{"id":56370,"date":"2020-02-11T00:00:00","date_gmt":"2020-02-10T21:00:00","guid":{"rendered":"https:\/\/prohoster.info\/blog\/blog_prohoster\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning"},"modified":"2020-02-18T14:04:38","modified_gmt":"2020-02-18T11:04:38","slug":"kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","status":"publish","type":"post","link":"https:\/\/prohoster.info\/cs\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","title":{"rendered":"Jako energetik jsem studoval neuronov\u00e9 s\u00edt\u011b a p\u0159ehled na bezplatn\u00fd kurz \u201eUdacity: Intro to TensorFlow for Deep Learning\u201c","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Cel\u00fd sv\u016fj v\u011bdom\u00fd \u017eivot jsem byl energetikem (ne, nyn\u00ed nejde o n\u00e1poj se sporn\u00fdmi vlastnostmi). <\/p>\n<p>Nikdy m\u011b zvl\u00e1\u0161\u0165 nezaj\u00edmaly technologie informa\u010dn\u00edch technologi\u00ed, a dokonce bych asi ani na pap\u00ed\u0159e neum\u011bl vyn\u00e1sobit matice. A to mi nikdy ani nebylo pot\u0159eba, abyste pochopili n\u011bco o specifik\u00e1ch m\u00e9 pr\u00e1ce, mohu sd\u00edlet skv\u011bl\u00fd p\u0159\u00edb\u011bh. Jednou jsem po\u017e\u00e1dal sv\u00e9 kolegy, aby ud\u011blali pr\u00e1ci v Excelu \u2013 tabulce, uplynula polovina pracovn\u00edho dne, p\u0159istoupil jsem k nim a oni si sed\u00ed a s\u010d\u00edtaj\u00ed \u00fadaje na kalkula\u010dce, ano, na oby\u010dejn\u00e9 \u010dern\u00e9 kalkula\u010dce s tla\u010d\u00edtky. A o jak\u00fdch neuronov\u00fdch s\u00edt\u00edch se po tom m\u016f\u017ee mluvit?\u2026 Proto jsem nikdy nem\u011bl \u017e\u00e1dn\u00e9 zvl\u00e1\u0161tn\u00ed p\u0159edpoklady k tomu, abych se pono\u0159il do sv\u011bta IT. Ale, jak se \u0159\u00edk\u00e1, \u201edob\u0159e tam, kde n\u00e1s nen\u00ed\u201c, moji p\u0159\u00e1tel\u00e9 mi st\u00e1le vypr\u00e1v\u011bli o roz\u0161\u00ed\u0159en\u00e9 realit\u011b, neuronov\u00fdch s\u00edt\u00edch, programovac\u00edch jazyc\u00edch (zejm\u00e9na o Pythonu).<\/p>\n<p>Na slovech to vypadalo velmi jednodu\u0161e, a tak jsem se rozhodl, pro\u010d se nenau\u010dit toto magick\u00e9 um\u011bn\u00ed, abych ho mohl pou\u017e\u00edt ve sv\u00e9 sf\u00e9\u0159e \u010dinnosti.<\/p>\n<p>V tomto \u010dl\u00e1nku p\u0159esko\u010d\u00edm m\u00e9 pokusy zvl\u00e1dnout z\u00e1klady Pythonu a pod\u011bl\u00edm se s v\u00e1mi o sv\u00e9 dojmy z bezplatn\u00e9ho kurzu o TensorFlow od Udacity.<\/p>\n<p><img decoding=\"async\" alt=\"Jako energetik jsem studoval neuronov\u00e9 s\u00edt\u011b a p\u0159ehled na bezplatn\u00fd kurz \u201eUdacity: Intro to TensorFlow for Deep Learning\u201c\" src=\"\/wp-content\/uploads\/2020\/02\/d8955ee8fd84fe551521a7675f425073.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><\/p>\n<h2> \u00davod<\/h2>\n<p>\nNejprve si mus\u00edm uv\u011bdomit, \u017ee po 11 letech v energetice, kdy v\u00edte a um\u00edte v\u0161echno a dokonce o kousek v\u00edc (podle sv\u00fdch povinnost\u00ed), u\u010den\u00ed se zcela nov\u00fdm v\u011bcem \u2013 na jedn\u00e9 stran\u011b vyvol\u00e1v\u00e1 bou\u0159liv\u00fd nad\u0161en\u00ed, ale na druh\u00e9 stran\u011b obratem zp\u016fsobuje fyzickou bolest \u201eozuben\u00fdch kole\u010dek v hlav\u011b\u201c.