{"id":101605,"date":"2021-10-12T16:22:58","date_gmt":"2021-10-12T14:23:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz"},"modified":"2021-10-12T16:22:58","modified_gmt":"2021-10-12T14:23:00","slug":"nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz","title":{"rendered":"Az NVIDIA megnyitotta a StyleGAN3 k\u00f3dj\u00e1t, amely egy fejlett g\u00e9pi tanul\u00e1si rendszer az arcok szint\u00e9zis\u00e9hez","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Az NVIDIA k\u00f6zz\u00e9tette a StyleGAN3 forr\u00e1sk\u00f3dj\u00e1t, egy generat\u00edv ellens\u00e9ges neur\u00e1lis h\u00e1l\u00f3zaton (GAN) alapul\u00f3 g\u00e9pi tanul\u00e1si rendszert, amely a realisztikus emberi arcok k\u00e9peinek szint\u00e9zis\u00e9re \u00f6sszpontos\u00edt. A k\u00f3d Python nyelven k\u00e9sz\u00fclt a PyTorch keretrendszer haszn\u00e1lat\u00e1val, \u00e9s az NVIDIA Forr\u00e1sk\u00f3d Licenc alatt terjesztik, amely kereskedelmi c\u00e9l\u00fa felhaszn\u00e1l\u00e1sra vonatkoz\u00f3 korl\u00e1toz\u00e1sokat tartalmaz.      <\/p>\n<p>K\u00e9sz, el\u0151k\u00e9pzett modellek is rendelkez\u00e9sre \u00e1llnak a Flickr-Faces-HQ (FFHQ) gy\u0171jtem\u00e9nyen, amely 70 ezer magas sz\u00ednvonal\u00fa (1024&#215;1024) PNG-form\u00e1tum\u00fa emberi arck\u00e9pet tartalmaz. Ezen k\u00edv\u00fcl van olyan modell, amely az AFHQv2 (\u00e1llatok arck\u00e9pei) \u00e9s a Metfaces (klasszikus festm\u00e9nyek portr\u00e9i) gy\u0171jtem\u00e9nyek alapj\u00e1n k\u00e9sz\u00fclt. A fejleszt\u00e9s sor\u00e1n a hangs\u00faly az arcokon van, de a rendszer k\u00e9pes b\u00e1rminem\u0171 objektumok, p\u00e9ld\u00e1ul t\u00e1jak \u00e9s aut\u00f3k gener\u00e1l\u00e1s\u00e1ra is. Tov\u00e1bb\u00e1 eszk\u00f6z\u00f6ket biztos\u00edtanak a felhaszn\u00e1l\u00f3k saj\u00e1t k\u00e9pkollekci\u00f3ik alapj\u00e1n t\u00f6rt\u00e9n\u0151 \u00f6n\u00e1ll\u00f3 neur\u00e1lis h\u00e1l\u00f3zati tan\u00edt\u00e1s\u00e1hoz. A m\u0171k\u00f6d\u00e9shez egy vagy t\u00f6bb NVIDIA grafikus k\u00e1rtya sz\u00fcks\u00e9ges (aj\u00e1nlott a GPU Tesla V100 vagy A100), legal\u00e1bb 12 GB RAM, PyTorch 1.9 \u00e9s CUDA 11.1+ eszk\u00f6zk\u00e9szlet. A gener\u00e1lt arck\u00e9pek mesters\u00e9ges jelleg\u00e9nek meghat\u00e1roz\u00e1s\u00e1ra egy speci\u00e1lis detektort fejlesztenek.        <\/p>\n<p>A rendszer lehet\u0151v\u00e9 teszi \u00faj arcok k\u00e9peinek szint\u00e9zis\u00e9t t\u00f6bb arc jellemz\u0151inek interpol\u00e1l\u00e1sa alapj\u00e1n, kombin\u00e1lva azok tulajdons\u00e1gait, \u00e9s az elk\u00e9sz\u00edtett k\u00e9pet az \u00e9letkor, nem, hajhossz, mosoly t\u00edpusa, orr form\u00e1ja, b\u0151rsz\u00edn, szem\u00fcveg \u00e9s f\u00e9nyk\u00e9pez\u00e9si sz\u00f6g ig\u00e9nyeire is alak\u00edtva. A gener\u00e1tor \u00fagy tekinti a k\u00e9pet, mint st\u00edlusok gy\u0171jtem\u00e9ny\u00e9t, automatikusan elk\u00fcl\u00f6n\u00edti a jellemz\u0151 r\u00e9szleteket (\u00f6n\u00e1ll\u00f3 \u00e1rny\u00e9kok, haj, szem\u00fcveg) a k\u00f6z\u00f6s, magas szint\u0171 attrib\u00fatumokt\u00f3l (testtart\u00e1s, nem, \u00e9letkor), \u00e9s lehet\u0151v\u00e9 teszi ezek tetsz\u0151leges kombin\u00e1l\u00e1s\u00e1t a domin\u00e1l\u00f3 tulajdons\u00e1gok s\u00falyoz\u00e1s\u00e1val. Ennek eredm\u00e9nyek\u00e9nt olyan k\u00e9pek gener\u00e1l\u00f3dnak, amelyek l\u00e1tsz\u00f3lag megk\u00fcl\u00f6nb\u00f6ztethetetlenek a val\u00f3di f\u00e9nyk\u00e9pekt\u0151l.     <center><img decoding=\"async\" alt=\"Az NVIDIA megnyitotta a StyleGAN3 k\u00f3dj\u00e1t, amely egy fejlett g\u00e9pi tanul\u00e1si rendszer az arcok szint\u00e9zis\u00e9hez\" src=\"\/wp-content\/uploads\/2021\/10\/94ecac7b420fcd6b3d164134b830e147.jpg\" style=\"display:block;margin: 0 auto;\" \/><\/center>      <\/p>\n<p>A StyleGAN technol\u00f3gia els\u0151 verzi\u00f3j\u00e1t 2019-ben tett\u00e9k k\u00f6zz\u00e9, amelyet 2020-ban egy tov\u00e1bbfejlesztett StyleGAN2 verzi\u00f3 k\u00f6vetett, amely lehet\u0151v\u00e9 tette a k\u00e9pek min\u0151s\u00e9g\u00e9nek jav\u00edt\u00e1s\u00e1t \u00e9s bizonyos artefaktumok elt\u00fcntet\u00e9s\u00e9t. A rendszer statikus maradt, azaz nem tette lehet\u0151v\u00e9 a re\u00e1lis anim\u00e1ci\u00f3 \u00e9s arcmozg\u00e1s el\u00e9r\u00e9s\u00e9t. A StyleGAN3 fejleszt\u00e9se sor\u00e1n a f\u0151 c\u00e9l az volt, hogy a technol\u00f3gi\u00e1t anim\u00e1ci\u00f3k \u00e9s vide\u00f3k haszn\u00e1lat\u00e1ra alkalmazz\u00e1k.    <\/p>\n<p>A StyleGAN3 \u00fajragondolt k\u00e9pgener\u00e1l\u00f3 architekt\u00far\u00e1t alkalmaz, amely mentes az aliasing-t\u00f3l, \u00e9s \u00faj tanul\u00e1si szcen\u00e1ri\u00f3kat k\u00edn\u00e1l a neur\u00e1lis h\u00e1l\u00f3 sz\u00e1m\u00e1ra. \u00daj seg\u00e9dprogramok ker\u00fcltek bele az interakt\u00edv vizualiz\u00e1ci\u00f3hoz (visualizer.py), elemz\u00e9shez (avg_spectra.py) \u00e9s vide\u00f3 gener\u00e1l\u00e1s\u00e1hoz (gen_video.py). A megval\u00f3s\u00edt\u00e1s sor\u00e1n cs\u00f6kkentett\u00e9k a mem\u00f3riafogyaszt\u00e1st \u00e9s felgyors\u00edtott\u00e1k a tan\u00edt\u00e1si folyamatot.      <center><img decoding=\"async\" alt=\"Az NVIDIA megnyitotta a StyleGAN3 k\u00f3dj\u00e1t, amely egy fejlett g\u00e9pi tanul\u00e1si rendszer az arcok szint\u00e9zis\u00e9hez\" src=\"\/wp-content\/uploads\/2021\/10\/e8a68abee5a637f9be1b9ca79652e043.jpg\" style=\"display:block;margin: 0 auto;\" \/><\/center>    <\/p>\n<p>A StyleGAN3 architekt\u00fara kulcsfontoss\u00e1g\u00fa jellemz\u0151je a neur\u00e1lis h\u00e1l\u00f3zatban l\u00e9v\u0151 \u00f6sszes jel folyamatos folyamatk\u00e9nt val\u00f3 \u00e9rtelmez\u00e9s\u00e9re val\u00f3 \u00e1tt\u00e9r\u00e9s, amely lehet\u0151v\u00e9 tette a r\u00e9szletek kialak\u00edt\u00e1s\u00e1n\u00e1l az abszol\u00fat koordin\u00e1t\u00e1khoz nem k\u00f6t\u00f6tt, hanem a megjelen\u00edtett objektumok fel\u00fclet\u00e9hez r\u00f6gz\u00edtett relat\u00edv poz\u00edci\u00f3k manipul\u00e1l\u00e1s\u00e1t. A StyleGAN \u00e9s a StyleGAN2 eset\u00e9ben a pixelekhez val\u00f3 r\u00f6gz\u00edt\u00e9s gener\u00e1l\u00e1s k\u00f6zben probl\u00e9m\u00e1kat okozott a dinamikus vizualiz\u00e1ci\u00f3 sor\u00e1n, p\u00e9ld\u00e1ul a k\u00e9pek mozg\u00e1sa k\u00f6zben a kism\u00e9ret\u0171 r\u00e9szletek, mint a r\u00e1ncok \u00e9s hajsz\u00e1lak, \u00fagy t\u0171nt, hogy k\u00fcl\u00f6n mozognak az arc t\u00f6bbi r\u00e9sz\u00e9t\u0151l. A StyleGAN3 ezekre a probl\u00e9m\u00e1kra megold\u00e1st k\u00edn\u00e1l, \u00e9s a technol\u00f3gia teljesen alkalmas lett vide\u00f3k l\u00e9trehoz\u00e1s\u00e1ra.        <center>  <video controls=\"\" style=\"width: 640px; height: 480px; max-width:100%\"><source src=\"https:\/\/nvlabs-fi-cdn.nvidia.com\/stylegan3\/videos\/video_0_ffhq_cinemagraphs.mp4\" type=\"video\/mp4\"><\/video>  <\/center>  <center>  <video controls=\"\" style=\"width: 640px; height: 480px; max-width:100%\"><source src=\"https:\/\/nvlabs-fi-cdn.nvidia.com\/stylegan3\/videos\/video_1_ffhq_cinemagraphs.mp4\" type=\"video\/mp4\"><\/video>  <\/center>    <center>  <video controls=\"\" style=\"width: 640px; height: 480px; max-width:100%\"><source src=\"https:\/\/nvlabs-fi-cdn.nvidia.com\/stylegan3\/videos\/video_2_metfaces_interpolations.mp4\" type=\"video\/mp4\"><\/video>  <\/center>    <center>  <video controls=\"\" style=\"width: 640px; height: 480px; max-width:100%\"><source src=\"https:\/\/nvlabs-fi-cdn.nvidia.com\/stylegan3\/videos\/video_8_internal_activations.mp4\" type=\"video\/mp4\"><\/video>  <\/center>    <center>  <video controls=\"\" style=\"width: 640px; height: 