{"id":105302,"date":"2022-10-13T15:36:48","date_gmt":"2022-10-13T13:36:48","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/otkryt-kod-sistemy-mashinnogo-obucheniya-dlya-generaczii-realistichnyh-dvizhenij-cheloveka"},"modified":"2022-10-13T15:36:48","modified_gmt":"2022-10-13T13:36:48","slug":"otkryt-kod-sistemy-mashinnogo-obucheniya-dlya-generaczii-realistichnyh-dvizhenij-cheloveka","status":"publish","type":"post","link":"https:\/\/prohoster.info\/da\/blog\/news\/otkryt-kod-sistemy-mashinnogo-obucheniya-dlya-generaczii-realistichnyh-dvizhenij-cheloveka","title":{"rendered":"Koden til et maskinl\u00e6ringssystem til generering af realistiske menneskelige bev\u00e6gelser er blevet offentliggjort","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

En gruppe forskere fra Tel Aviv Universitet har offentliggjort kildekoder relateret til systemet for maskinl\u00e6ring MDM (Motion Diffusion Model), som g\u00f8r det muligt at generere realistiske menneskelige bev\u00e6gelser. Koden er skrevet i Python med brug af frameworket PyTorch og distribueres under MIT-licensen. Til eksperimenterne kan man bruge b\u00e5de f\u00e6rdige modeller og tr\u00e6ne modeller selv ved hj\u00e6lp af de tilbudte scripts, f.eks. ved at bruge samlingen af 3D-billeder af mennesker HumanML3D. Systemet kr\u00e6ver et GPU, der underst\u00f8tter CUDA til tr\u00e6ning. <\/p>\n

Anvendelsen af traditionelle metoder til at animere menneskelige bev\u00e6gelser er vanskeliggjort af kompleksiteten ved det store udvalg af mulige bev\u00e6gelser og vanskelighederne ved at beskrive dem formelt, samt den store f\u00f8lsomhed i menneskelig perception over for unaturlige bev\u00e6gelser. Tidligere fors\u00f8g p\u00e5 at bruge generative modeller af maskinl\u00e6ring har haft problemer med kvalitet og begr\u00e6nset udtryksfuldhed. <\/p>\n

I det foresl\u00e5ede system er der gjort et fors\u00f8g p\u00e5 at anvende diffusionsmodeller til generering af bev\u00e6gelser, som i sit v\u00e6sen er bedre egnet til simulering af menneskelige bev\u00e6gelser, men som ikke er uden ulemper, s\u00e5som h\u00f8je krav til computerenheder og kompleksitet i styringen. For at minimere ulemperne ved diffusionsmodeller anvendes en neural netv\u00e6rksarkitektur kaldet 'transformer' i MDM, og der prognoseres p\u00e5 m\u00f8nstre i stedet for st\u00f8j p\u00e5 hvert trin, hvilket g\u00f8r det lettere at forhindre anomalier s\u00e5som tab af kontakt mellem fod og overflade. <\/p>\n

For at styre genereringen er der mulighed for at anvende en tekstbeskrivelse af handlinger p\u00e5 et naturligt sprog (for eksempel 'personen g\u00e5r fremad og b\u00f8jer sig for at samle noget op fra jorden') eller bruge standardhandlinger s\u00e5som 'l\u00f8b' og 'spring'. Systemet kan ogs\u00e5 anvendes til at redigere bev\u00e6gelser og supplere manglende detaljer. Forskere har gennemf\u00f8rt test, hvor deltagerne skulle v\u00e6lge det mere kvalitetsbeviste resultat fra flere muligheder \u2014 i 42% af tilf\u00e6ldene foretrak folk de syntetiserede bev\u00e6gelser fremfor de reale.

\r\n \"Afspil\r\n
<\/div>\r\n <\/div><\/center>
\n
Kilde: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0422\u0435\u043b\u044c-\u0410\u0432\u0438\u0432\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f MDM (Motion Diffusion Model), \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0435\u0439 \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0435 \u0434\u0432\u0438\u0436\u0435\u043d\u0438\u044f \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430. \u041a\u043e\u0434 \u043d\u0430\u043f\u0438\u0441\u0430\u043d \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python \u0441 \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 MIT. \u0414\u043b\u044f \u043f\u0440\u043e\u0432\u0435\u0434\u0435\u043d\u0438\u044f \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u043e\u0432 \u043c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043a\u0430\u043a \u0433\u043e\u0442\u043e\u0432\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438, \u0442\u0430\u043a \u0438 \u043f\u0440\u043e\u0432\u0435\u0441\u0442\u0438 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043a\u0443 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0441\u0430\u043c\u043e\u0441\u0442\u043e\u044f\u0442\u0435\u043b\u044c\u043d\u043e \u043f\u0440\u0438 \u043f\u043e\u043c\u043e\u0449\u0438 \u043f\u0440\u0435\u0434\u043b\u0430\u0433\u0430\u0435\u043c\u044b\u0445 \u0441\u043a\u0440\u0438\u043f\u0442\u043e\u0432, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440, […]<\/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":[702],"tags":[],"class_list":["post-105302","post","type-post","status-publish","format-standard","hentry","category-news"],"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\udd47Koden til maskinl\u00e6ringssystemet til generation af realistiske menneskelige bev\u00e6gelser er blevet \u00e5bnet | ProHoster","description":"En gruppe forskere fra Tel Aviv Universitet har \u00e5bnet de originale tekster relateret til MDM (Motion Diffusion Model) maskinl\u00e6ringssystemet, der g\u00f8r det muligt at generere realistiske menneskelige bev\u00e6gelser.","canonical_url":"https:\/\/prohoster.info\/da\/blog\/news\/otkryt-kod-sistemy-mashinnogo-obucheniya-dlya-generaczii-realistichnyh-dvizhenij-cheloveka","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"da_DK","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\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 \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 \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0445 \u0434\u0432\u0438\u0436\u0435\u043d\u0438\u0439 \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430 | ProHoster","og:description":"\u0413\u0440\u0443\u043f\u043f\u0430 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0438\u0437 \u0422\u0435\u043b\u044c-\u0410\u0432\u0438\u0432\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f MDM (Motion Diffusion Model), \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0435\u0439 \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0440\u0435\u0430\u043b\u0438\u0441\u0442\u0438\u0447\u043d\u044b\u0435 \u0434\u0432\u0438\u0436\u0435\u043d\u0438\u044f \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430.","og:url":"https:\/\/prohoster.info\/da\/blog\/news\/otkryt-kod-sistemy-mashinnogo-obucheniya-dlya-generaczii-realistichnyh-dvizhenij-cheloveka","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":"2022-10-13T13:36:48+00:00","article:modified_time":"2022-10-13T13:36:48+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts\/105302","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/comments?post=105302"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/posts\/105302\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/media?parent=105302"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/categories?post=105302"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/da\/wp-json\/wp\/v2\/tags?post=105302"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}