<\/p>\n<p>St\u00e1le si je\u0161t\u011b zcela neuv\u011bdomuji v\u0161echny z\u00e1kladn\u00ed koncepty programov\u00e1n\u00ed a strojov\u00e9ho u\u010den\u00ed, proto m\u011b pros\u00edm p\u0159\u00edsn\u011b nesu\u010fte. Douf\u00e1m, \u017ee m\u016fj \u010dl\u00e1nek bude zaj\u00edmav\u00fd a u\u017eite\u010dn\u00fd lidem, jako jsem j\u00e1 \u2013 vzd\u00e1len\u00fdm od v\u00fdvoje softwaru.<\/p>\n<p>Ne\u017e p\u0159ejdu k p\u0159ehledu kurzu, \u0159eknu, \u017ee k jeho studiu budete pot\u0159ebovat alespo\u0148 minim\u00e1ln\u00ed znalosti Pythonu. M\u016f\u017eete si p\u0159e\u010d\u00edst p\u00e1r knih pro za\u010d\u00e1te\u010dn\u00edky (je\u0161t\u011b jsem za\u010dal absolvovat kurz na Stepic, ale zat\u00edm ho nedokon\u010dil). <\/p>\n<p>V samotn\u00e9m kurzu o TensorFlow nebudou slo\u017eit\u00e9 konstrukce, ale pochopit, pro\u010d se importuj\u00ed knihovny, jak se ur\u010duje funkce a pro\u010d se do n\u00ed n\u011bco dosazuje, bude nutn\u00e9.<\/p>\n<h2> Pro\u010d TensorFlow a Udacity? <\/h2>\n<p>\nHlavn\u00edm c\u00edlem m\u00e9ho studia bylo nau\u010dit se rozpozn\u00e1vat fotografie prvk\u016f elektroinstalac\u00ed pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed. <\/p>\n<p>TensorFlow jsem si vybral, proto\u017ee jsem o n\u011bm sly\u0161el od sv\u00fdch p\u0159\u00e1tel. A jak jsem pochopil, tento kurz je celkem popul\u00e1rn\u00ed.<\/p>\n<p>Sna\u017eil jsem se za\u010d\u00edt studium s ofici\u00e1ln\u00edm <noindex><a rel=\"nofollow\" href=\"https:\/\/www.tensorflow.org\/tutorials\"> taughtorem. <\/a><\/noindex>.<\/p>\n<p>A hned jsem narazil na dv\u011b probl\u00e9my.<\/p>\n<ul>\n<li>Studijn\u00edch materi\u00e1l\u016f je hodn\u011b, a jsou neuspo\u0159\u00e1dan\u00e9. Sestavit alespo\u0148 relativn\u011b ucelen\u00fd obraz \u0159e\u0161en\u00ed \u00falohy rozpozn\u00e1v\u00e1n\u00ed obraz\u016f bylo pro m\u011b velmi obt\u00ed\u017en\u00e9. <\/li>\n<li>V\u011bt\u0161ina pot\u0159ebn\u00fdch \u010dl\u00e1nk\u016f nen\u00ed p\u0159elo\u017eena do ru\u0161tiny. Tak se stalo, \u017ee jsem v d\u011btstv\u00ed studoval n\u011bm\u010dinu a nyn\u00ed, jako mnoz\u00ed sov\u011bt\u0161t\u00ed d\u011bti, nev\u00edm ani n\u011bmecky, ani anglicky. Samoz\u0159ejm\u011b jsem se b\u011bhem sv\u00e9ho v\u011bdom\u00e9ho \u017eivota sna\u017eil ovl\u00e1dnout angli\u010dtinu, ale povedlo se to p\u0159ibli\u017en\u011b tak, jako na obr\u00e1zku. <\/li>\n<\/ul>\n<p>\n<img decoding=\"async\" alt=\"Jako energetik jsem studoval neuronov\u00e9 s\u00edt\u011b a p\u0159ehled na bezplatn\u00fd kurz \u201eUdacity: Intro to TensorFlow for Deep Learning\u201c\" src=\"\/wp-content\/uploads\/2020\/02\/44250d475745cf02ee7126e31f695c3b.