{"id":8890,"date":"2019-06-20T08:53:53","date_gmt":"2019-06-20T15:53:53","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=8890"},"modified":"2019-06-20T15:38:10","modified_gmt":"2019-06-20T22:38:10","slug":"ml-developers-come-check-out-mediapipe","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2019\/06\/20\/ml-developers-come-check-out-mediapipe\/","title":{"rendered":"ML developers: Come check out MediaPipe"},"content":{"rendered":"<p>The glue my team developed to connect &amp; coordinate machine learning, computer vision, and other processes is now <a href=\"https:\/\/github.com\/google\/mediapipe\">available for developers<\/a>:<\/p>\n<blockquote><p>The main use case for MediaPipe is rapid prototyping of applied machine learning pipelines with inference models and other reusable components. MediaPipe also facilitates the deployment of machine learning technology into demos and applications on a wide variety of different hardware platforms (e.g., Android, iOS, workstations).<\/p><\/blockquote>\n<p>If you\u2019ve tried any of the Google AR examples I\u2019ve posted in the last year+ (Playground, Motion Stills, YouTube Stories or ads, etc.), you\u2019ve already used MediaPipe, and&nbsp; now you can use it to remove some drudgery when creating your own apps.<\/p>\n<p><a href=\"https:\/\/sites.google.com\/corp\/view\/perception-cv4arvr\/mediapipe\">Here\u2019s a whole site<\/a> full of examples, <a href=\"http:\/\/mediapipe.readthedocs.io\">documentation<\/a>, a <a href=\"https:\/\/drive.google.com\/file\/d\/1j3rRHwIusrKqqeWjY4DQANIXna6X0pXf\/view\">technical white paper<\/a>, <a href=\"https:\/\/mediapipe-viz.appspot.com\/\">graph visualizer<\/a>, and more. If you take it for a spin, let us know how it goes!<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2019\/06\/NewImage-12.png\" alt=\"NewImage\" width=\"600\" height=\"678\" border=\"0\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The glue my team developed to connect &amp; coordinate machine learning, computer vision, and other processes is now available for developers: The main use case for MediaPipe is rapid prototyping of applied machine learning pipelines with inference models and other reusable components. MediaPipe also facilitates the deployment of machine learning technology into demos and applications [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[13],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8890"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=8890"}],"version-history":[{"count":4,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8890\/revisions"}],"predecessor-version":[{"id":8902,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8890\/revisions\/8902"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=8890"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=8890"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=8890"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}