[{"data":1,"prerenderedAt":320},["ShallowReactive",2],{"project-21934247":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":34,"aspects":35,"strip":41,"post_text":42,"what":43,"said":57,"maker_in_thread":143,"shape":153,"grid":158,"attempts":283,"same_week":284,"maker_shows":37,"maker_hidden":312,"reader_version":313,"card":314},"21934247","Confusing Coleopterists","A beetle generator made by machine-learning zoological illustrations","title","Show HN: A beetle generator made by machine-learning zoological illustrations","https:\u002F\u002Fwww.cunicode.com\u002Fworks\u002Fconfusing-coleopterists\u002F#StyleGAN","cunicode.com","belforn",1577960992,2020,308,47,131,3028,5,"legend","ai","generative image model","web_app",[24,25,26,27],"stylegan","beetle generator","gan","machine learning illustrations","curious",0.019,{"positive":31,"neutral":32,"mixed":33,"critical":31},3,13,0,19,{"idea":36,"execution":39,"design":40},{"positive":37,"critical":38},2,1,{"positive":33,"critical":37},{"positive":33,"critical":33},[33,33,33,33,33,33,33,33,33,33,33,31,33,38,31,33,31,18,18,33,33,33,33,33,33,33,18,33,31,31,38,31,33,31,31,33,31,38,31,31],null,{"problem":42,"audience":42,"pricing":42,"motivation":42,"time_to_build":42,"stack":44,"openness":55,"stage":56,"team_size":55},[45],{"value":46,"source":47,"evidence":48},"StyleGAN","maker",[49,52],{"id":50,"by":11,"text":51},"21934709","it could be used like that. Technically, the model already learned the features of the dataset. (although it was unlabelled). There are some implementations to find features in…",{"id":53,"by":11,"text":54},"21992188","yes, it is published. Available via @RunwayML https:\u002F\u002Fopen-app.runwayml.com\u002F?model=cunicode\u002Fconfusing_coleopterists","unknown","launched",{"praise":58,"objections":75,"requests":90,"questions":109,"alternatives":128},[59],{"value":60,"source":61,"evidence":62},"Clever and beautiful results, and fun to browse","commenter",[63,67,71],{"id":64,"by":65,"text":66},"21935457","ArtWomb","This is a beautiful write-up. And I don't wish to detract from the author's work. Nature's result side-by-side with that of the Machine. Makes one feel as though we've taken a…",{"id":68,"by":69,"text":70},"21934671","bayesian_horse","I wonder if this could be used as an identification tool for beetles like a phantom sketch. You could move some sliders to get it closer to the bug you are thinking of or which…",{"id":72,"by":73,"text":74},"21939929","cortesi","Excellent. I did something similar a few months ago using a dataset of zoological silhouettes, resulting in a menagerie of mammals, bugs, spiders and other mutant wonders.…",[76,83],{"value":77,"source":61,"evidence":78},"Mirrored halves look unnatural because lighting is asymmetric",[79],{"id":80,"by":81,"text":82},"21935208","dan-robertson","Most of the images have lighting which isn’t symmetrical and I think that makes it pretty obvious when an image is made by mirroring half a beetle. But maybe there’s some way to…",{"value":84,"source":61,"evidence":85},"Legs and symmetry are handled poorly",[86],{"id":87,"by":88,"text":89},"21940626","proc0","Interesting to see how it handled the legs. Looks like it had problems with the fact insects have 3 pairs of symmetrical legs.",[91,102],{"value":92,"source":61,"evidence":93},"Check the model for overfitting against source images",[94,98],{"id":95,"by":96,"text":97},"21939523","fiter","Was this model tested for overfitting? I do not have any sense of whether the beetles that I'm seeing match some source pictures exactly. I noticed that the transformations seem…",{"id":99,"by":100,"text":101},"21939954","enchiridion","Is there a good way to test a gan for overfitting?",{"value":103,"source":61,"evidence":104},"Train on Chernobyl mutated insect images",[105],{"id":106,"by":107,"text":108},"21938728","eskimobloood","Would be interesting to see the result trained on images from this book[1] about mutation on insects in the chernobyl area.