual data. From enhancing medical diagnostics with precise imaging techniques to powering autonomous vehicles with real-time object detection and navigation, the applications of computer vision models are vast and diverse. Building state-of-the-art CV [&hellip;]<\/p>\n","protected":false},"author":21,"featured_media":9995,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"customer_name":"","customer_description":"","customer_industry":"","customer_technologies":"","customer_logo":"","_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[6],"tags":[17,18,29,24,37],"coauthors":[134],"class_list":["post-9985","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-anomalib","tag-anomaly-detection","tag-computer-vision","tag-kangas","tag-object-detection"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Top 5 Open-Source Computer Vision Libraries<\/title>\n<meta name=\"description\" content=\"Try these open-source computer vision libraries for anomaly detection, object detection, autoencoding, image transformations, and EDA.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"5 Open-Source Computer Vision Libraries You Need to Know\" \/>\n<meta property=\"og:description\" content=\"Try these open-source computer vision libraries for anomaly detection, object detection, autoencoding, image transformations, and EDA.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/\" \/>\n<meta property=\"og:site_name\" content=\"Comet\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cometdotml\" \/>\n<meta property=\"article:published_time\" content=\"2024-06-21T18:46:25+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-24T17:02:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"798\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Siddharth Mehta\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@Cometml\" \/>\n<meta name=\"twitter:site\" content=\"@Cometml\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Siddharth Mehta\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Top 5 Open-Source Computer Vision Libraries","description":"Try these open-source computer vision libraries for anomaly detection, object detection, autoencoding, image transformations, and EDA.","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:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/","og_locale":"en_US","og_type":"article","og_title":"5 Open-Source Computer Vision Libraries You Need to Know","og_description":"Try these open-source computer vision libraries for anomaly detection, object detection, autoencoding, image transformations, and EDA.","og_url":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/","og_site_name":"Comet","article_publisher":"https:\/\/www.facebook.com\/cometdotml","article_published_time":"2024-06-21T18:46:25+00:00","article_modified_time":"2025-04-24T17:02:45+00:00","og_image":[{"width":1200,"height":798,"url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","type":"image\/jpeg"}],"author":"Siddharth Mehta","twitter_card":"summary_large_image","twitter_creator":"@Cometml","twitter_site":"@Cometml","twitter_misc":{"Written by":"Siddharth Mehta","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#article","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/"},"author":{"name":"Siddharth Mehta","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/652eb7d782d18f295922f50ea3b9e54c"},"headline":"5 Open-Source Computer Vision Libraries You Need to Know","datePublished":"2024-06-21T18:46:25+00:00","dateModified":"2025-04-24T17:02:45+00:00","mainEntityOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/"},"wordCount":550,"publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","keywords":["Anomalib","Anomaly Detection","Computer Vision","Kangas","Object Detection"],"articleSection":["Machine Learning"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/","url":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/","name":"Top 5 Open-Source Computer Vision Libraries","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#primaryimage"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","datePublished":"2024-06-21T18:46:25+00:00","dateModified":"2025-04-24T17:02:45+00:00","description":"Try these open-source computer vision libraries for anomaly detection, object detection, autoencoding, image transformations, and EDA.","breadcrumb":{"@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#primaryimage","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","width":1200,"height":798,"caption":"Object detection example asset from the YOLOv8 open source computer vision library"},{"@type":"BreadcrumbList","@id":"https:\/\/www.comet.com\/site\/blog\/computer-vision-libraries-open-source\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.comet.com\/site\/"},{"@type":"ListItem","position":2,"name":"5 Open-Source Computer Vision Libraries You Need to Know"}]},{"@type":"WebSite","@id":"https:\/\/www.comet.com\/site\/#website","url":"https:\/\/www.comet.com\/site\/","name":"Comet","description":"Build Better Models Faster","publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.comet.com\/site\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.comet.com\/site\/#organization","name":"Comet ML, Inc.","alternateName":"Comet","url":"https:\/\/www.comet.com\/site\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","width":310,"height":310,"caption":"Comet ML, Inc."},"image":{"@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/cometdotml","https:\/\/x.com\/Cometml","https:\/\/www.youtube.com\/channel\/UCmN63HKvfXSCS-UwVwmK8Hw"]},{"@type":"Person","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/652eb7d782d18f295922f50ea3b9e54c","name":"Siddharth Mehta","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/image\/940c7280faea9e1b8b086c2ed7ec01db","url":"https:\/\/secure.gravatar.com\/avatar\/27a672e997fa7a66796e4be0503e0efeec6bd34daae185bb6de163227a5a0739?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/27a672e997fa7a66796e4be0503e0efeec6bd34daae185bb6de163227a5a0739?s=96&d=mm&r=g","caption":"Siddharth Mehta"},"description":"ML Growth Engineer @ Comet. Interested in Computer Vision, Robotics, and Reinforcement Learning","sameAs":["https:\/\/www.comet.com\/"],"url":"https:\/\/www.comet.com\/site\/blog\/author\/siddharthmcomet-com\/"}]}},"jetpack_featured_media_url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2024\/06\/computer-vision-library-ultralytics-.jpeg","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9985","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/users\/21"}],"replies":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/comments?post=9985"}],"version-history":[{"count":1,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9985\/revisions"}],"predecessor-version":[{"id":15362,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/9985\/revisions\/15362"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media\/9995"}],"wp:attachment":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media?parent=9985"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/categories?post=9985"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/tags?post=9985"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/coauthors?post=9985"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}