{"id":29895,"date":"2019-10-31T21:32:30","date_gmt":"2019-10-31T18:32:30","guid":{"rendered":"https:\/\/prohoster.info\/blog\/nejroset-ot-nvidia-prevrashhaet-prostejshie-nabroski-v-krasivye-pejzazhi\/"},"modified":"2019-10-31T21:32:30","modified_gmt":"2019-10-31T18:32:30","slug":"nejroset-ot-nvidia-prevrashhaet-prostejshie-nabroski-v-krasivye-pejzazhi","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/nejroset-ot-nvidia-prevrashhaet-prostejshie-nabroski-v-krasivye-pejzazhi","title":{"rendered":"Az Nvidia neur\u00e1lis h\u00e1l\u00f3zata a legegyszer\u0171bb v\u00e1zlatokat gy\u00f6ny\u00f6r\u0171 t\u00e1jakk\u00e1 alak\u00edtja.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

\"Az
\nA doh\u00e1nyz\u00f3 \u00e9s az eg\u00e9szs\u00e9ges ember v\u00edzes\u00e9se.<\/p>\n

Mindannyian tudjuk, hogyan kell baglyot rajzolni. El\u0151sz\u00f6r egy ov\u00e1list kell rajzolni, azt\u00e1n egy k\u00f6rt, \u00e9s v\u00e9g\u00fcl \u2014 k\u00e9sz a gy\u00f6ny\u00f6r\u0171 bagoly. Persze, ez csak egy vicc, nagyon r\u00e9gi, de az Nvidia m\u00e9rn\u00f6kei azon dolgoztak, hogy a fant\u00e1zia val\u00f3ra v\u00e1ljon. <\/p>\n

\u00daj fejleszt\u00e9s<\/a><\/noindex>, amelyet GauGAN-nak h\u00edvnak, leny\u0171g\u00f6z\u0151 t\u00e1jakat hoz l\u00e9tre nagyon egyszer\u0171 v\u00e1zlatokb\u00f3l (val\u00f3ban egyszer\u0171ek \u2014 karik\u00e1k, vonalak \u00e9s ennyi). Term\u00e9szetesen a fejleszt\u00e9s alapja a modern technol\u00f3gia \u2014 nevezetesen a generat\u00edv ellen\u00e1ll\u00f3 neur\u00e1lis h\u00e1l\u00f3zatok.
\n<\/a><\/noindex>
\nA GauGAN lehet\u0151v\u00e9 teszi sz\u00ednes virtu\u00e1lis vil\u00e1gok l\u00e9trehoz\u00e1s\u00e1t \u2014 \u00e9s nemcsak sz\u00f3rakoz\u00e1s c\u00e9lj\u00e1b\u00f3l, hanem munk\u00e1ra is. \u00cdgy az \u00e9p\u00edt\u00e9szek, t\u00e1j\u00e9p\u00edt\u00e9szek \u00e9s j\u00e1t\u00e9kfejleszt\u0151k \u2014 mindannyian hasznos dolgot mer\u00edthetnek bel\u0151le. A mesters\u00e9ges intelligencia azonnal \u201emeg\u00e9rti\u201d, mit akar az ember, \u00e9s rengeteg r\u00e9szlettel eg\u00e9sz\u00edti ki az eredeti \u00f6tletet. <\/p>\n

\u201eA design fejleszt\u00e9s\u00e9nek brainstormingja sokkal k\u00f6nnyebb a GauGAN seg\u00edts\u00e9g\u00e9vel, mivel az intelligens ecset k\u00e9pes kieg\u00e9sz\u00edteni az eredeti v\u00e1zlatot, \u00e9s min\u0151s\u00e9gi k\u00e9peket ad hozz\u00e1\u201d \u2014 nyilatkozta a GauGAN egyik fejleszt\u0151je.<\/p>\n