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nPo prozkoum\u00e1n\u00ed ofici\u00e1ln\u00edho webu jsem na\u0161el doporu\u010den\u00ed absolvovat <noindex><a rel=\"nofollow\" href=\"https:\/\/www.tensorflow.org\/resources\/learn-ml\/basics-of-machine-learning\/\"> jeden ze dvou online kurz\u016f.<\/a><\/noindex>.<\/p>\n<p>Jak jsem pochopil, kurz na Courcera byl placen\u00fd, zat\u00edmco kurz <noindex><a rel=\"nofollow\" href=\"https:\/\/www.udacity.com\/course\/intro-to-tensorflow-for-deep-learning--ud187\"> Udacity: \u00davod do TensorFlow pro hlubok\u00e9 u\u010den\u00ed<\/a><\/noindex> bylo mo\u017en\u00e9 absolvovat \"bez n\u00e1klad\u016f, tedy zdarma\".<\/p>\n<h2> Obsah kurzu<\/h2>\n<p>\nKurz se skl\u00e1d\u00e1 z 9 lekc\u00ed. <\/p>\n<p>Nejprve sekce je \u00favodn\u00ed, tam se \u0159\u00edk\u00e1, k \u010demu je vlastn\u011b pot\u0159eba.<\/p>\n<p>Lekce \u010d. 2 se uk\u00e1zala jako moje obl\u00edben\u00e1. Byla dost jednoduch\u00e1 na to, aby se dala pochopit, a z\u00e1rove\u0148 demonstrovala z\u00e1zraky v\u011bdy. Stru\u010dn\u011b \u0159e\u010deno, v t\u00e9to lekci krom\u011b z\u00e1kladn\u00edch informac\u00ed o neuronov\u00fdch s\u00edt\u00edch auto\u0159i ukazuj\u00ed, jak pomoc\u00ed jednovrstv\u00e9 neuronov\u00e9 s\u00edt\u011b vy\u0159e\u0161it \u00falohu p\u0159evodu teploty z Fahrenheita do Celsia.<\/p>\n<p>To je opravdu velmi n\u00e1zorn\u00fd p\u0159\u00edklad. Po\u0159\u00e1d p\u0159em\u00fd\u0161l\u00edm, jak vymyslet a vy\u0159e\u0161it podobnou \u00falohu, ale jen pro elektrotechniku.<\/p>\n<p>Bohu\u017eel jsem se zasekl, proto\u017ee u\u010dit se nezn\u00e1m\u00e9 v\u011bci v ciz\u00edm jazyce je docela obt\u00ed\u017en\u00e9. Zachr\u00e1nilo m\u011b, \u017ee jsem na\u0161el na Habru <noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/post\/453482\/\">p\u0159eklad tohoto kurzu do ru\u0161tiny.<\/a><\/noindex>.<\/p>\n<p>P\u0159eklad byl proveden kvalitn\u011b, tak\u00e9 byly p\u0159elo\u017eeny pozn\u00e1mkov\u00e9 bloky Colab, tak\u017ee jsem d\u00e1le nahl\u00ed\u017eel jak do origin\u00e1lu, tak do p\u0159ekladu.<\/p>\n<p>Lekce \u010d. 3 je v podstat\u011b p\u0159evypr\u00e1v\u011bn\u00ed materi\u00e1l\u016f ofici\u00e1ln\u00edho tutori\u00e1lu TensorFlow. V t\u00e9to lekci se pomoc\u00ed v\u00edcerozm\u011brn\u00e9 neuronov\u00e9 s\u00edt\u011b u\u010d\u00edme klasifikovat obr\u00e1zky s od\u011bvy (dataset Fashion MNIST).<\/p>\n<p>Lekce \u010d\u00edslo 4 a\u017e 7 jsou tak\u00e9 p\u0159epracov\u00e1n\u00edm tutori\u00e1lu. D\u00edky tomu, \u017ee jsou dob\u0159e uspo\u0159\u00e1d\u00e1ny, nen\u00ed nutn\u00e9 se s\u00e1m zab\u00fdvat po\u0159ad\u00edm u\u010den\u00ed. V t\u011bchto lekc\u00edch n\u00e1m stru\u010dn\u011b p\u0159edstav\u00ed vysoce p\u0159esn\u00e9 neuronov\u00e9 s\u00edt\u011b, jak zv\u00fd\u0161it p\u0159esnost u\u010den\u00ed a uchovat model. P\u0159itom se budeme z\u00e1rove\u0148 zab\u00fdvat \u00fakolem klasifikace ko\u010dek a ps\u016f na obr\u00e1zc\u00edch.