{"id":38448,"date":"2019-10-31T22:23:47","date_gmt":"2019-10-31T19:23:47","guid":{"rendered":"https:\/\/prohoster.info\/blog\/github-otkryl-narabotki-po-primeneniyu-mashinnogo-obucheniya-dlya-poiska-i-analiza-koda\/"},"modified":"2019-10-31T22:23:47","modified_gmt":"2019-10-31T19:23:47","slug":"github-otkryl-narabotki-po-primeneniyu-mashinnogo-obucheniya-dlya-poiska-i-analiza-koda","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hr\/blog\/news\/github-otkryl-narabotki-po-primeneniyu-mashinnogo-obucheniya-dlya-poiska-i-analiza-koda","title":{"rendered":"GitHub je otvorio radove na primjeni strojno u\u010denje za pretra\u017eivanje i analizu koda","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

GitHub predstavio<\/a><\/noindex> projekt CodeSearchNet<\/a><\/noindex>, u sklopu kojeg su pripremljeni modeli strojnog u\u010denja i skupovi podataka potrebni za analizu, klasifikaciju i analizu koda na razli\u010ditim programskim jezicima. CodeSearchNet, analogno ImageNet<\/a><\/noindex>, uklju\u010duje veliku zbirku odlomaka koda, opskrbljenih anotacijama koje formaliziraju radnje koje kod izvr\u0161ava. Komponente za obuku modela i primjeri kori\u0161tenja CodeSearchNet napisani su u Python programskom jeziku koriste\u0107i Tensorflow okvir i distribuira se<\/a><\/noindex> pod MIT licencom.<\/p>\n

Pri izradi CodeSearchNet kori\u0161tene su tehnologije obrade prirodnog jezika, koje omogu\u0107uju sustavima strojnog u\u010denja da uzmu u obzir ne samo sintakti\u010dke zna\u010dajke, ve\u0107 i zna\u010denje radnji koje kod izvr\u0161ava. U GitHub sustavu se koristi<\/a><\/noindex> u eksperimentima s organizacijom semanti\u010dkog pretra\u017eivanja koda koriste\u0107i upite na prirodnom jeziku<\/a><\/noindex> (na primjer, kada se zatra\u017ei «sortiranje popisa nizova», ispisuje se kod s implementacijom odgovaraju\u0107ih algoritama).<\/p>\n

Predlo\u017eeni skup podataka uklju\u010duje vi\u0161e od 2 milijuna parova «kod-komentar», pripremljenih na temelju izvornih tekstova postoje\u0107ih otvorenih knji\u017enica. Kod pokriva cjeloviti izvorni tekst pojedinih funkcija ili metoda, dok komentar opisuje radnje koje funkcija izvr\u0161ava (prikazana je detaljna dokumentacija). Trenutno su skupovi podataka pripremljeni za jezike Python, JavaScript, Ruby, Go, Java i PHP. Pru\u017eeni su primjeri kori\u0161tenja predlo\u017eenih skupova podataka za obuku razli\u010ditih tipova neuronskih mre\u017ea, uklju\u010duju\u0107i Neural-Bag-Of-Words<\/a><\/noindex>, RNN<\/a><\/noindex>, Self-Attention<\/a><\/noindex> (BERT) i 1D-CNN+Self-Attention Hybrid<\/a><\/noindex>.<\/p>\n

Za razvoj mehanizama pretra\u017eivanja na prirodnom jeziku dodatno je pripremljen skup CodeSearchNet Challenge, koji uklju\u010duje
\n99 tipi\u010dnih<\/a><\/noindex> upita s oko 4 tisu\u0107e stru\u010dnih anotacija, koje opisuju najvjerojatnije veze s kodom u skupu podataka CodeSearchNet Corpus, koji obuhva\u0107a oko 6 milijuna metoda i funkcija (veli\u010dina skupa<\/a><\/noindex> oko 20 GB). CodeSearchNet Challenge mo\u017ee poslu\u017eit kao referenca za ocjenu u\u010dinkovitosti razli\u010ditih metoda pretra\u017eivanja koda na prirodnom jeziku. Koriste\u0107i alati Kubeflow<\/a><\/noindex> pripremljen
\nprimjer<\/a><\/noindex> motor za pretra\u017eivanje koda.<\/p>\n