A felhaszn\u00e1l\u00f3k ezzel az eszk\u00f6zzel m\u00f3dos\u00edthatj\u00e1k az eredeti elk\u00e9pzel\u00e9st, \u00e1talak\u00edthatj\u00e1k a t\u00e1jat vagy m\u00e1s k\u00e9peket, \u00e9s hozz\u00e1adhatnak eget, homokot, tengert \u00e9s \u00edgy tov\u00e1bb. Minden, amit csak szeretne, \u00e9s a hozz\u00e1ad\u00e1s mind\u00f6ssze p\u00e1r m\u00e1sodpercet vesz ig\u00e9nybe.<\/p>\n

A neur\u00e1lis h\u00e1l\u00f3zatot t\u00f6bb milli\u00f3 k\u00e9pb\u0151l \u00e1ll\u00f3 adatb\u00e1zissal k\u00e9pezt\u00e9k. Ennek k\u00f6sz\u00f6nhet\u0151en a rendszer meg\u00e9rti, mit akar az ember, \u00e9s hogyan \u00e9rheti el a k\u00edv\u00e1nt eredm\u00e9nyt. R\u00e1ad\u00e1sul a neur\u00e1lis h\u00e1l\u00f3zat nem feledkezik meg a legkisebb r\u00e9szletekr\u0151l sem. P\u00e9ld\u00e1ul, ha v\u00e1zlatosan egy tavat rajzolunk \u00e9s mellette n\u00e9h\u00e1ny f\u00e1t, akkor a t\u00e1j \u00e9letre kelt\u00e9se ut\u00e1n az \u00f6sszes k\u00f6zeli objektum visszat\u00fckr\u00f6z\u0151dik a t\u00f3 viz\u00e9ben.<\/p>\n

A rendszer megadhatja, hogy a l\u00e1that\u00f3 fel\u00fclet hogyan n\u00e9zzen ki \u2014 lehet f\u00fcves, havas, v\u00edz vagy homok bor\u00edtotta. Mindezt egy m\u00e1sodperc alatt \u00e1talak\u00edthatjuk, \u00edgy a h\u00f3 homokk\u00e1 v\u00e1lik, \u00e9s a havas pusztas\u00e1g helyett a m\u0171v\u00e9sz egy sivatagi t\u00e1jat kap. <\/p>\n

\u201eEz olyan, mint egy sz\u00ednez\u0151k\u00f6nyv, amely azt mondja, hol kell elhelyezni a f\u00e1t, hol a napot \u00e9s hol az eget. Ezut\u00e1n, az alapfeladat ut\u00e1n, a neur\u00e1lis h\u00e1l\u00f3zat \u00e9letre kelti a k\u00e9pet, hozz\u00e1adja a sz\u00fcks\u00e9ges r\u00e9szleteket \u00e9s text\u00far\u00e1kat, valamint kidolgozza a t\u00fckr\u00f6z\u0151d\u00e9seket. Mindez val\u00f3s k\u00e9peken alapul\u201c - mondja az egyik fejleszt\u0151. <\/p>\n

\r\n \"Vide\u00f3\r\n
<\/div>\r\n <\/div><\/center>
\nB\u00e1r a rendszernek hi\u00e1nyzik a val\u00f3s vil\u00e1g \u201emeg\u00e9rt\u00e9se\u201c, m\u00e9gis leny\u0171g\u00f6z\u0151 t\u00e1jakat hoz l\u00e9tre. Ennek oka, hogy itt k\u00e9t neur\u00e1lis h\u00e1l\u00f3zatot haszn\u00e1lnak: egy gener\u00e1tort \u00e9s egy diszkrimin\u00e1tort. A gener\u00e1tor l\u00e9trehozza a k\u00e9pet, \u00e9s megmutatja azt a diszkrimin\u00e1tornak, aki a kor\u00e1bban l\u00e1tott milli\u00f3k alapj\u00e1n kiv\u00e1lasztja a legrealisztikusabb verzi\u00f3kat. <\/p>\n