<\/p>\n<p>Lekce \u010d\u00edslo 8 p\u0159edstavuje samostatn\u00fd kurz s jin\u00fdm lektorem a je dost ob\u0161\u00edrn\u00e1. Tato lekce je v\u011bnov\u00e1na \u010dasov\u00fdm \u0159ad\u00e1m. Proto\u017ee m\u011b to zat\u00edm nezaj\u00edm\u00e1, pro\u0161el jsem to jen zb\u011b\u017en\u011b.<\/p>\n<p>V\u0161echny lekce uzav\u00edr\u00e1 lekce \u010d\u00edslo 9, kter\u00e1 je pozv\u00e1nkou na bezplatn\u00fd kurz o TensorFlow lite.<\/p>\n<h2> Co se mi l\u00edbilo a co ne<\/h2>\n<p>\nZa\u010dnu s klady:<\/p>\n<ul>\n<li> Kurz je zdarma <\/li>\n<li> Kurz je o TensorFlow 2. N\u011bkter\u00e9 u\u010debnice, kter\u00e9 jsem vid\u011bl, a n\u011bkter\u00e9 kurzy na internetu byly o TensorFlow 1. Nev\u00edm, jestli je mezi nimi velk\u00fd rozd\u00edl, ale je p\u0159\u00edjemn\u00e9 u\u010dit se aktu\u00e1ln\u00ed verzi. <\/li>\n<li> Lektor na videu m\u011b neru\u0161\u00ed (i kdy\u017e v rusk\u00e9 verzi \u010dtou m\u00e9n\u011b energicky ne\u017e v origin\u00e1le) <\/li>\n<li> Kurz nebere moc \u010dasu<\/li>\n<li> Kurz nevytv\u00e1\u0159\u00ed pocit smutku a beznad\u011bje. \u00dakoly v kurzu jsou jednoduch\u00e9 a v\u017edy je k dispozici n\u00e1pov\u011bda ve form\u011b Colab s spr\u00e1vn\u00fdm \u0159e\u0161en\u00edm, pokud n\u011bco nen\u00ed jasn\u00e9 (a polovina \u00faloh mi jasn\u00e1 nebyla) <\/li>\n<li> Nen\u00ed t\u0159eba nic instalovat, v\u0161echny laboratorn\u00ed pr\u00e1ce kurzu lze ud\u011blat v prohl\u00ed\u017ee\u010di<\/li>\n<\/ul>\n<p>\nTe\u010f m\u00ednusy:<\/p>\n<ul>\n<li> Skoro nejsou \u017e\u00e1dn\u00e9 kontroln\u00ed materi\u00e1ly. \u017d\u00e1dn\u00e9 testy, ani \u00fakoly, nic, co by pomohlo ov\u011b\u0159it osvojen\u00ed kurzu <\/li>\n<li> Ne v\u0161echny notebooky mi pracovaly tak, jak m\u011bly. Mysl\u00edm, \u017ee ve t\u0159et\u00ed lekci origin\u00e1ln\u00edho kurzu v angli\u010dtin\u011b Colab vyhazoval chybu, a nev\u011bd\u011bl jsem, co s n\u00ed d\u011blat <\/li>\n<li> Pohodln\u011b se to sleduje jen na po\u010d\u00edta\u010di. Mo\u017en\u00e1 jsem se v tom dostate\u010dn\u011b nevyznal, ale nena\u0161el jsem aplikaci Udacity na sv\u00e9m chytr\u00e9m telefonu. A mobiln\u00ed verze webu nen\u00ed adaptivn\u00ed, tak\u017ee v\u011bt\u0161inu obrazovky zab\u00edr\u00e1 naviga\u010dn\u00ed menu, ale abyste vid\u011bli hlavn\u00ed obsah, mus\u00edte listovat doprava za zorn\u00e9 pole. Tak\u00e9 videa nelze sledovat na telefonu. Na obrazovce o velikosti \u0161est palc\u016f nic po\u0159\u00e1dn\u011b nerozli\u0161\u00edte.<\/li>\n<li>N\u011bkter\u00e9 v\u011bci v kurzu jsou rozeb\u00edr\u00e1ny n\u011bkolikr\u00e1t, ale skute\u010dn\u011b pot\u0159ebn\u00e9 informace o sam\u00fdch konvolu\u010dn\u00edch s\u00edt\u00edch nejsou dostate\u010dn\u011b vysv\u011btleny. Tak jsem ani nepochopil glob\u00e1ln\u00ed c\u00edl n\u011bkter\u00fdch cvi\u010den\u00ed (nap\u0159\u00edklad, k \u010demu je Max Pooling). <\/li>\n<\/ul>\n<p><\/p>\n<h2> Shrnut\u00ed<\/h2>\n<p>\nJist\u011b jste u\u017e uh\u00e1dli, \u017ee kouzlo se nekonalo. A po absolvov\u00e1n\u00ed tohoto kr\u00e1tk\u00e9ho kurzu nen\u00ed mo\u017en\u00e9 opravdu pochopit, jak funguj\u00ed neuronov\u00e9 s\u00edt\u011b.