{"id":15975,"date":"2024-01-19T09:17:13","date_gmt":"2024-01-19T05:47:13","guid":{"rendered":"https:\/\/rasanegar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/"},"modified":"2024-01-19T09:17:13","modified_gmt":"2024-01-19T05:47:13","slug":"tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86","status":"publish","type":"post","link":"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/","title":{"rendered":"Tensorflow 2.0: \u062d\u0644 \u0645\u0633\u0627\u0626\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\"><p class=\"ez-toc-title\" style=\"cursor:inherit\">\u0633\u0631\u0641\u0635\u0644\u0647\u0627\u06cc \u0645\u0637\u0644\u0628<\/p>\n<\/div><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d8%b7%d8%a8%d9%82%d9%87_%d8%a8%d9%86%d8%af%db%8c_%d8%a8%d8%a7_tensorflow_20\" >\u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0627 Tensorflow 2.0<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87\" >\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%88%d8%a7%d8%b1%d8%af%d8%a7%d8%aa_%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87_%d9%87%d8%a7\" >\u0648\u0627\u0631\u062f\u0627\u062a \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%88%d8%a7%d8%b1%d8%af_%da%a9%d8%b1%d8%af%d9%86_%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87\" >\u0648\u0627\u0631\u062f \u06a9\u0631\u062f\u0646 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d8%aa%d8%ac%d8%b2%db%8c%d9%87_%d9%88_%d8%aa%d8%ad%d9%84%db%8c%d9%84_%d8%af%d8%a7%d8%af%d9%87_%d9%87%d8%a7_%d9%88_%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4\" >\u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0648 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d8%a2%d9%85%d9%88%d8%b2%d8%b4_%d9%85%d8%af%d9%84\" >\u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86_%d8%a8%d8%a7_tensorflow_20\" >\u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0628\u0627 TensorFlow 2.0<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87-2\" >\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4_%d8%af%d8%a7%d8%af%d9%87_%d9%87%d8%a7\" >\u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634 \u062f\u0627\u062f\u0647 \u0647\u0627<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d8%a2%d9%85%d9%88%d8%b2%d8%b4_%d9%85%d8%af%d9%84-2\" >\u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/rasanegaar.com\/blog\/tensorflow-2-0-%d8%ad%d9%84-%d9%85%d8%b3%d8%a7%d8%a6%d9%84-%d8%b7%d8%a8%d9%82%d9%87-%d8%a8%d9%86%d8%af%db%8c-%d9%88-%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86\/#%d9%86%d8%aa%db%8c%d8%ac%d9%87\" >\u0646\u062a\u06cc\u062c\u0647<\/a><\/li><\/ul><\/nav><\/div>\n<span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 9<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span><p> <br \/>\n<\/p>\n<div><noscript><\/noscript><\/p>\n<p>\u067e\u0633 \u0627\u0632 \u0647\u06cc\u0627\u0647\u0648\u06cc \u0628\u0633\u06cc\u0627\u0631\u060c \u0633\u0631\u0627\u0646\u062c\u0627\u0645 \u06af\u0648\u06af\u0644 \u0645\u0646\u062a\u0634\u0631 \u0634\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.tensorflow.org\/guide\/effective_tf2\" class=\"broken_link\">TensorFlow 2.0<\/a> \u06a9\u0647 \u0622\u062e\u0631\u06cc\u0646 \u0646\u0633\u062e\u0647 \u067e\u0644\u062a\u0641\u0631\u0645 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u067e\u0631\u0686\u0645\u062f\u0627\u0631 \u06af\u0648\u06af\u0644 \u0627\u0633\u062a.  \u0628\u0633\u06cc\u0627\u0631\u06cc \u0627\u0632 \u0648\u06cc\u0698\u06af\u06cc\u200c\u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0627\u0646\u062a\u0638\u0627\u0631 \u062f\u0631 TensorFlow 2.0 \u0645\u0639\u0631\u0641\u06cc \u0634\u062f\u0647\u200c\u0627\u0646\u062f.  \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0631\u0648\u0634 \u062a\u0648\u0633\u0639\u0647 \u0645\u062f\u0644 \u0647\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0633\u0627\u062f\u0647 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 TensorFlow 2.0 \u067e\u0648\u0634\u0634 \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<h2 id=\"classificationwithtensorflow20\"><span class=\"ez-toc-section\" id=\"%d8%b7%d8%a8%d9%82%d9%87_%d8%a8%d9%86%d8%af%db%8c_%d8%a8%d8%a7_tensorflow_20\"><\/span>\u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0627 Tensorflow 2.0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u0627\u06af\u0631 \u062a\u0627 \u0628\u0647 \u062d\u0627\u0644 \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 Keras \u06a9\u0627\u0631 \u06a9\u0631\u062f\u0647 \u0627\u06cc\u062f\u060c \u062f\u0631 \u0627\u0646\u062a\u0638\u0627\u0631 \u0634\u0645\u0627 \u0647\u0633\u062a\u06cc\u062f.  TensorFlow 2.0 \u0627\u06a9\u0646\u0648\u0646 \u0627\u0632 Keras API \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u067e\u06cc\u0634 \u0641\u0631\u0636 \u062e\u0648\u062f \u0628\u0631\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644 \u0647\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f.  \u0642\u0628\u0644 \u0627\u0632 TensorFlow 2.0\u060c \u06cc\u06a9\u06cc \u0627\u0632 \u0627\u0646\u062a\u0642\u0627\u062f\u0627\u062a \u0639\u0645\u062f\u0647 \u0627\u06cc \u06a9\u0647 \u0646\u0633\u062e\u0647 \u0647\u0627\u06cc \u0642\u0628\u0644\u06cc TensorFlow \u0628\u0627 \u0622\u0646 \u0645\u0648\u0627\u062c\u0647 \u0628\u0648\u062f\u0646\u062f\u060c \u0646\u0627\u0634\u06cc \u0627\u0632 \u067e\u06cc\u0686\u06cc\u062f\u06af\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 \u0628\u0648\u062f.  \u0642\u0628\u0644\u0627\u064b \u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u06cc\u06a9 \u0645\u062f\u0644 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0644\u062c\u0633\u062a\u06cc\u06a9 \u0633\u0627\u062f\u0647\u060c \u0628\u0627\u06cc\u062f \u0646\u0645\u0648\u062f\u0627\u0631\u0647\u0627\u060c \u062c\u0644\u0633\u0627\u062a \u0648 \u0645\u06a9\u0627\u0646\u200c\u0647\u0627 \u0631\u0627 \u0628\u0647 \u0647\u0645 \u0628\u0686\u0633\u0628\u0627\u0646\u06cc\u062f.  \u0628\u0627 TensorFlow 2.0\u060c \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 \u0647\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u062a\u0628\u062f\u06cc\u0644 \u0628\u0647 \u06cc\u06a9 \u062a\u06a9\u0647 \u06a9\u06cc\u06a9 \u0634\u062f\u0647 \u0627\u0633\u062a.<\/p>\n<p>\u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u0628\u062f\u0648\u0646 \u0628\u062d\u062b \u0628\u06cc\u0634\u062a\u0631\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f \u06cc\u06a9 \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0627 TensorFlow \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u0645.