\u00c9ppen ez\u00e9rt a gener\u00e1tor \u201etudja\u201c, hol kell lennie a t\u00fckr\u00f6z\u0151d\u00e9seknek. \u00c9rdemes megjegyezni, hogy az eszk\u00f6z rendk\u00edv\u00fcl rugalmas \u00e9s sz\u00e1mos be\u00e1ll\u00edt\u00e1ssal rendelkezik. \u00cdgy ezzel lehet festm\u00e9nyeket k\u00e9sz\u00edteni, alkalmazkodva egy bizonyos m\u0171v\u00e9sz st\u00edlus\u00e1hoz, vagy egyszer\u0171en csak j\u00e1tszani a gyors napfelkelt\u00e9k vagy naplement\u00e9k hozz\u00e1ad\u00e1s\u00e1val. <\/p>\n

A fejleszt\u0151k azt \u00e1ll\u00edtj\u00e1k, hogy a rendszer nem egyszer\u0171en \u00f6sszerak valahonnan k\u00e9peket, \u00e9s \u00edgy kapja meg az eredm\u00e9nyt. Nem, minden kapott \u201ek\u00e9p\u201c gener\u00e1lt. Vagyis a neur\u00e1lis h\u00e1l\u00f3zat \u201ealkot\u201c, mint egy igazi m\u0171v\u00e9sz (vagy ak\u00e1r jobb).<\/p>\n

M\u00e9g nem \u00e1ll rendelkez\u00e9sre a program szabadon, de hamarosan kipr\u00f3b\u00e1lhat\u00f3 lesz. Ezt a GPU Technology Conference 2019 technol\u00f3giai ki\u00e1ll\u00edt\u00e1son lehet megtenni, amely jelenleg Kaliforni\u00e1ban zajlik. A szerencs\u00e9sek, akik r\u00e9szt tudtak venni a ki\u00e1ll\u00edt\u00e1son, m\u00e1r tesztelhetik a GauGAN-t.<\/p>\n

A neur\u00e1lis h\u00e1l\u00f3zatokat m\u00e1r r\u00e9g\u00f3ta arra tan\u00edtj\u00e1k, hogy r\u00e9szt vegyenek a kreat\u00edv folyamatban. P\u00e9ld\u00e1ul tavaly n\u00e9h\u00e1ny k\u00f6z\u00fcl\u00fck k\u00e9pes volt 3D modelleket k\u00e9sz\u00edteni<\/a><\/noindex>. R\u00e1ad\u00e1sul a DeepMind fejleszt\u0151i olyan neur\u00e1lis h\u00e1l\u00f3zatot tan\u00edtottak, amely k\u00e9pes a h\u00e1romdimenzi\u00f3s t\u00e9r \u00e9s objektumok helyre\u00e1ll\u00edt\u00e1s\u00e1ra rajzok, f\u00e9nyk\u00e9pek \u00e9s v\u00e1zlatok alapj\u00e1n. Egy egyszer\u0171 figura \u00fajraalkot\u00e1s\u00e1hoz elegend\u0151 egy k\u00e9p, bonyolultabb objektumok l\u00e9trehoz\u00e1s\u00e1hoz \u00f6t k\u00e9p sz\u00fcks\u00e9ges a \u201ek\u00e9pz\u00e9shez\u201d.<\/p>\n

Ami a GauGAN-t illeti, ez az eszk\u00f6z nyilv\u00e1nval\u00f3an m\u00e9lt\u00f3 kereskedelmi alkalmaz\u00e1st fog tal\u00e1lni - sok \u00fczleti \u00e9s tudom\u00e1nyos ter\u00fcleten van sz\u00fcks\u00e9g hasonl\u00f3 szolg\u00e1ltat\u00e1sokra.<\/p>\n