<\/p>\n<p>Samoz\u0159ejm\u011b, \u017ee jsem po tomto nedok\u00e1zal s\u00e1m vy\u0159e\u0161it sv\u016fj \u00fakol s klasifikac\u00ed fotografi\u00ed vyp\u00edna\u010d\u016f a tla\u010d\u00edtek v rozvodn\u00fdch za\u0159\u00edzen\u00edch. <\/p>\n<p>Ale celkov\u011b je kurz u\u017eite\u010dn\u00fd. Ukazuje, jak\u00e9 v\u011bci lze ud\u011blat pomoc\u00ed TensorFlow a jak\u00fdm sm\u011brem se d\u00e1 pokra\u010dovat d\u00e1l. <\/p>\n<p>Mysl\u00edm, \u017ee se nejprve mus\u00edm nau\u010dit z\u00e1klady Pythonu a p\u0159e\u010d\u00edst si knihy v \u010de\u0161tin\u011b o tom, jak funguj\u00ed neuronov\u00e9 s\u00edt\u011b, a a\u017e potom se pustit do TensorFlow.<\/p>\n<p>Na z\u00e1v\u011br bych cht\u011bl pod\u011bkovat sv\u00fdm p\u0159\u00e1tel\u016fm za to, \u017ee m\u011b povzbudili k naps\u00e1n\u00ed prvn\u00edho \u010dl\u00e1nku na \"Habr\" a pomohli mi s jeho \u00fapravou.<\/p>\n<p>P.S. Budu r\u00e1d za va\u0161e koment\u00e1\u0159e a jakoukoli konstruktivn\u00ed kritiku.<br \/>\n<br \/>Zdroj: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/post\/487950\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438). \u042f \u043d\u0438\u043a\u043e\u0433\u0434\u0430 \u043e\u0441\u043e\u0431\u043e \u043d\u0435 \u0438\u043d\u0442\u0435\u0440\u0435\u0441\u043e\u0432\u0430\u043b\u0441\u044f \u043c\u0438\u0440\u043e\u043c \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0445 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439, \u0434\u0430 \u0438 \u0434\u0430\u0436\u0435 \u043c\u0430\u0442\u0440\u0438\u0446\u044b \u044f \u0432\u0440\u044f\u0434 \u043b\u0438 \u043d\u0430 \u043b\u0438\u0441\u0442\u043e\u0447\u043a\u0435 \u0441\u043c\u043e\u0433\u0443 \u043f\u0435\u0440\u0435\u043c\u043d\u043e\u0436\u0438\u0442\u044c. \u0414\u0430 \u0438 \u043d\u0435 \u043d\u0443\u0436\u043d\u043e \u043c\u043d\u0435 \u044d\u0442\u043e \u0431\u044b\u043b\u043e \u043d\u0438\u043a\u043e\u0433\u0434\u0430, \u0447\u0442\u043e\u0431\u044b \u0432\u044b \u043f\u043e\u043d\u0438\u043c\u0430\u043b\u0438 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u043e \u0441\u043f\u0435\u0446\u0438\u0444\u0438\u043a\u0435 \u043c\u043e\u0435\u0439 \u0440\u0430\u0431\u043e\u0442\u044b, \u043c\u043e\u0433\u0443 \u043f\u043e\u0434\u0435\u043b\u0438\u0442\u044c\u0441\u044f \u0437\u0430\u043c\u0435\u0447\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0439 [&hellip;]<\/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-56370","post","type-post","status-publish","format-standard","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=\"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).