{"id":395989,"date":"2024-06-29T12:33:48","date_gmt":"2024-06-29T12:33:48","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=395989"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=395989","title":{"rendered":"Data Phoenix Digest \u2014 ISSUE 2.2023<\/span>"},"content":{"rendered":"
<\/div>\n
\n
\n
\n
\n
<\/figcaption><\/figure>\n

Video recording of the webinar about dstack and reproducible ML workflows, AVL binary tree operations, Ultralytics YOLOv8, training XGBoost, productionize ML models, introduction to forecasting ensembles, domain expansion of image generators, Muse, X-Decoder, Box2Mask, RoDynRF, AgileAvatar and more.<\/p>\n\n

VIDEO<\/h3>\n

dstack \u2013 a command-line utility to provision infrastructure for ML workflows<\/u><\/strong><\/a><\/p>\n

<\/div>\n

Video recording of our webinar about\u00a0dstack<\/u><\/a>\u00a0and reproducible ML workflows by Andrey Cheptsov.<\/p>\n\n

If you have interesting topics or projects that you would like to share with the world in our webinars, you can submit them\u00a0here<\/u><\/a>.<\/p>\n\n

ARTICLES<\/h3>\n

AVL Binary Tree Operations<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

In this article, the author described AVL trees and operations you can perform on them, such as inserting a node in different variants (for example, left, right or right, right).<\/p>\n

Ultralytics YOLOv8: State-of-the-Art YOLO Models<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

YOLOv8 is the latest family of YOLO based Object Detection models from Ultralytics providing state-of-the-art performance. This article looks into the latest improvements and features added to YOLOv8, and provides a guide on using it in practice.<\/p>\n

End-to-End MLOps with Snowpark Python and MLFlow<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

How would you leverage Snowpark Python for operationalizing your machine learning models within the flow of your existing MLOps processes? The article provides detailed answers and looks into end-to-end MLOps, from A to Z.<\/p>\n

Building a Predictive Maintenance Solution Using AWS AutoML and No-Code Tools<\/u><\/strong><\/a>
Industrial machine, equipment, and vehicle operators need to reduce maintenance costs while operating under strict constraints. This article presents a predictive maintenance solution built using AutoML and no-code tools powered by AWS. Check it out!<\/p>\n

PAPERS & PROJECTS<\/h3>\n

Zero-Shot Text-Guided Object Generation with Dream Fields<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

Dream Fields can generate the geometry and color of a wide range of objects without 3D supervision. It combines neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Take a look!<\/p>\n

AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

AgileAvatar is a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. To ensure the discrete parameters are optimized, a cascaded relaxation-and-search pipeline is implemented.<\/p>\n

RoDynRF: Robust Dynamic Radiance Fields<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

In this work, the authors address the robustness issue of dynamic radiance field reconstruction methods by jointly estimating the static and dynamic radiance fields along with the camera parameters (poses and focal length). Learn how they do it!<\/p>\n

Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution<\/u><\/strong><\/a><\/p>\n

\"\"
<\/figcaption><\/figure>\n

Box2Mask is a novel single-shot instance segmentation approach, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision. Check the paper out!<\/p>\n\n

If you enjoyed this content<\/strong>\u00a0make sure to\u00a0subscribe<\/u><\/a>\u00a0to our newsletter and share it with others who may be interested. Follow us on social networks (Telegram<\/u><\/a>,\u00a0Facebook<\/u><\/a>,\u00a0Twitter<\/u><\/a>,\u00a0LinkedIn<\/u><\/a>,\u00a0YouTube<\/u><\/a>) to stay updated about the upcoming webinars and have more interesting content.<\/p>\n\n

Read the full digest\u00a0here<\/a>.<\/p>\n<\/div>\n<\/div>\n<\/div>\n

<\/div>\n


\u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 https:\/\/habr.com\/ru\/articles\/713128\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

<\/div>\n
\n
\n
\n
\n
<\/figcaption><\/figure>\n

Video recording of the webinar about dstack and reproducible ML workflows, AVL binary tree operations, Ultralytics YOLOv8, training XGBoost, productionize ML models, introduction to forecasting ensembles, domain expansion of image generators, Muse, X-Decoder, Box2Mask, RoDynRF, AgileAvatar and more.<\/p>\n\n

VIDEO<\/h3>\n

dstack \u2013 a command-line utility to provision infrastructure for ML workflows<\/u><\/strong><\/a><\/p>\n

<\/div>\n

Video recording of our webinar about\u00a0dstack<\/u><\/a>\u00a0and reproducible ML workflows by Andrey Cheptsov.<\/p>\n\n

If you have interesting topics or projects that you would like to share with the world in our webinars, you can submit them\u00a0here<\/u><\/a>.<\/p>\n\n

ARTICLES<\/h3>\n

AVL Binary Tree Operations<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

In this article, the author described AVL trees and operations you can perform on them, such as inserting a node in different variants (for example, left, right or right, right).<\/p>\n

Ultralytics YOLOv8: State-of-the-Art YOLO Models<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

YOLOv8 is the latest family of YOLO based Object Detection models from Ultralytics providing state-of-the-art performance. This article looks into the latest improvements and features added to YOLOv8, and provides a guide on using it in practice.<\/p>\n

End-to-End MLOps with Snowpark Python and MLFlow<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

How would you leverage Snowpark Python for operationalizing your machine learning models within the flow of your existing MLOps processes? The article provides detailed answers and looks into end-to-end MLOps, from A to Z.<\/p>\n

Building a Predictive Maintenance Solution Using AWS AutoML and No-Code Tools<\/u><\/strong><\/a>
Industrial machine, equipment, and vehicle operators need to reduce maintenance costs while operating under strict constraints. This article presents a predictive maintenance solution built using AutoML and no-code tools powered by AWS. Check it out!<\/p>\n

PAPERS & PROJECTS<\/h3>\n

Zero-Shot Text-Guided Object Generation with Dream Fields<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

Dream Fields can generate the geometry and color of a wide range of objects without 3D supervision. It combines neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Take a look!<\/p>\n

AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

AgileAvatar is a novel self-supervised learning framework to create high-quality stylized 3D avatars with a mix of continuous and discrete parameters. To ensure the discrete parameters are optimized, a cascaded relaxation-and-search pipeline is implemented.<\/p>\n

RoDynRF: Robust Dynamic Radiance Fields<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

In this work, the authors address the robustness issue of dynamic radiance field reconstruction methods by jointly estimating the static and dynamic radiance fields along with the camera parameters (poses and focal length). Learn how they do it!<\/p>\n

Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution<\/u><\/strong><\/a><\/p>\n

<\/figcaption><\/figure>\n

Box2Mask is a novel single-shot instance segmentation approach, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision. Check the paper out!<\/p>\n\n

If you enjoyed this content<\/strong>\u00a0make sure to\u00a0subscribe<\/u><\/a>\u00a0to our newsletter and share it with others who may be interested. Follow us on social networks (Telegram<\/u><\/a>,\u00a0Facebook<\/u><\/a>,\u00a0Twitter<\/u><\/a>,\u00a0LinkedIn<\/u><\/a>,\u00a0YouTube<\/u><\/a>) to stay updated about the upcoming webinars and have more interesting content.<\/p>\n\n

Read the full digest\u00a0here<\/a>.<\/p>\n<\/div>\n<\/div>\n<\/div>\n

<\/div>\n


\u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 https:\/\/habr.com\/ru\/articles\/713128\/<\/a>
<\/br><\/br><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-395989","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/395989","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=395989"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/395989\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=395989"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=395989"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=395989"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}