480px; max-width:100%\"><source src=\"https:\/\/nvlabs-fi-cdn.nvidia.com\/stylegan3\/videos\/video_5_figure_3_left_equivariance_quality.mp4\" type=\"video\/mp4\"><\/video>  <\/center>      <\/p>\n<p>Tov\u00e1bbi \u00e9rdekess\u00e9g, hogy az NVIDIA \u00e9s a Microsoft bejelentette a legnagyobb MT-NLG nyelvi modell l\u00e9trehoz\u00e1s\u00e1t, amely egy m\u00e9ly neur\u00e1lis h\u00e1l\u00f3zatra \u00e9p\u00fcl \u00e9s \"transformer\" architekt\u00far\u00e1val rendelkezik. A modell 530 milli\u00e1rd param\u00e9tert \u00f6lel fel, \u00e9s a tan\u00edt\u00e1shoz egy 4480 GPU-b\u00f3l \u00e1ll\u00f3 klasztert haszn\u00e1ltak fel (560 <a class=\"wpil_keyword_link\" href=\"https:\/\/prohoster.info\/hu\/server\/\"   title=\"szerverek\" data-wpil-keyword-link=\"linked\"  data-wpil-monitor-id=\"1612\">szerverek<\/a> A modell alkalmaz\u00e1si ter\u00fcletei k\u00f6z\u00f6tt szerepelnek a term\u00e9szetes nyelv feldolgoz\u00e1s\u00e1val kapcsolatos feladatok, mint p\u00e9ld\u00e1ul a befejezetlen mondatok el\u0151rejelz\u00e9se, k\u00e9rd\u00e9sekre adott v\u00e1laszok, olvasott sz\u00f6veg meg\u00e9rt\u00e9se, term\u00e9szetes nyelv\u0171 k\u00f6vetkeztet\u00e9sek levon\u00e1sa \u00e9s a szavak jelent\u00e9s\u00e9nek t\u00f6bbsz\u00f6r\u00f6ss\u00e9 t\u00e9tel\u00e9nek kezel\u00e9se.    <center><img decoding=\"async\" alt=\"Az NVIDIA megnyitotta a StyleGAN3 k\u00f3dj\u00e1t, amely egy fejlett g\u00e9pi tanul\u00e1si rendszer az arcok szint\u00e9zis\u00e9hez\" src=\"\/wp-content\/uploads\/2021\/10\/bf51e995a3b53046c8fa048e4f6bfd12.jpg\" style=\"display:block;margin: 0 auto;\" \/><\/center><br \/>\n<br \/>Forr\u00e1s: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=55952\">opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f NVIDIA \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e-\u0441\u043e\u0441\u0442\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 (GAN), \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u043e\u0439 \u043d\u0430 \u0441\u0438\u043d\u0442\u0435\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0445 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446 \u043b\u044e\u0434\u0435\u0439. \u041a\u043e\u0434 \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u0444\u0440\u0435\u0439\u043c\u0432\u043e\u0440\u043a\u0430 PyTorch \u0438 \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u0435\u0442\u0441\u044f \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 NVIDIA Source Code License, \u043d\u0430\u043a\u043b\u0430\u0434\u044b\u0432\u0430\u044e\u0449\u0435\u0439 \u043e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u0438\u0435 \u043d\u0430 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u0432 \u043a\u043e\u043c\u043c\u0435\u0440\u0447\u0435\u0441\u043a\u0438\u0445 \u0446\u0435\u043b\u044f\u0445. \u0414\u043b\u044f \u0437\u0430\u0433\u0440\u0443\u0437\u043a\u0438 \u0442\u0430\u043a\u0436\u0435 \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b \u0433\u043e\u0442\u043e\u0432\u044b\u0435 \u043d\u0430\u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438, \u043e\u0431\u0443\u0447\u0435\u043d\u043d\u044b\u0435 \u043d\u0430 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":101606,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-101605","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.3 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f NVIDIA \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e-\u0441\u043e\u0441\u0442\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 (GAN), \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u043e\u0439 \u043d\u0430 \u0441\u0438\u043d\u0442\u0435\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0445 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446 \u043b\u044e\u0434\u0435\u0439.