{"id":4609,"date":"2016-04-16T00:33:36","date_gmt":"2016-04-15T22:33:36","guid":{"rendered":"http:\/\/www.andreas-maschke.com\/?page_id=4609"},"modified":"2018-05-27T23:02:12","modified_gmt":"2018-05-27T21:02:12","slug":"jwf2net","status":"publish","type":"page","link":"https:\/\/blog.overwhale.com\/?page_id=4609","title":{"rendered":"JWF2NET"},"content":{"rendered":"

About JWF2NET (“Electric Sheep on Steroids”)<\/strong><\/p>\n

“JWF2NET” is a dnn (deep neural network) trained on top of the popular “BVLC GoogleNet” with JWildfire-flame-fractals.
\nBasically, those flame-fractals are a collection of my own flames I created over the last years, together with some computer-generated mutations of those flames, which were manually selected. A total of 20000 images where used, and about 200000 iterations of learning were applied.<\/span><\/p>\n

The first version of the dnn (“JWFNET”) was a failure and also crashed my computer, so it is finally lost. But, for the 2nd generation I refined the image base and some params, and finally got the results I was aiming for: letting the computer dream of flame-fractals.<\/span><\/p>\n

So, when thinking of flame-fractals as\u00a0“Electric Sheep” \u00a0(an idea from the inventor of the flame-fractals Scott Draves), we now have some kind of “Electric Sheep on Steroids” \ud83d\ude42
\n<\/span><\/p>\n

Here is one of the early results, you can clearly can see lots of fractal flowers inside:<\/span><\/p>\nngg_shortcode_0_placeholder\n

Some other examples:<\/p>\nngg_shortcode_1_placeholder\nngg_shortcode_2_placeholder\nngg_shortcode_3_placeholder\nngg_shortcode_4_placeholder\nngg_shortcode_5_placeholder\n

About the software (“How to run it?”)<\/strong><\/p>\n

The software to run JWF2NET is a combination of different packages (caffe, python, java, JWildfire) and is still in early alpha state. Depending on the resolution it can run on GPU or CPU, so there is a rather fast “playful mode” and a slow mode for generating final images at higher resolution.<\/span><\/p>\n

Currently it only features a Java-based scripting-interface and I’m not sure if I will ever publish it as it really is not easy to set it up.<\/span><\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

About JWF2NET (“Electric Sheep on Steroids”) “JWF2NET” is a dnn (deep neural network) trained on top of the popular “BVLC GoogleNet” with JWildfire-flame-fractals. Basically, those flame-fractals are a collection of my own flames I created over the last years, together with some computer-generated mutations of those flames, which were manually selected. A total of 20000 images where used, and about 200000 iterations of learning were applied. The first version of the dnn (“JWFNET”) was a failure and also crashed my computer, so it is finally lost. But, for the 2nd generation I refined the image base and some params, and finally got the results I was aiming for: letting the computer dream of flame-fractals. So, when thinking of flame-fractals as\u00a0“Electric Sheep” \u00a0(an idea from the inventor of the flame-fractals Scott Draves), we now have some kind of “Electric Sheep on Steroids” \ud83d\ude42 Here is one of the early results, you can clearly can see lots of fractal flowers inside: Some other examples: About the software (“How to run it?”) The software to run JWF2NET is a combination of different packages (caffe, python, java, JWildfire) and is still in early alpha state. Depending on the resolution it can run on GPU […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":42,"menu_order":12,"comment_status":"closed","ping_status":"closed","template":"","meta":{"ngg_post_thumbnail":0,"footnotes":""},"class_list":["post-4609","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/pages\/4609","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4609"}],"version-history":[{"count":10,"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/pages\/4609\/revisions"}],"predecessor-version":[{"id":4672,"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/pages\/4609\/revisions\/4672"}],"up":[{"embeddable":true,"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=\/wp\/v2\/pages\/42"}],"wp:attachment":[{"href":"https:\/\/blog.overwhale.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4609"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}