<\/a><\/noindex><\/p>\n

Izvor: opennet.ru<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

GitHub \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b \u043f\u0440\u043e\u0435\u043a\u0442 CodeSearchNet, \u0432 \u0440\u0430\u043c\u043a\u0430\u0445 \u043a\u043e\u0442\u043e\u0440\u043e\u0433\u043e \u043f\u043e\u0434\u0433\u043e\u0442\u043e\u0432\u043b\u0435\u043d\u044b \u043c\u043e\u0434\u0435\u043b\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0438 \u043d\u0430\u0431\u043e\u0440\u044b \u0434\u0430\u043d\u043d\u044b\u0445, \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u044b\u0435 \u0434\u043b\u044f \u0440\u0430\u0437\u0431\u043e\u0440\u0430, \u043a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0438 \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u043a\u043e\u0434\u0430 \u043d\u0430 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u044f\u0437\u044b\u043a\u0430\u0445 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f. CodeSearchNet, \u043f\u043e \u0430\u043d\u0430\u043b\u043e\u0433\u0438\u0438 \u0441 ImageNet, \u0432\u043a\u043b\u044e\u0447\u0430\u0435\u0442 \u0431\u043e\u043b\u044c\u0448\u0443\u044e \u043a\u043e\u043b\u043b\u0435\u043a\u0446\u0438\u044e \u043e\u0442\u0440\u044b\u0432\u043a\u043e\u0432 \u043a\u043e\u0434\u0430, \u0441\u043d\u0430\u0431\u0436\u0451\u043d\u043d\u044b\u0445 \u0430\u043d\u043d\u043e\u0442\u0430\u0446\u0438\u044f\u043c\u0438, \u0444\u043e\u0440\u043c\u0430\u043b\u0438\u0437\u0443\u044e\u0449\u0438\u043c\u0438 \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u043c\u044b\u0435 \u043a\u043e\u0434\u043e\u043c \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f. \u041a\u043e\u043c\u043f\u043e\u043d\u0435\u043d\u0442\u044b \u0434\u043b\u044f \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0438 \u043f\u0440\u0438\u043c\u0435\u0440\u044b \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f CodeSearchNet \u043d\u0430\u043f\u0438\u0441\u0430\u043d\u044b \u043d\u0430 \u044f\u0437\u044b\u043a\u0435 Python \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c […]<\/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-38448","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\udd47GitHub je predstavio radove na primjeni strojnog u\u010denja za pretra\u017eivanje i analizu koda | ProHoster","description":"GitHub je predstavio projekt","canonical_url":"https:\/\/prohoster.info\/hr\/blog\/news\/github-otkryl-narabotki-po-primeneniyu-mashinnogo-obucheniya-dlya-poiska-i-analiza-koda","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hr_HR","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\udd47GitHub \u043e\u0442\u043a\u0440\u044b\u043b \u043d\u0430\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u043f\u043e \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u044e \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u043f\u043e\u0438\u0441\u043a\u0430 \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0430 \u043a\u043e\u0434\u0430 | ProHoster","og:description":"GitHub \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b \u043f\u0440\u043e\u0435\u043a\u0442","og:url":"https:\/\/prohoster.info\/hr\/blog\/news\/github-otkryl-narabotki-po-primeneniyu-mashinnogo-obucheniya-dlya-poiska-i-analiza-koda","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":"2019-10-31T19:23:47+00:00","article:modified_time":"2019-10-31T19:23:47+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"38448","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":"2026-01-23 22:05:20","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 01:09:22","updated":"2026-01-23 22:05:20","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts\/38448","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/comments?post=38448"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/posts\/38448\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/media?parent=38448"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/categories?post=38448"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hr\/wp-json\/wp\/v2\/tags?post=38448"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}