\" \/>\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\/cs\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"cs_CZ\" \/>\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\udd47\u041a\u0430\u043a \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a \u0438\u0437\u0443\u0447\u0430\u043b \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043e\u0431\u0437\u043e\u0440 \u043d\u0430 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u044b\u0439 \u043a\u0443\u0440\u0441 \u00abUdacity: Intro to TensorFlow for Deep Learning\u00bb | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/cs\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning\" \/>\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=\"2020-02-10T21:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2020-02-18T11:04:38+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\udd47Jak energetik studoval neuronov\u00e9 s\u00edt\u011b a p\u0159ehled zdarma kurzu \u201eUdacity: \u00davod do TensorFlow pro hlubok\u00e9 u\u010den\u00ed\u201c | ProHoster","description":"Cel\u00fd sv\u016fj v\u011bdom\u00fd \u017eivot jsem byl energetikem (ne, nyn\u00ed nejde o n\u00e1poj se sporn\u00fdmi vlastnostmi).","canonical_url":"https:\/\/prohoster.info\/cs\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"cs_CZ","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\u041a\u0430\u043a \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a \u0438\u0437\u0443\u0447\u0430\u043b \u043d\u0435\u0439\u0440\u043e\u0441\u0435\u0442\u0438 \u0438 \u043e\u0431\u0437\u043e\u0440 \u043d\u0430 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u044b\u0439 \u043a\u0443\u0440\u0441 \u00abUdacity: Intro to TensorFlow for Deep Learning\u00bb | ProHoster","og:description":"\u0412\u0441\u044e \u0441\u0432\u043e\u044e \u0441\u043e\u0437\u043d\u0430\u0442\u0435\u043b\u044c\u043d\u0443\u044e \u0436\u0438\u0437\u043d\u044c, \u044f \u0431\u044b\u043b \u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u043e\u043c (\u043d\u0435\u0442, \u0441\u0435\u0439\u0447\u0430\u0441 \u0440\u0435\u0447\u044c \u043d\u0435 \u0438\u0434\u0435\u0442 \u043e \u043d\u0430\u043f\u0438\u0442\u043a\u0435 \u0441 \u0441\u043e\u043c\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0441\u0432\u043e\u0439\u0441\u0442\u0432\u0430\u043c\u0438).","og:url":"https:\/\/prohoster.info\/cs\/blog\/news\/kak-energetik-izuchal-nejroseti-i-obzor-na-besplatnyj-kurs-udacity-intro-to-tensorflow-for-deep-learning","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":"2020-02-10T21:00:00+00:00","article:modified_time":"2020-02-18T11:04:38+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"56370","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":"2021-02-28 19:26:38","updated":"2022-10-07 20:14:09","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/56370","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/comments?post=56370"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/56370\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media?parent=56370"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/categories?post=56370"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/tags?post=56370"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}