{"id":996,"date":"2025-06-29T05:19:33","date_gmt":"2025-06-29T12:19:33","guid":{"rendered":"http:\/\/fx-td.com\/houdiniandchill\/?p=996"},"modified":"2025-06-29T05:28:34","modified_gmt":"2025-06-29T12:28:34","slug":"hou-tops-archived-post-by-fabriciochamon","status":"publish","type":"post","link":"http:\/\/fx-td.com\/houdiniandchill\/2025\/06\/29\/hou-tops-archived-post-by-fabriciochamon\/","title":{"rendered":"[hou-tops] Archived post by fabriciochamon"},"content":{"rendered":"<div class=\"postie-post\">\n<p class=\"\">Here you go, node recommender trained in Houdini.<br \/>\nI&#8217;ve reorganized this thing to avoid external python code, so now a topnet scans hip files and stores node connections. In sops I create the ML examples, which are then trained in another topnet, and finally I do model inference in sops again.<br \/>\nadded comments so its (hopefully) easy to follow. Worth noting that it builds a list of available node types based on the current houdini session and won&#8217;t evaluate HDAs that are not part of current environment (ie: unloaded packages).<br \/>\nFirst run takes a while since the ml regression top creates a venv with pytorch (5gb!)<br \/>\nregarding inference:  It needs a good amount of examples to produce something useful!  also its just prototype ofc, would definitely need some work on the UX, etc..<\/p>\n<p>Attachments in this post: <br \/><a href=\"http:\/\/fx-td.com\/houdiniandchill\/wp-content\/uploads\/discord\/20251906\/29\/25\/image.png\">http:\/\/fx-td.com\/houdiniandchill\/wp-content\/uploads\/discord\/20251906\/29\/25\/image.png<\/a><br \/><a href=\"http:\/\/fx-td.com\/houdiniandchill\/wp-content\/uploads\/discord\/20251906\/29\/25\/node_recommender.hiplc\">http:\/\/fx-td.com\/houdiniandchill\/wp-content\/uploads\/discord\/20251906\/29\/25\/node_recommender.hiplc<\/a><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Here you go, node recommender trained in Houdini. I&#8217;ve reorganized this thing to avoid external python code, so now a topnet scans hip files and stores node connections. In sops I create the ML examples, which are then trained in another topnet, and finally I do model inference in sops again. added comments so its &hellip; <a href=\"http:\/\/fx-td.com\/houdiniandchill\/2025\/06\/29\/hou-tops-archived-post-by-fabriciochamon\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">[hou-tops] Archived post by fabriciochamon<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-996","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/posts\/996","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/comments?post=996"}],"version-history":[{"count":0,"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/posts\/996\/revisions"}],"wp:attachment":[{"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/media?parent=996"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/categories?post=996"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/fx-td.com\/houdiniandchill\/wp-json\/wp\/v2\/tags?post=996"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}