…",[110,117],{"value":111,"source":61,"evidence":112},"Is the model available to run?",[113],{"id":114,"by":115,"text":116},"21939013","jamesfisher","Is the source\u002Fmodel\u002Fnetwork available to run?",{"value":118,"source":61,"evidence":119},"Does the network draw the beetles or how does it generate pixels?",[120,124],{"id":121,"by":122,"text":123},"21936208","nsxwolf","What I never understand about these things is ... what actually does the drawing? The AI decides what the beetle looks like, at what level of abstraction? When\u002Fhow does it go…",{"id":125,"by":126,"text":127},"21936506","slynn12","Very clever. Do you know if a machine does the drawing? Wasn't totally clear on that bit.",[129,136],{"value":130,"source":61,"evidence":131},"Picture This plant identification app",[132],{"id":133,"by":134,"text":135},"21934904","deanclatworthy","They already have similar apps to this for a range of things. I guess the most popular ones are for plants [1] [1] https:\u002F\u002Fwww.picturethisai.com\u002F",{"value":137,"source":61,"evidence":138},"Dawkins biomorphs",[139],{"id":140,"by":141,"text":142},"21935490","auton1","Reminds me of Dawkins' biomorphs: http:\u002F\u002Fwww.emergentmind.com\u002Fbiomorphs",{"comments":144,"answered":38,"key":145},6,[146,149,150],{"id":147,"text":148},"21935176","-> https:\u002F\u002Fthisrentaldoesnotexist.com All of the dynamic content on each listing is generated via a series of different machine-learned AI models.",{"id":50,"text":51},{"id":151,"text":152},"21992271","Someone already set it up: http:\u002F\u002Fthisbeetledoesnotexist.com\u002F",{"commenters":154,"max_depth":155,"maker_replies":144,"first_comment_mins":156,"lifespan_hours":157},39,4,88,374,[159,163,165,169,173,176,179,183,186,189,192,195,198,201,203,205,207,208,211,215,216,219,221,224,227,230,233,236,239,242,245,247,250,253,254,259,261,263,265,267,269,272,274,277,279,281,282],[160,33,33,161,162,33],"21935058","other\u002Fneutral\u002Fidea","mensetmanusman",[147,33,33,164,11,38],"maker\u002Fneutral\u002Fidea",[166,33,33,167,168,33],"21937838","other\u002Fneutral\u002Fnone","chaosmachine",[170,33,33,171,172,33],"21939129","other\u002Fcritical\u002Fexecution","csande17",[174,33,33,167,175,33],"21939878","mipmap04",[177,33,33,167,178,33],"21945369","Aeolun",[180,33,33,181,182,33],"21938818","commenter\u002Fneutral\u002Fnone","lopmotr",[184,33,33,181,185,33],"21939177","wpietri",[187,38,33,167,188,33],"21934959","todd8",[190,38,33,167,191,33],"21936222","onychomys",[193,38,33,167,194,33],"21938930","mrob",[196,38,33,167,197,33],"21940150","mc3",[199,38,33,167,200,33],"21940420","benibela",[68,37,31,202,69,33],"project\u002Fneutral\u002Fidea",[50,37,33,204,11,38],"maker\u002Fneutral\u002Fnone",[133,37,38,206,134,33],"project\u002Fcritical\u002Fidea",[140,31,31,202,141,33],[209,31,33,167,210,33],"21938266","stcredzero",[212,155,31,213,214,33],"21935608","project\u002Fneutral\u002Fnone","jonplackett",[151,155,33,204,11,38],[217,155,18,218,214,33],"22081200","project\u002Fpositive\u002Fnone",[64,18,18,220,65,33],"maker\u002Fpositive\u002Fidea",[222,18,33,167,223,33],"21936178","erikpukinskis",[225,18,33,167,226,33],"21936407","skykooler",[228,18,33,167,229,33],"21936571","l_t",[231,18,33,167,232,33],"21937726","nbardy",[234,18,33,167,235,33],"21937807","hayksaakian",[237,18,33,167,238,33],"21942228","drdeca",[240,18,33,167,241,33],"21938194","dllthomas",[243,18,33,167,244,33],"21938384","copenja",[72,144,18,246,73,33],"project\u002Fpositive\u002Fidea",[248,144,33,249,11,38],"21992238","maker\u002Fpositive\u002Fnone",[95,251,31,252,96,33],7,"project\u002Fneutral\u002Fexecution",[99,251,31,252,100,33],[255,256,31,257,258,33],"21935163",8,"project\u002Fneutral\u002Fdesign","CSactuary",[80,256,38,260,81,33],"project\u002Fcritical\u002Fexecution",[262,256,31,252,223,33],"21936335",[264,256,33,181,182,33],"21938972",[106,266,31,202,107,33],9,[121,268,31,202,122,33],10,[270,268,31,202,271,33],"21936255","_fullpint",[273,268,33,202,11,38],"21937481",[275,268,31,202,276,33],"21937320","tlack",[87,278,38,260,88,33],11,[114,280,31,213,115,33],12,[53,280,33,204,11,38],[125,32,31,213,126,33],[],[285,290,294,299,303,307],{"id":286,"name":287,"points":288,"category":289},"21991382","Beef",533,"languages",{"id":291,"name":292,"points":293,"category":289},"21951692","amazon-kinesis-video-streams-webrtc-sdk-c",251,{"id":295,"name":296,"points":297,"category":298},"21981158","jql",217,"dev_tools",{"id":300,"name":301,"points":302,"category":298},"21958986","Terrastruct",187,{"id":304,"name":305,"points":306,"category":289},"21948472","sscaffold-css",158,{"id":308,"name":309,"points":310,"category":311},"21932381","DiscoTask",126,"productivity",false,"v2",{"id":315,"name":5,"line":6,"ai":312,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":316,"top":18,"kw":317,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":318,"url":9,"mix":319,"praise":60,"objection":77,"sub":21},21934247,0.02,[24,25,26,27],"0000000000030130355000000050331303303133",[31,32,33,31],1794036584688]