Forr\u00e1s: habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0412\u043e\u0434\u043e\u043f\u0430\u0434 \u043a\u0443\u0440\u0438\u043b\u044c\u0449\u0438\u043a\u0430 \u0438 \u0432\u043e\u0434\u043e\u043f\u0430\u0434 \u0437\u0434\u043e\u0440\u043e\u0432\u043e\u0433\u043e \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430 \u0412\u0441\u0435 \u043c\u044b \u0437\u043d\u0430\u0435\u043c, \u043a\u0430\u043a \u043d\u0430\u0440\u0438\u0441\u043e\u0432\u0430\u0442\u044c \u0441\u043e\u0432\u0443. \u041d\u0443\u0436\u043d\u043e \u0441\u043d\u0430\u0447\u0430\u043b\u0430 \u043d\u0430\u0440\u0438\u0441\u043e\u0432\u0430\u0442\u044c \u043e\u0432\u0430\u043b, \u043f\u043e\u0442\u043e\u043c \u0435\u0449\u0435 \u043e\u043a\u0440\u0443\u0436\u043d\u043e\u0441\u0442\u044c, \u043d\u0443 \u0430 \u043f\u043e\u0442\u043e\u043c \u2014 \u043f\u043e\u043b\u0443\u0447\u0430\u0435\u0442\u0441\u044f \u0448\u0438\u043a\u0430\u0440\u043d\u0430\u044f \u0441\u043e\u0432\u0430. \u041a\u043e\u043d\u0435\u0447\u043d\u043e, \u044d\u0442\u043e \u0448\u0443\u0442\u043a\u0430, \u043f\u0440\u0438\u0447\u0435\u043c \u043e\u0447\u0435\u043d\u044c \u0441\u0442\u0430\u0440\u0430\u044f, \u043d\u043e \u0438\u043d\u0436\u0435\u043d\u0435\u0440\u044b Nvidia \u043f\u043e\u0441\u0442\u0430\u0440\u0430\u043b\u0438\u0441\u044c \u0441\u0434\u0435\u043b\u0430\u0442\u044c \u0442\u0430\u043a, \u0447\u0442\u043e\u0431\u044b \u0444\u0430\u043d\u0442\u0430\u0437\u0438\u044f \u0441\u0442\u0430\u043b\u0430 \u0440\u0435\u0430\u043b\u044c\u043d\u043e\u0441\u0442\u044c\u044e. \u041d\u043e\u0432\u0430\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043d\u0430\u0437\u044b\u0432\u0430\u0435\u0442\u0441\u044f GauGAN, \u0441\u043e\u0437\u0434\u0430\u0435\u0442 \u0448\u0438\u043a\u0430\u0440\u043d\u044b\u0435 \u043f\u0435\u0439\u0437\u0430\u0436\u0438 \u0438\u0437 \u043e\u0447\u0435\u043d\u044c \u043f\u0440\u043e\u0441\u0442\u044b\u0445 \u043d\u0430\u0431\u0440\u043e\u0441\u043a\u043e\u0432 (\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0442\u0435\u043b\u044c\u043d\u043e […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-29895","post","type-post","status-publish","format-standard","hentry"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Az Nvidia neur\u00e1lis h\u00e1l\u00f3zata a legegyszer\u0171bb v\u00e1zlatokat is gy\u00f6ny\u00f6r\u0171 t\u00e1jk\u00e9pekk\u00e9 alak\u00edtja | ProHoster","description":"A f\u00fcst\u00f6s v\u00edzes\u00e9s \u00e9s.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/nejroset-ot-nvidia-prevrashhaet-prostejshie-nabroski-v-krasivye-pejzazhi","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u044c \u043e\u0442 Nvidia \u043f\u0440\u0435\u0432\u0440\u0430\u0449\u0430\u0435\u0442 \u043f\u0440\u043e\u0441\u0442\u0435\u0439\u0448\u0438\u0435 \u043d\u0430\u0431\u0440\u043e\u0441\u043a\u0438 \u0432 \u043a\u0440\u0430\u0441\u0438\u0432\u044b\u0435 \u043f\u0435\u0439\u0437\u0430\u0436\u0438 | ProHoster","og:description":"\u0412\u043e\u0434\u043e\u043f\u0430\u0434 \u043a\u0443\u0440\u0438\u043b\u044c\u0449\u0438\u043a\u0430 \u0438.","og:url":"https:\/\/prohoster.info\/hu\/blog\/nejroset-ot-nvidia-prevrashhaet-prostejshie-nabroski-v-krasivye-pejzazhi","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-10-31T18:32:30+00:00","article:modified_time":"2019-10-31T18:32:30+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"29895","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"Article","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-20 22:55:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 03:46:27","updated":"2026-01-20 22:55:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/29895","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=29895"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/29895\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=29895"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=29895"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=29895"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}