{"id":3892,"date":"2022-09-12T15:24:04","date_gmt":"2022-09-12T23:24:04","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=3892"},"modified":"2025-04-29T14:10:04","modified_gmt":"2025-04-29T14:10:04","slug":"build-production-ready-vision-models-with-comet-yolov5","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/","title":{"rendered":"Build Production Ready Computer Vision Models with Comet and YOLOv5"},"content":{"rendered":"\n<p><span style=\"font-weight: 400;\">To jump directly into resources about how to use Comet and Ultralytics YOLOv5, check out:&nbsp;<\/span><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.comet.com\/docs\/v2\/integrations\/third-party-tools\/yolov5\/\"><span style=\"font-weight: 400;\">Comet docs<\/span><\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.comet.com\/examples\/comet-example-yolov5\/view\/1c4Dqcu8mZ767NBipjwlx3gz6\/panels?shareable=YcwMiJaZSXfcEXpGOHDD12vA1\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">YOLOv5 experiment<\/span><span style=\"font-weight: 400;\"> logged in Comet<\/span><\/a><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\"><a href=\"https:\/\/colab.research.google.com\/drive\/1pV6kWv8eputbZYV2EcwBU4DA43k74ZXL#scrollTo=k12SqoTKAWQd\" target=\"\u201d_blank\u201d\" rel=\"noopener\">Colab tutorial on training YOLOv5 with custom datasets in Comet<\/a>&nbsp;<\/span><\/li>\n\n\n\n<li><a href=\"https:\/\/github.com\/ultralytics\/yolov5\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">YOLOv5 GitHub repo<\/span><\/a><\/li>\n<\/ul>\n\n\n\n<p>Start training and logging Ultralytics YOLOv5 models with Comet:<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link wp-element-button\" href=\"\/signup?utm_source=yolov5&amp;utm_medium=partner&amp;utm_campaign=online_partner_yolov5_integration\" target=\"_blank\" rel=\"noreferrer noopener\">Create your free Comet account here<\/a><\/div>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">What is YOLOv5?<\/span><\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">The Ultralytics YOLOv5 library is a family of deep learning object detection architectures that are pre-trained on the COCO dataset. It\u2019s open-source and feature-rich. To date, it\u2019s become one of the most practical set of object detection algorithms that anyone can use.&nbsp;<\/span><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">Computer vision use cases are costly to train. Handling unstructured data and debugging the model performance is also complicated. YOLOv5 makes it simple to apply computer vision to any custom application.&nbsp;<\/span><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">Want to learn more about YOLO object detection more generally? Check out this <\/span><a href=\"https:\/\/youtu.be\/-MMj68JnWmk?t=1278\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">YouTube video tutorial<\/span><\/a><span style=\"font-weight: 400;\">.&nbsp;<\/span><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">What makes YOLOv5 so convenient<\/span><\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">YOLOv5 is a library with a suite of tools that enables both beginners and experts of object detection to train and tune a model for production-ready performance. Some of the unique features include:<\/span><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">auto-anchors that use k-means and a Genetic Algorithm (GA) for optimization. They identify anchors that weren\u2019t already labeled so you don\u2019t have to do it yourself.&nbsp;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">easily train on custom datasets<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">multiple model architectures including a small one that can run on the edge<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">a low-code library that just works right out of the box. All you have to do is modify a config file and load up your custom dataset<\/span><\/li>\n<\/ul>\n\n\n\n<p><span style=\"font-weight: 400;\">The <\/span><a href=\"https:\/\/ultralytics.com\/about\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">Ultralytics team<\/span><\/a><span style=\"font-weight: 400;\"> that manages YOLOv5 has put a lot of effort into their documentation, along with adding integrations and tutorials.&nbsp;<\/span><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">YOLOv5 is now fully integrated with Comet<\/span><\/h2>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"300\" height=\"157\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-300x157.png\" alt=\"Comet dashboard with various diagrams and charts\" class=\"wp-image-3915\" srcset=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-300x157.png 300w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-1024x535.png 1024w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-768x401.png 768w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-1536x802.png 1536w, https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-2048x1070.png 2048w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">The YOLOv5 library can be a great starting point to your computer vision journey.&nbsp; To improve the model\u2019s performance and get it production-ready, you&#8217;ll need to log the results in an experiment tracking tool like Comet.