[{"data":1,"prerenderedAt":285},["ShallowReactive",2],{"project-8483763":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":27,"sentiment":28,"stance_mix":29,"scored_comments":34,"aspects":35,"strip":42,"post_text":44,"what":45,"said":68,"maker_in_thread":162,"shape":164,"grid":168,"attempts":246,"same_week":247,"maker_shows":30,"maker_hidden":277,"reader_version":278,"card":279},"8483763","Flickr Park or Bird","Using computer vision to detect birds in parks","title","Show HN: Using computer vision to detect birds in parks","http:\u002F\u002Fcode.flickr.net\u002F2014\u002F10\u002F20\u002Fintroducing-flickr-park-or-bird\u002F","code.flickr.net","sawthat",1413830513,2014,195,33,106,2272,5,"notable","ai","image recognition","web_app",[24,25,21,26],"computer vision","bird detection","deep learning","roasted",-0.447,{"positive":30,"neutral":31,"mixed":32,"critical":33},1,4,2,11,18,{"performance":36,"idea":39,"docs":40,"design":41},{"positive":37,"critical":38},0,6,{"positive":30,"critical":30},{"positive":37,"critical":32},{"positive":37,"critical":32},[37,37,37,37,43,43,37,30,30,18,43,30,30,43,43,37,37,37,30,30,43,30,37,30,30,30,37,30],3,null,{"problem":46,"audience":44,"pricing":44,"motivation":44,"time_to_build":44,"stack":56,"openness":65,"stage":66,"team_size":67},{"value":47,"source":48,"evidence":49},"Detecting whether a photo contains a bird","inferred",[50,52],{"id":51},"post",{"id":53,"by":54,"text":55},"8484860","JangoSteve","Also, the exact question you're trying to answer makes a difference. If the question is, \"Is this a picture of a bird?\" where \"of a bird\" means that the primary focus of the…",[57],{"value":58,"source":59,"evidence":60},"Deep convolutional neural networks","commenter",[61],{"id":62,"by":63,"text":64},"8486865","r3m6","Nice. They use deep convolutional neural nets, which is the key algorithm that dominated the ILSVRC 2014. This computer vision contest included, among other challenges,…","unknown","launched","company",{"praise":69,"objections":78,"requests":109,"questions":124,"alternatives":136},[70],{"value":71,"source":59,"evidence":72},"Impressive results on close-up photos of single birds",[73,77],{"id":74,"by":75,"text":76},"8486190","hemangshah","Looks like it does quite well (on good images with closeup of a single bird). Some fails:…",{"id":62,"by":63,"text":64},[79,94,102],{"value":80,"source":59,"evidence":81},"Fails on many bird photos, especially distant or non-close-up shapes",[82,86,90],{"id":83,"by":84,"text":85},"8484326","tlack","Some pretty clear bird photos aren't working either; I guess it has to be a close up, which kind of ruins the usefulness for me.…",{"id":87,"by":88,"text":89},"8484045","cowpig","http:\u002F\u002Fbioexpedition.com\u002Fwp-content\u002Fuploads\u002F2012\u002F04\u002FPeacock_With_Fanned_Tail_600.jpg wrong…",{"id":91,"by":92,"text":93},"8484102","tolkienfanatic","Does not recognize Big Bird. I proclaim this to be a failure.",{"value":95,"source":59,"evidence":96},"Misclassifies flowers, bees and non-birds as birds",[97,101],{"id":98,"by":99,"text":100},"8484235","verelo","I'm seeing a lot of pictures of flowers and bees in the bird pictures. I'm guessing this is due to the way the training is done, anyone from Flickr who can comment on that?",{"id":87,"by":88,"text":89},{"value":103,"source":59,"evidence":104},"Does not work on tablet",[105],{"id":106,"by":107,"text":108},"8485034","callesgg","Does not work on tablet :(",[110,117],{"value":111,"source":59,"evidence":112},"Trigger app that photographs birds passing by a phone left in a tree",[113],{"id":114,"by":115,"text":116},"8484128","bambax","Totally not what I was expecting! What would be very cool would be some kind of trigger app where you leave your phone in a tree for an hour, and it takes pictures of all the…",{"value":118,"source":59,"evidence":119},"Open image2vec style feature extractor",[120],{"id":121,"by":122,"text":123},"8484022","kcarnold","It's cool that a team of deep learning researchers can pull this off quickly. Anyone know of an \"image2vec\" (word2vec for images) that would empower others to try out