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/hu\/blog\/news\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"hu_HU\" \/>\n\t\t<meta property=\"og:site_name\" content=\"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\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47NVIDIA \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043a\u043e\u0434 StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u0438\u043d\u0442\u0435\u0437\u0430 \u043b\u0438\u0446 | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f NVIDIA \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e-\u0441\u043e\u0441\u0442\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 (GAN), \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u043e\u0439 \u043d\u0430 \u0441\u0438\u043d\u0442\u0435\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0445 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446 \u043b\u044e\u0434\u0435\u0439.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/hu\/blog\/news\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2021-10-12T14:23:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2021-10-12T14:23:00+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Az NVIDIA megnyitotta a StyleGAN3 k\u00f3dj\u00e1t, a g\u00e9pi tanul\u00e1s rendszer\u00e9t az arcok szint\u00e9zis\u00e9re | ProHoster","description":"Az NVIDIA k\u00f6zz\u00e9tette a StyleGAN3 forr\u00e1ssz\u00f6veg\u00e9t, amely egy generat\u00edv ellenfelek \u00e1ltal vez\u00e9relt neur\u00e1lis h\u00e1l\u00f3zat (GAN) alap\u00fa g\u00e9pi tanul\u00e1si rendszer, amely a val\u00f3s\u00e1gh\u0171 emberi arcok szint\u00e9zis\u00e9re ir\u00e1nyul.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz","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\udd47NVIDIA \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043a\u043e\u0434 StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u0438\u043d\u0442\u0435\u0437\u0430 \u043b\u0438\u0446 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f NVIDIA \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b StyleGAN3, \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u043e-\u0441\u043e\u0441\u0442\u044f\u0437\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438 (GAN), \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u043e\u0439 \u043d\u0430 \u0441\u0438\u043d\u0442\u0435\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0445 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446 \u043b\u044e\u0434\u0435\u0439.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/nvidia-otkryla-kod-stylegan3-sistemy-mashinnogo-obucheniya-dlya-sinteza-licz","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":"2021-10-12T14:23:00+00:00","article:modified_time":"2021-10-12T14:23:00+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"101605","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":"","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":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-10-12 14:46:53","updated":"2026-02-09 16:51:03","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\/101605","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=101605"}],"version-history":[{"count":1,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/101605\/revisions"}],"predecessor-version":[{"id":158856,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/101605\/revisions\/158856"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/101606"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=101605"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=101605"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=101605"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}