<\/p>\n<h3 id=\"thedataset\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87\"><\/span>\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0628\u0631\u0627\u06cc \u0645\u062b\u0627\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0647 \u0635\u0648\u0631\u062a \u0631\u0627\u06cc\u06af\u0627\u0646 \u0627\u0632 \u0627\u06cc\u0646\u062c\u0627 \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0631\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/www.kaggle.com\/elikplim\/car-evaluation-data-set\">\u0627\u06cc\u0646 \u0644\u06cc\u0646\u06a9<\/a>.  \u0641\u0627\u06cc\u0644 \u0631\u0627 \u0628\u0627 \u0641\u0631\u0645\u062a CSV \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0646\u06cc\u062f.  \u0627\u06af\u0631 \u0641\u0627\u06cc\u0644 CSV \u062f\u0627\u0646\u0644\u0648\u062f \u0634\u062f\u0647 \u0631\u0627 \u0628\u0627\u0632 \u06a9\u0646\u06cc\u062f\u060c \u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u0641\u0627\u06cc\u0644 \u062d\u0627\u0648\u06cc \u0647\u06cc\u0686 \u0639\u0646\u0648\u0627\u0646\u06cc \u0646\u06cc\u0633\u062a.  \u062c\u0632\u0626\u06cc\u0627\u062a \u0633\u062a\u0648\u0646 \u0647\u0627 \u062f\u0631 \u062f\u0633\u062a\u0631\u0633 \u0627\u0633\u062a <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/archive.ics.uci.edu\/ml\/datasets\/car+evaluation\">\u0645\u062e\u0632\u0646 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0645\u0627\u0634\u06cc\u0646 UCI<\/a>.  \u062a\u0648\u0635\u06cc\u0647 \u0645\u06cc \u06a9\u0646\u0645 \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0631\u0627 \u0628\u0647 \u0637\u0648\u0631 \u06a9\u0627\u0645\u0644 \u0627\u0632 \u0644\u06cc\u0646\u06a9 \u062f\u0627\u0646\u0644\u0648\u062f \u0645\u0637\u0627\u0644\u0639\u0647 \u06a9\u0646\u06cc\u062f.  \u0645\u0646 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0631\u0627 \u062f\u0631 \u0627\u06cc\u0646 \u0628\u062e\u0634 \u062e\u0644\u0627\u0635\u0647 \u0645\u06cc \u06a9\u0646\u0645.<\/p>\n<p>\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0627\u0633\u0627\u0633\u0627\u064b \u0627\u0632 7 \u0633\u062a\u0648\u0646 \u062a\u0634\u06a9\u06cc\u0644 \u0634\u062f\u0647 \u0627\u0633\u062a:<\/p>\n<ol>\n<li>\u0642\u06cc\u0645\u062a (\u0642\u06cc\u0645\u062a \u062e\u0631\u06cc\u062f \u0645\u0627\u0634\u06cc\u0646)<\/li>\n<li>\u062a\u0639\u0645\u06cc\u0631 \u0648 \u0646\u06af\u0647\u062f\u0627\u0631\u06cc (\u0647\u0632\u06cc\u0646\u0647 \u062a\u0639\u0645\u06cc\u0631 \u0648 \u0646\u06af\u0647\u062f\u0627\u0631\u06cc)<\/li>\n<li>\u062f\u0631\u0628 (\u062a\u0639\u062f\u0627\u062f \u062f\u0631\u0628)<\/li>\n<li>\u0627\u0641\u0631\u0627\u062f (\u0638\u0631\u0641\u06cc\u062a \u0635\u0646\u062f\u0644\u06cc)<\/li>\n<li>lug_capacity (\u0638\u0631\u0641\u06cc\u062a \u0686\u0645\u062f\u0627\u0646)<\/li>\n<li>\u0627\u06cc\u0645\u0646\u06cc (\u0645\u0627\u0634\u06cc\u0646 \u0686\u0642\u062f\u0631 \u0627\u06cc\u0645\u0646 \u0627\u0633\u062a)<\/li>\n<li>\u062e\u0631\u0648\u062c\u06cc (\u0648\u0636\u0639\u06cc\u062a \u0645\u0627\u0634\u06cc\u0646)<\/li>\n<\/ol>\n<p>\u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 6 \u0633\u062a\u0648\u0646 \u0627\u0648\u0644\u060c \u0648\u0638\u06cc\u0641\u0647 \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0645\u0642\u062f\u0627\u0631 \u0628\u0631\u0627\u06cc \u0633\u062a\u0648\u0646 7 \u06cc\u0639\u0646\u06cc \u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u062a.  \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u06cc\u06a9\u06cc \u0627\u0632 \u0633\u0647 \u0645\u0642\u062f\u0627\u0631 \u0631\u0627 \u062f\u0627\u0634\u062a\u0647 \u0628\u0627\u0634\u062f <code>unacc<\/code> (\u063a\u06cc\u0631 \u0642\u0627\u0628\u0644 \u0642\u0628\u0648\u0644)\u060c <code>acc<\/code> (\u0642\u0627\u0628\u0644 \u0642\u0628\u0648\u0644) <code>good<\/code>\u060c \u0648 <code>very good<\/code>.<\/p>\n<h3 id=\"importinglibraries\"><span class=\"ez-toc-section\" id=\"%d9%88%d8%a7%d8%b1%d8%af%d8%a7%d8%aa_%da%a9%d8%aa%d8%a7%d8%a8%d8%ae%d8%a7%d9%86%d9%87_%d9%87%d8%a7\"><\/span>\u0648\u0627\u0631\u062f\u0627\u062a \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0642\u0628\u0644 \u0627\u0632 \u0645\u0627 import \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0631\u0627 \u062f\u0631 \u0628\u0631\u0646\u0627\u0645\u0647 \u0645\u0627 \u0646\u06cc\u0627\u0632 \u062f\u0627\u0631\u06cc\u0645 import \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0646\u06cc\u0627\u0632<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">import<\/span> pandas <span class=\"hljs-keyword\">as<\/span> pd\n<span class=\"hljs-keyword\">import<\/span> numpy <span class=\"hljs-keyword\">as<\/span> np\n<span class=\"hljs-keyword\">import<\/span> tensorflow <span class=\"hljs-keyword\">as<\/span> tf\n\n<span class=\"hljs-keyword\">import<\/span> matplotlib.pyplot <span class=\"hljs-keyword\">as<\/span> plt\n%matplotlib inline\n\n<span class=\"hljs-keyword\">import<\/span> seaborn <span class=\"hljs-keyword\">as<\/span> sns\nsns.<span class=\"hljs-built_in\">set<\/span>(style=<span class=\"hljs-string\">\"darkgrid\"<\/span>)\n<\/code><\/pre>\n<p>\u0642\u0628\u0644 \u0627\u0632 \u0627\u062f\u0627\u0645\u0647\u060c \u0645\u06cc\u200c\u062e\u0648\u0627\u0647\u0645 \u0645\u0637\u0645\u0626\u0646 \u0634\u0648\u06cc\u062f \u06a9\u0647 \u0622\u062e\u0631\u06cc\u0646 \u0646\u0633\u062e\u0647 TensorFlow \u06cc\u0639\u0646\u06cc TensorFlow 2.0 \u0631\u0627 \u062f\u0627\u0631\u06cc\u062f.  \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0646\u0633\u062e\u0647 TensorFlow \u062e\u0648\u062f \u0631\u0627 \u0628\u0627 \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0628\u0631\u0631\u0633\u06cc \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-built_in\">print<\/span>(tf.__version__)\n<\/code><\/pre>\n<p>\u0627\u06af\u0631 TensorFlow 2.0 \u0631\u0627 \u0646\u0635\u0628 \u0646\u06a9\u0631\u062f\u0647 \u0627\u06cc\u062f\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0627\u0632 \u0637\u0631\u06cc\u0642 \u062f\u0633\u062a\u0648\u0631 \u0632\u06cc\u0631 \u0628\u0647 \u0622\u062e\u0631\u06cc\u0646 \u0646\u0633\u062e\u0647 \u0627\u0631\u062a\u0642\u0627 \u062f\u0647\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-meta\">$<\/span><span class=\"bash\"> pip install --upgrade tensorflow<\/span>\n<\/code><\/pre>\n<h3 id=\"importingthedataset\"><span class=\"ez-toc-section\" id=\"%d9%88%d8%a7%d8%b1%d8%af_%da%a9%d8%b1%d8%af%d9%86_%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87\"><\/span>\u0648\u0627\u0631\u062f \u06a9\u0631\u062f\u0646 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0631\u0627 \u0648\u0627\u0631\u062f \u0645\u06cc \u06a9\u0646\u062f.  \u0628\u0631 \u0627\u06cc\u0646 \u0627\u0633\u0627\u0633 \u0645\u0633\u06cc\u0631 \u0641\u0627\u06cc\u0644 \u062f\u0627\u062f\u0647 CSV \u062e\u0648\u062f \u0631\u0627 \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0647\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">cols = (<span class=\"hljs-string\">'price'<\/span>, <span class=\"hljs-string\">'maint'<\/span>, <span class=\"hljs-string\">'doors'<\/span>, <span class=\"hljs-string\">'persons'<\/span>, <span class=\"hljs-string\">'lug_capacity'<\/span>, <span class=\"hljs-string\">'safety'<\/span>,<span class=\"hljs-string\">'output'<\/span>)\ncars = pd.read_csv(<span class=\"hljs-string\">r'\/content\/drive\/My Drive\/datasets\/car_dataset.csv'<\/span>, names=cols, header=<span class=\"hljs-literal\">None<\/span>)\n<\/code><\/pre>\n<p>\u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0641\u0627\u06cc\u0644 CSV \u0628\u0647 \u0637\u0648\u0631 \u067e\u06cc\u0634\u200c\u0641\u0631\u0636 \u062d\u0627\u0648\u06cc \u0633\u0631\u0635\u0641\u062d\u0647\u200c\u0647\u0627\u06cc \u0633\u062a\u0648\u0646 \u0646\u06cc\u0633\u062a\u060c \u0645\u0627 \u0641\u0647\u0631\u0633\u062a\u06cc \u0627\u0632 \u0633\u0631\u0635\u0641\u062d\u0647\u200c\u0647\u0627\u06cc \u0633\u062a\u0648\u0646 \u0631\u0627 \u0628\u0647 \u0622\u0646 \u0627\u0631\u0633\u0627\u0644 \u06a9\u0631\u062f\u06cc\u0645 <code>pd.read_csv()<\/code> \u0631\u0648\u0634.<\/p>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0627\u06a9\u0646\u0648\u0646 5 \u0631\u062f\u06cc\u0641 \u0627\u0648\u0644 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0631\u0627 \u0627\u0632 \u0637\u0631\u06cc\u0642 the \u0628\u0628\u06cc\u0646\u06cc\u0645 <code>head()<\/code> \u0631\u0648\u0634.<\/p>\n<pre><code class=\"hljs\">cars.head()\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/Introduction-to-tensorflow-2.0-1.PNG\" alt=\"5 \u0631\u062f\u06cc\u0641 \u0627\u0648\u0644 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647\" title=\"\"><\/p>\n<p>\u0634\u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f 7 \u0633\u062a\u0648\u0646 \u0631\u0627 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0646\u06cc\u062f.<\/p>\n<h3 id=\"dataanalysisandpreprocessing\"><span class=\"ez-toc-section\" id=\"%d8%aa%d8%ac%d8%b2%db%8c%d9%87_%d9%88_%d8%aa%d8%ad%d9%84%db%8c%d9%84_%d8%af%d8%a7%d8%af%d9%87_%d9%87%d8%a7_%d9%88_%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4\"><\/span>\u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0648 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0627\u062c\u0627\u0632\u0647 \u062f\u0647\u06cc\u062f \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0631\u0627 \u0628\u0627 \u0631\u0633\u0645 \u0646\u0645\u0648\u062f\u0627\u0631 \u062f\u0627\u06cc\u0631\u0647 \u0627\u06cc \u06a9\u0647 \u062a\u0648\u0632\u06cc\u0639 \u062e\u0631\u0648\u062c\u06cc \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f\u060c \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0627\u0646\u062f\u0627\u0632\u0647 \u0637\u0631\u062d \u067e\u06cc\u0634 \u0641\u0631\u0636 \u0631\u0627 \u0627\u0641\u0632\u0627\u06cc\u0634 \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<pre><code class=\"hljs\">plot_size = plt.rcParams(<span class=\"hljs-string\">\"figure.figsize\"<\/span>)\nplot_size (<span class=\"hljs-number\">0<\/span>) = <span class=\"hljs-number\">8<\/span>\nplot_size (<span class=\"hljs-number\">1<\/span>) = <span class=\"hljs-number\">6<\/span>\nplt.rcParams(<span class=\"hljs-string\">\"figure.figsize\"<\/span>) = plot_size\n<\/code><\/pre>\n<p>\u0648 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0646\u0645\u0648\u062f\u0627\u0631 \u062f\u0627\u06cc\u0631\u0647 \u0627\u06cc \u0631\u0627 \u062a\u0631\u0633\u06cc\u0645 \u0645\u06cc \u06a9\u0646\u062f \u06a9\u0647 \u062a\u0648\u0632\u06cc\u0639 \u062e\u0631\u0648\u062c\u06cc \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f.