&nbsp;&nbsp;<\/span><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">The Comet and YOLOv5 integration offers 3 main features that we\u2019ll cover in this post:<\/span><\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">Autologging and custom logging features&nbsp;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">Saving datasets and models as artifacts for debugging, and reproducibility<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">Organizing your view with Comet\u2019s custom panels<\/span><\/li>\n<\/ol>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">Comet automates tracking of ML metadata<\/span><\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">Comet is a powerful tool for tracking your models, datasets, and metrics. It even logs your system and environment variables to ensure reproducibility and smooth debugging for each and every run. It\u2019s like having a virtual assistant that magically knows what notes to keep.<\/span><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1902\" height=\"909\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-autologged-metrics-2.gif\" alt=\"\" class=\"wp-image-3900\"\/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">With the YOLOv5 integration, Comet automatically logs each of the following, straight out-of-the-box, and without any additional code:&nbsp;&nbsp;<\/span><\/p>\n\n\n\n<p><b>Metrics<\/b><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">Box loss, object loss, classification loss for the training and validation data;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">mAP_0.5, mAP_0.5:0.95 metrics for the validation data;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">Precision and recall for the validation data.<\/span><\/li>\n<\/ul>\n\n\n\n<p><b>Parameters<\/b><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">Model hyperparameters;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">All parameters passed through the command line options.<\/span><\/li>\n<\/ul>\n\n\n\n<p><b>Visualizations<\/b><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">Confusion matrix of model predictions on the validation data;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">Plots for the precision-recall and F1 curves across all classes;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">Correlogram of the class labels.<\/span><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">Easily log custom data like YOLOv5 checkpoints, models and datasets<\/span><\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">If you\u2019re looking for more in-depth experiment management, custom logging capabilities are also available either through command line flags or environment variables. With Comet, you can log <a href=\"https:\/\/www.comet.com\/docs\/v2\/api-and-sdk\/python-sdk\/reference\/Experiment\/\" target=\"\u201d_blank\u201d\" rel=\"noopener\">custom user-defined metrics, class-level metrics, and model predictions<\/a>.&nbsp;<\/span><\/p>\n\n\n\n<p><strong>Log YOLOv5 checkpoints in Comet<\/strong><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">Training with unstructured data (like images) can be painfully time-consuming. Any interruption can be a major set-back, especially if you have to start training from scratch.&nbsp;<\/span><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">By logging checkpoints, you can simply pick-up where you left off! Comet allows you to resume training from your latest checkpoint, specify which checkpoints are logged, overwrite checkpoints, and retrieve saved checkpoints with a simple command line flag.<\/span><\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">--save_period 1<\/pre>\n\n\n\n<p><strong>Log datasets and YOLOv5 models as Comet Artifacts<\/strong><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">Saving datasets and models as Artifacts in Comet will support you with debugging and reproducibility. You can upload artifacts in isolation (e.g. a dataset you plan on using later, or a pre-trained model), or you can upload them automatically with your training runs, all with a simple command line flag.<\/span><\/p>\n\n\n\n<p>To log model predictions as images, you can add<\/p>\n\n\n\n<div>\n<pre>--bbox_interval 1<\/pre>\n<\/div>\n\n\n\n<p><strong>With Comet Artifacts, you can:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">version control your models and datasets, while tracking their lineages.&nbsp;<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">upload saved Artifacts and use them in new experiments<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">view them directly in the Comet UI, or download into your environment of choice for further analysis.<\/span><\/li>\n<\/ul>\n\n\n\n<p>Once you&#8217;ve logged an artifact with Comet, you can upload a version of it with:<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">--upload_dataset \"train\"<\/pre>\n\n\n\n<p><span style=\"font-weight: 400;\">To see any of the custom logging in action, check out the<\/span><a href=\"https:\/\/colab.research.google.com\/drive\/1pV6kWv8eputbZYV2EcwBU4DA43k74ZXL?usp=sharing#scrollTo=wuTSQzIKIF_x\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\"> Colab.<\/span><\/a><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">Organize your view with Comet&#8217;s custom panels<\/span><\/h3>\n\n\n\n<p>Comet&#8217;s platform lets you visualize your model in any way you like. <span style=\"font-weight: 400;\">You can choose from any of Comets 200+ publicly available Panels or build your own!