[{"data":1,"prerenderedAt":208},["ShallowReactive",2],{"project-19161515":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":29,"sentiment":30,"stance_mix":31,"scored_comments":36,"aspects":37,"strip":39,"post_text":42,"what":43,"said":75,"maker_in_thread":129,"shape":136,"grid":140,"attempts":168,"same_week":169,"maker_shows":32,"maker_hidden":200,"reader_version":201,"card":202},"19161515","Cortex","machine learning infrastructure for developers","title","Show HN: Cortex – machine learning infrastructure for developers","https:\u002F\u002Fgithub.com\u002Fcortexlabs\u002Fcortex","github.com","deliahu",1550149205,2019,86,14,562,2195,26,"notable","ai","ml infrastructure","library",[24,25,26,27,28],"machine learning infrastructure","tensorflow serving","kubernetes ml pipelines","model deployment","declarative ml","roasted",-0.188,{"positive":32,"neutral":33,"mixed":34,"critical":35},1,2,0,4,7,{"idea":38},{"positive":34,"critical":35},[34,32,34,32,34,32,32,34,40,34,40,34,41,34],3,5,null,{"problem":44,"audience":42,"pricing":42,"motivation":42,"time_to_build":42,"stack":51,"openness":74,"stage":74,"team_size":74},{"value":45,"source":46,"evidence":47},"Orchestrating Spark, TensorFlow and other ML workloads without managing infrastructure","maker",[48],{"id":49,"by":11,"text":50},"19177510","The main thing we try to help with is orchestrating Spark, TensorFlow, TensorFlow Serving, and other workloads without requiring you to manage the infrastructure. You’re right…",[52,56,60,64,70],{"value":53,"source":46,"evidence":54},"TensorFlow",[55],{"id":49,"by":11,"text":50},{"value":57,"source":46,"evidence":58},"Spark",[59],{"id":49,"by":11,"text":50},{"value":61,"source":46,"evidence":62},"Kubernetes",[63],{"id":49,"by":11,"text":50},{"value":65,"source":46,"evidence":66},"TensorFlow Serving",[67],{"id":68,"by":11,"text":69},"19177736","We use TesnorFlow serving (https:\u002F\u002Fwww.tensorflow.org\u002Fserving) for serving the trained models. We also run Flask to transform the incoming JSON to match the way the data has been…",{"value":71,"source":46,"evidence":72},"Flask",[73],{"id":68,"by":11,"text":69},"unknown",{"praise":76,"objections":85,"requests":108,"questions":109,"alternatives":124},[77],{"value":78,"source":79,"evidence":80},"Congratulations on the launch","commenter",[81],{"id":82,"by":83,"text":84},"19166660","weitingster","Congrats!",[86,93],{"value":87,"source":79,"evidence":88},"Thin wrapper around tf.estimator with little novelty",[89],{"id":90,"by":91,"text":92},"19177383","ipsum2","I work on ML infrastructure at some big company, so I'm always interested to see whats new in this field. This seems to be a thin wrapper around tf.estimator, which provides a…",{"value":94,"source":79,"evidence":95},"Name clashes with other projects named Cortex",[96,100,104],{"id":97,"by":98,"text":99},"19176282","gleenn","Somewhat unfortunate name clash with the now-back-burnered deep learning framework written in Clojure, also called Cortex: https:\u002F\u002Fgithub.com\u002Foriginrose\u002Fcortex",{"id":101,"by":102,"text":103},"19177567","malkia","Pretty cool name (cortex), but also taken by this project - https:\u002F\u002Fgithub.com\u002Fcortexproject\u002Fcortex - \"A multitenant, horizontally scalable Prometheus as a Service\"",{"id":105,"by":106,"text":107},"19189469","mrmrcoleman","And this from Weaveworks: https:\u002F\u002Fwww.weave.works\u002Foss\u002Fcortex\u002F",[],[110,117],{"value":111,"source":79,"evidence":112},"How does it compare to KubeFlow?",[113],{"id":114,"by":115,"text":116},"19179042","camuel","How does this compare to KubeFlow?",{"value":118,"source":79,"evidence":119},"What infrastructure is used for deployment and serving of models?",[120],{"id":121,"by":122,"text":123},"19177711","doppenhe","curious what kind of infrastructure have you built for deployment, serving and managing models?",[125],{"value":126,"source":79,"evidence":127},"KubeFlow",[128],{"id":114,"by":115,"text":116},{"comments":41,"answered":40,"key":130},[131,134,135],{"id":132,"text":133},"19177513","Thanks for letting us know, we'll take a look",{"id":49,"text":50},{"id":68,"text":69},{"commenters":137,"max_depth":40,"maker_replies":41,"first_comment_mins":138,"lifespan_hours":139},10,564,92,[141,143,147,149,150,154,155,156,158,159,161,162,164,166],[97,34,34,142,98,34],"commenter\u002Fneutral\u002Fnone",[144,34,32,145,146,34],"19176321","project\u002Fcritical\u002Fidea","SlowRobotAhead",[132,34,34,148,11,32],"maker\u002Fneutral\u002Fnone",[101,34,32,145,102,34],[151,34,34,152,153,34],"19178255","other\u002Fneutral\u002Fnone","TaupeRanger",[105,34,32,145,106,34],[90,32,32,145,91,34],[49,32,34,157,11,32],"project\u002Fneutral\u002Fidea",[121,32,40,148,122,34],[68,32,34,160,11,32],"maker\u002Fneutral\u002Fexecution",[114,33,40,157,115,34],[163,33,34,157,11,32],"19179381",[82,40,41,165,83,34],"maker\u002Fpositive\u002Fnone",[167,40,34,148,11,32],"19177511",[],[170,175,180,185,190,195],{"id":171,"name":172,"points":173,"category":174},"19210697","Commento",271,"web_saas",{"id":176,"name":177,"points":178,"category":179},"19200151","IMDB Ratings on Netflix",234,"consumer_social",{"id":181,"name":182,"points":183,"category":184},"19206507","GitNews Web",183,"dev_tools",{"id":186,"name":187,"points":188,"category":189},"19189455","Inlets",146,"infrastructure",{"id":191,"name":192,"points":193,"category":194},"19162876","Scannable Chess Scoresheets",117,"games",{"id":196,"name":197,"points":198,"category":199},"19196352","Summarized Finance \u002F Tech Newsletter",93,"finance_crypto",false,"v2",{"id":203,"name":5,"line":6,"ai":200,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":204,"top":18,"kw":205,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":206,"url":9,"mix":207,"praise":78,"objection":87,"sub":21},19161515,-0.19,[24,25,26,27,28],"01010110303050",[32,33,34,35],1794036574826]