similar…",[125,132],{"value":126,"source":59,"evidence":127},"Did they build from scratch or use a library",[128],{"id":129,"by":130,"text":131},"8483967","franciscop","I put a picture of some chicken breasts and it didn't recognize it, is it a feature? Joke aside, incredible work here. Did you do everything from scratch or used some library to…",{"value":133,"source":59,"evidence":134},"Which question the classifier answers: primary subject or any bird present",[135],{"id":53,"by":54,"text":55},[137,148,155],{"value":138,"source":59,"evidence":139},"Clarifai image recognition",[140,144],{"id":141,"by":142,"text":143},"8485534","vinayan3","http:\u002F\u002Fi.imgur.com\u002FSvn2bZ4.jpg Also, Matt Zeiler runs an image recognition startup which the image above was generated from. Check them out at http:\u002F\u002Fclarifai.com\u002F",{"id":145,"by":146,"text":147},"8484047","Nogwater","Do you just want the neural net, or the tags too? This might not be what you want, but it looks like it could be fun to play with: http:\u002F\u002Fclarifai.com\u002F",{"value":149,"source":59,"evidence":150},"Caffe",[151],{"id":152,"by":153,"text":154},"8484113","ajtulloch","Caffe (and other frameworks) provide exactly this. It's basically: 1) To setup, load a pre-trained AlexNet\u002FOverfeat\u002Fother architecture model (e.g. trained on ILSVRC2012) 2) To…",{"value":156,"source":59,"evidence":157},"CCV",[158],{"id":159,"by":160,"text":161},"8485550","atburrow","Is this something that could be accomplished with the help of CCV? https:\u002F\u002Fgithub.com\u002Fliuliu\u002Fccv",{"comments":37,"answered":37,"key":163},[],{"commenters":165,"max_depth":43,"maker_replies":37,"first_comment_mins":166,"lifespan_hours":167},28,39,23,[169,173,176,179,183,187,189,190,192,195,197,200,202,203,205,207,208,212,213,215,218,219,222,226,231,234,238,242],[170,37,37,171,172,37],"8485371","other\u002Fneutral\u002Fnone","iamwil",[174,37,37,171,175,37],"8485969","zuck9",[177,37,37,171,178,37],"8488727","cbhl",[180,30,37,181,182,37],"8485926","other\u002Fneutral\u002Fidea","erjiang",[184,32,43,185,186,37],"8484849","project\u002Fneutral\u002Fperformance","kowdermeister",[74,43,43,188,75,37],"project\u002Fmixed\u002Fperformance",[141,31,37,171,142,37],[87,18,30,191,88,37],"project\u002Fcritical\u002Fperformance",[193,18,30,191,194,37],"8484741","infinitone",[62,38,18,196,63,37],"project\u002Fpositive\u002Fidea",[129,198,43,199,130,37],7,"maker\u002Fmixed\u002Fperformance",[98,201,30,191,99,37],8,[83,201,30,191,84,37],[53,201,43,204,54,37],"project\u002Fneutral\u002Fidea",[121,206,43,204,122,37],9,[145,206,37,171,146,37],[209,206,37,210,211,37],"8484101","commenter\u002Fneutral\u002Fnone","levlandau",[152,206,37,210,153,37],[91,214,30,191,92,37],10,[216,214,30,191,217,37],"8484202","avalaunch",[159,33,43,204,160,37],[114,220,30,221,115,37],12,"project\u002Fcritical\u002Fidea",[223,220,37,224,225,37],"8485878","commenter\u002Fneutral\u002Fidea","rictic",[227,228,30,229,230,37],"8487823",13,"project\u002Fcritical\u002Fdocs","talmand",[106,232,30,233,107,37],14,"project\u002Fcritical\u002Fdesign",[235,236,30,229,237,37],"8484085",15,"therobot24",[239,240,37,171,241,37],"8484966",16,"azeirah",[243,244,30,233,245,37],"8484539",17,"pbhjpbhj",[],[248,253,258,263,268,272],{"id":249,"name":250,"points":251,"category":252},"8464074","RemoteCoder.io",220,"web_saas",{"id":254,"name":255,"points":256,"category":257},"8466023","knowyour4",202,"infrastructure",{"id":259,"name":260,"points":261,"category":262},"8471161","Sublime Text Book",163,"learning_science",{"id":264,"name":265,"points":266,"category":267},"8487809","Appetize.io",147,"dev_tools",{"id":269,"name":270,"points":271,"category":267},"8463560","Maim",124,{"id":273,"name":274,"points":275,"category":276},"8486178","Luakernel",115,"languages",false,"v2",{"id":280,"name":5,"line":6,"ai":277,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":281,"top":18,"kw":282,"maker":11,"domain":10,"tier":19,"attempts":37,"strip":283,"url":9,"mix":284,"praise":71,"objection":80,"sub":21},8483763,-0.45,[24,25,21,26],"0000330115311330001131011101",[30,31,32,33],1794036524078]