&nbsp;<\/span><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1625\" height=\"803\" src=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Custom-panels-1.gif\" alt=\"\" class=\"wp-image-3903\"\/><\/figure>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><\/h3>\n\n\n\n<h3 class=\"wp-block-heading\"><span style=\"font-weight: 400;\">Review a YOLOv5 model logged with Comet<\/span><\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">Now that you know what the integration can do, why not see it for yourself? Our <a href=\"https:\/\/youtu.be\/qZGSc4jSKWU\" target=\"_blank\" rel=\"noopener\">resident data scientist, Dhruv Nair<\/a> has logged a YOLOv5 model. <\/span><\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/www.comet.com\/examples\/comet-example-yolov5\/view\/1c4Dqcu8mZ767NBipjwlx3gz6\/panels\" target=\"_blank\" rel=\"noreferrer noopener\">View Yolov5 model logged in Comet<\/a><\/div>\n<\/div>\n\n\n\n<p><span style=\"font-weight: 400;\">When you navigate to Dhruv\u2019s public experiment in the Comet UI, your default view displays Panels that illustrate performance metrics across multiple experiment runs, helping you visually compare models and experiments within a single project. Comet\u2019s YOLOv5 integration automatically logs experiment metrics like precision, mean average precision (mAP), recall, and training loss, and then plots them for you in the default panel view. Additionally, if you select individual experiments, you\u2019ll find that Comet auto-logs even more details of each specific experiment run like system metrics and package installations, learning rate, loss metrics, and more.\u00a0<\/span><\/p>\n\n\n\n<p><span style=\"font-weight: 400;\">With Comet, you also have the freedom to further customize which metrics and features are logged. For most experiment-specific logging, just insert the relevant command line flag or environment variable into your original code from this <\/span><a href=\"https:\/\/github.com\/DN6\/yolov5\/tree\/feature-comet-integration\/utils\/loggers\/comet\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">simple documentation<\/span><\/a><span style=\"font-weight: 400;\">. This panel illustrates your model\u2019s bounding box predictions on validation images, and allows you to adjust confidence thresholds and filter by label\u2013 all directly in the UI!<\/span><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Other tools you might use for your YOLOv5 model<\/h3>\n\n\n\n<p><span style=\"font-weight: 400;\">Since you\u2019re still here, thanks for reading this far! Check out these free resources to help debug your Ultralytics YOLOv5 model.&nbsp;<\/span><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><span style=\"font-weight: 400;\">If you\u2019re using synthetic images, check out this <\/span><a href=\"https:\/\/29a.ch\/photo-forensics\/#forensic-magnifier\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">forensic image<\/span><\/a><span style=\"font-weight: 400;\"> tool to see if your model has identified some differences between your real and simulated images.<\/span><\/li>\n\n\n\n<li><a href=\"https:\/\/albumentations.ai\/docs\/\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">Albumentations<\/span><\/a><span style=\"font-weight: 400;\"> is already auto-implemented in YOLOv5, but take a look and you might find a different way to see your data.<\/span><\/li>\n\n\n\n<li><span style=\"font-weight: 400;\">If you need to annotate your own data, check out <\/span><a href=\"https:\/\/github.com\/heartexlabs\/labelImg\" target=\"\u201d_blank\u201d\" rel=\"noopener\"><span style=\"font-weight: 400;\">labelimg.<\/span><\/a><\/li>\n<\/ul>\n\n\n\n<p><span style=\"font-weight: 400;\">You can also <\/span><a href=\"https:\/\/join.slack.com\/t\/cometml\/shared_invite\/zt-1fa356mer-2AMqwrzobWAJNx1oo1KSpQ\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">join Comet\u2019s Slack community<\/span><\/a><span style=\"font-weight: 400;\"> to get support on any integration.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>To jump directly into resources about how to use Comet and Ultralytics YOLOv5, check out:&nbsp; Start training and logging Ultralytics YOLOv5 models with Comet: What is YOLOv5? The Ultralytics YOLOv5 library is a family of deep learning object detection architectures that are pre-trained on the COCO dataset. It\u2019s open-source and feature-rich. To date, it\u2019s become [&hellip;]<\/p>\n","protected":false},"author":112,"featured_media":3915,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"customer_name":"","customer_description":"","customer_industry":"","customer_technologies":"","customer_logo":"","footnotes":""},"categories":[8,5],"tags":[],"coauthors":[131,133],"class_list":["post-3892","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-comet-community-hub","category-partners-integrations"],"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>Build Production Ready Computer Vision Models with Comet and YOLOv5<\/title>\n<meta name=\"description\" content=\"Comet is now integrated with the Ultralytics YOLOv5 library. See examples for how to use both together for your computer vision project!\" \/>\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\/build-production-ready-vision-models-with-comet-yolov5\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Build Production Ready Computer Vision Models with Comet and YOLOv5\" \/>\n<meta property=\"og:description\" content=\"Comet is now integrated with the Ultralytics YOLOv5 library. See examples for how to use both together for your computer vision project!\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/\" \/>\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=\"2022-09-12T23:24:04+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-29T14:10:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-1024x535.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"535\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Claire Pena, Abby Morgan\" \/>\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=\"Claire Pena, Abby Morgan\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Build Production Ready Computer Vision Models with Comet and YOLOv5","description":"Comet is now integrated with the Ultralytics YOLOv5 library. See examples for how to use both together for your computer vision project!","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\/build-production-ready-vision-models-with-comet-yolov5\/","og_locale":"en_US","og_type":"article","og_title":"Build Production Ready Computer Vision Models with Comet and YOLOv5","og_description":"Comet is now integrated with the Ultralytics YOLOv5 library. See examples for how to use both together for your computer vision project!","og_url":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/","og_site_name":"Comet","article_publisher":"https:\/\/www.facebook.com\/cometdotml","article_published_time":"2022-09-12T23:24:04+00:00","article_modified_time":"2025-04-29T14:10:04+00:00","og_image":[{"width":1024,"height":535,"url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example-1024x535.png","type":"image\/png"}],"author":"Claire Pena, Abby Morgan","twitter_card":"summary_large_image","twitter_creator":"@Cometml","twitter_site":"@Cometml","twitter_misc":{"Written by":"Claire Pena, Abby Morgan","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#article","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/"},"author":{"name":"Claire Pena","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/b73b3ffc304cf8bec8866340329c5e89"},"headline":"Build Production Ready Computer Vision Models with Comet and YOLOv5","datePublished":"2022-09-12T23:24:04+00:00","dateModified":"2025-04-29T14:10:04+00:00","mainEntityOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/"},"wordCount":1113,"publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example.png","articleSection":["Comet Community Hub","Partners &amp; Integrations"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/","url":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/","name":"Build Production Ready Computer Vision Models with Comet and YOLOv5","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#primaryimage"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#primaryimage"},"thumbnailUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example.png","datePublished":"2022-09-12T23:24:04+00:00","dateModified":"2025-04-29T14:10:04+00:00","description":"Comet is now integrated with the Ultralytics YOLOv5 library. See examples for how to use both together for your computer vision project!","breadcrumb":{"@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#primaryimage","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example.png","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2022\/09\/Comet-Yolov5-example.png","width":3840,"height":2006,"caption":"Comet dashboard with various diagrams and charts"},{"@type":"BreadcrumbList","@id":"https:\/\/www.comet.com\/site\/blog\/build-production-ready-vision-models-with-comet-yolov5\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.comet.com\/site\/"},{"@type":"ListItem","position":2,"name":"Build Production Ready Computer Vision Models with Comet and YOLOv5"}]},{"@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\/b73b3ffc304cf8bec8866340329c5e89","name":"Claire Pena","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/image\/6c42de20d82274b5bcc55f12d2480401","url":"https:\/\/secure.gravatar.com\/avatar\/0158b496f72fba29753917da405441fa923b21dec99134ee8818143fc4113fe4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/0158b496f72fba29753917da405441fa923b21dec99134ee8818143fc4113fe4?s=96&d=mm&r=g","caption":"Claire Pena"},"url":"https:\/\/www.comet.com\/site\/blog\/author\/clairep\/"}]}},"_links":{"self":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/3892","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\/112"}],"replies":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/comments?post=3892"}],"version-history":[{"count":2,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/3892\/revisions"}],"predecessor-version":[{"id":15823,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/3892\/revisions\/15823"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media\/3915"}],"wp:attachment":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media?parent=3892"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/categories?post=3892"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/tags?post=3892"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/coauthors?post=3892"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}