<\/p>\n<pre><code class=\"hljs\">cars.output.value_counts().plot(kind=<span class=\"hljs-string\">'pie'<\/span>, autopct=<span class=\"hljs-string\">'%0.05f%%'<\/span>, colors=(<span class=\"hljs-string\">'lightblue'<\/span>, <span class=\"hljs-string\">'lightgreen'<\/span>, <span class=\"hljs-string\">'orange'<\/span>, <span class=\"hljs-string\">'pink'<\/span>), explode=(<span class=\"hljs-number\">0.05<\/span>, <span class=\"hljs-number\">0.05<\/span>, <span class=\"hljs-number\">0.05<\/span>,<span class=\"hljs-number\">0.05<\/span>))\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/Introduction-to-tensorflow-2.0-2.PNG\" alt=\"\u0646\u0645\u0648\u062f\u0627\u0631 \u062f\u0627\u06cc\u0631\u0647 \u0627\u06cc \u062a\u062c\u0632\u06cc\u0647 \u0648 \u062a\u062d\u0644\u06cc\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627\" title=\"\"><\/p>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f \u06a9\u0647 \u0627\u06a9\u062b\u0631\u06cc\u062a \u062e\u0648\u062f\u0631\u0648\u0647\u0627 (70 \u062f\u0631\u0635\u062f) \u062f\u0631 \u0634\u0631\u0627\u06cc\u0637 \u063a\u06cc\u0631\u0642\u0627\u0628\u0644 \u0642\u0628\u0648\u0644 \u0648 20 \u062f\u0631\u0635\u062f \u062e\u0648\u062f\u0631\u0648\u0647\u0627 \u062f\u0631 \u0634\u0631\u0627\u06cc\u0637 \u0642\u0627\u0628\u0644 \u0642\u0628\u0648\u0644 \u0647\u0633\u062a\u0646\u062f.  \u0646\u0633\u0628\u062a \u062e\u0648\u062f\u0631\u0648\u0647\u0627\u06cc \u0633\u0627\u0644\u0645 \u0648 \u0628\u0633\u06cc\u0627\u0631 \u062e\u0648\u0628 \u0628\u0633\u06cc\u0627\u0631 \u06a9\u0645 \u0627\u0633\u062a.<\/p>\n<p>\u062a\u0645\u0627\u0645 \u0633\u062a\u0648\u0646 \u0647\u0627\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0645\u0627 \u062f\u0633\u062a\u0647 \u0628\u0646\u062f\u06cc \u0647\u0633\u062a\u0646\u062f.  \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0645\u0628\u062a\u0646\u06cc \u0627\u0633\u062a \u0631\u0648\u06cc \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627\u06cc \u0622\u0645\u0627\u0631\u06cc \u0648 \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u0647\u0627\u06cc \u0622\u0645\u0627\u0631\u06cc \u0628\u0627 \u0627\u0639\u062f\u0627\u062f \u06a9\u0627\u0631 \u0645\u06cc \u06a9\u0646\u0646\u062f.  \u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646\u060c \u0628\u0627\u06cc\u062f \u0627\u0637\u0644\u0627\u0639\u0627\u062a \u062f\u0633\u062a\u0647 \u0628\u0646\u062f\u06cc \u0631\u0627 \u0628\u0647 \u0633\u062a\u0648\u0646 \u0647\u0627\u06cc \u0639\u062f\u062f\u06cc \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645.  \u0631\u0648\u0634\u200c\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641\u06cc \u0628\u0631\u0627\u06cc \u0627\u0646\u062c\u0627\u0645 \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f\u060c \u0627\u0645\u0627 \u06cc\u06a9\u06cc \u0627\u0632 \u0631\u0627\u06cc\u062c\u200c\u062a\u0631\u06cc\u0646 \u0631\u0648\u0634\u200c\u0647\u0627\u060c \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u062a\u06a9 \u062f\u0627\u063a \u0627\u0633\u062a.  \u062f\u0631 \u0631\u0645\u0632\u06af\u0630\u0627\u0631\u06cc \u062a\u06a9 \u062f\u0627\u063a\u060c \u0628\u0631\u0627\u06cc \u0647\u0631 \u0645\u0642\u062f\u0627\u0631 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0633\u062a\u0648\u0646 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc\u060c \u06cc\u06a9 \u0633\u062a\u0648\u0646 \u062c\u062f\u06cc\u062f \u0627\u06cc\u062c\u0627\u062f \u0645\u06cc \u0634\u0648\u062f.  \u0628\u0631\u0627\u06cc \u0633\u0637\u0631\u0647\u0627\u06cc\u06cc \u062f\u0631 \u0633\u062a\u0648\u0646 \u0648\u0627\u0642\u0639\u06cc \u06a9\u0647 \u0645\u0642\u062f\u0627\u0631 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u0648\u062c\u0648\u062f \u062f\u0627\u0634\u062a\u060c \u06cc\u06a9 \u0639\u062f\u062f 1 \u0628\u0647 \u0633\u0637\u0631 \u0645\u0631\u0628\u0648\u0637\u0647 \u0627\u0632 \u0633\u062a\u0648\u0646 \u0627\u06cc\u062c\u0627\u062f \u0634\u062f\u0647 \u0628\u0631\u0627\u06cc \u0622\u0646 \u0645\u0642\u062f\u0627\u0631 \u062e\u0627\u0635 \u0627\u0636\u0627\u0641\u0647 \u0645\u06cc \u0634\u0648\u062f.  \u0627\u06cc\u0646 \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u067e\u06cc\u0686\u06cc\u062f\u0647 \u0628\u0647 \u0646\u0638\u0631 \u0628\u0631\u0633\u062f \u0627\u0645\u0627 \u0645\u062b\u0627\u0644 \u0632\u06cc\u0631 \u0622\u0646 \u0631\u0627 \u0631\u0648\u0634\u0646 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0633\u062a\u0648\u0646 \u0647\u0627\u06cc \u062f\u0633\u062a\u0647 \u0628\u0646\u062f\u06cc \u0631\u0627 \u0628\u0647 \u0633\u062a\u0648\u0646 \u0647\u0627\u06cc \u0639\u062f\u062f\u06cc \u062a\u0628\u062f\u06cc\u0644 \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">price = pd.get_dummies(cars.price, prefix=<span class=\"hljs-string\">'price'<\/span>)\nmaint = pd.get_dummies(cars.maint, prefix=<span class=\"hljs-string\">'maint'<\/span>)\n\ndoors = pd.get_dummies(cars.doors, prefix=<span class=\"hljs-string\">'doors'<\/span>)\npersons = pd.get_dummies(cars.persons, prefix=<span class=\"hljs-string\">'persons'<\/span>)\n\nlug_capacity = pd.get_dummies(cars.lug_capacity, prefix=<span class=\"hljs-string\">'lug_capacity'<\/span>)\nsafety = pd.get_dummies(cars.safety, prefix=<span class=\"hljs-string\">'safety'<\/span>)\n\nlabels = pd.get_dummies(cars.output, prefix=<span class=\"hljs-string\">'condition'<\/span>)\n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u062c\u0645\u0648\u0639\u0647 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627\u06cc \u062e\u0648\u062f\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0634\u0634 \u0633\u062a\u0648\u0646 \u0627\u0648\u0644 \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0627\u0641\u0642\u06cc \u0627\u062f\u063a\u0627\u0645 \u06a9\u0646\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">X = pd.concat((price, maint, doors, persons, lug_capacity, safety) , axis=<span class=\"hljs-number\">1<\/span>)\n<\/code><\/pre>\n<p>\u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0628\u06cc\u0646\u06cc\u0645 \u0633\u062a\u0648\u0646 \u0628\u0631\u0686\u0633\u0628 \u0645\u0627 \u0627\u06a9\u0646\u0648\u0646 \u0686\u06af\u0648\u0646\u0647 \u0628\u0647 \u0646\u0638\u0631 \u0645\u06cc \u0631\u0633\u062f:<\/p>\n<pre><code class=\"hljs\">labels.head()\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/Introduction-to-tensorflow-2.0-3.PNG\" alt=\"\u0633\u062a\u0648\u0646 \u0647\u0627\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647\" title=\"\"><\/p>\n<p>\u0633\u062a\u0648\u0646 \u0628\u0631\u0686\u0633\u0628 \u0627\u0633\u0627\u0633\u0627\u064b \u06cc\u06a9 \u0646\u0633\u062e\u0647 \u06a9\u062f\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u06cc\u06a9\u0628\u0627\u0631\u0647 \u0627\u0632 \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u062a \u06a9\u0647 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u062e\u0648\u062f \u062f\u0627\u0634\u062a\u06cc\u0645.  \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc \u0686\u0647\u0627\u0631 \u0645\u0642\u062f\u0627\u0631 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0627\u0634\u062a: <code>unacc<\/code>\u060c <code>acc<\/code>\u060c <code>good<\/code> \u0648 <code>very good<\/code>.  \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0628\u0631\u0686\u0633\u0628 \u06a9\u062f\u06af\u0630\u0627\u0631\u06cc \u0634\u062f\u0647 \u06cc\u06a9 \u062f\u0627\u063a\u060c \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0686\u0647\u0627\u0631 \u0633\u062a\u0648\u0646 \u0631\u0627 \u0628\u0628\u06cc\u0646\u06cc\u062f\u060c \u06cc\u06a9\u06cc \u0628\u0631\u0627\u06cc \u0647\u0631 \u06cc\u06a9 \u0627\u0632 \u0645\u0642\u0627\u062f\u06cc\u0631 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f \u062f\u0631 \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc.  \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f 1 \u0631\u0627 \u062f\u0631 \u0633\u062a\u0648\u0646 \u0628\u0631\u0627\u06cc \u0645\u0642\u062f\u0627\u0631 \u0645\u0646\u062d\u0635\u0631 \u0628\u0647 \u0641\u0631\u062f\u06cc \u06a9\u0647 \u062f\u0631 \u0627\u0628\u062a\u062f\u0627 \u062f\u0631 \u0622\u0646 \u0633\u0637\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0634\u062a\u060c \u0628\u0628\u06cc\u0646\u06cc\u062f.  \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0645\u062b\u0627\u0644\u060c \u062f\u0631 \u067e\u0646\u062c \u0633\u0637\u0631 \u0627\u0648\u0644 \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc\u060c \u0645\u0642\u062f\u0627\u0631 \u0633\u062a\u0648\u0646 \u0628\u0648\u062f <code>unacc<\/code>.  \u062f\u0631 \u0633\u062a\u0648\u0646 \u0628\u0631\u0686\u0633\u0628\u200c\u0647\u0627\u060c \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u062f 1 \u0631\u0627 \u062f\u0631 \u067e\u0646\u062c \u0631\u062f\u06cc\u0641 \u0627\u0648\u0644 \u0628\u0628\u06cc\u0646\u06cc\u062f <code>condition_unacc<\/code> \u0633\u062a\u0648\u0646<\/p>\n<p>\u0627\u06a9\u0646\u0648\u0646 \u0628\u06cc\u0627\u06cc\u06cc\u062f \u0628\u0631\u0686\u0633\u0628 \u0647\u0627\u06cc \u062e\u0648\u062f \u0631\u0627 \u0628\u0647 \u0622\u0631\u0627\u06cc\u0647 NumPy \u062a\u0628\u062f\u06cc\u0644 \u06a9\u0646\u06cc\u0645 \u0632\u06cc\u0631\u0627 \u0645\u062f\u0644 \u0647\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u062f\u0631 TensorFlow \u0622\u0631\u0627\u06cc\u0647 \u0647\u0627\u06cc NumPy \u0631\u0627 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u0648\u0631\u0648\u062f\u06cc \u0645\u06cc \u067e\u0630\u06cc\u0631\u0646\u062f.<\/p>\n<pre><code class=\"hljs\">y = labels.values\n<\/code><\/pre>\n<p>\u0622\u062e\u0631\u06cc\u0646 \u0645\u0631\u062d\u0644\u0647 \u0642\u0628\u0644 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0628\u062a\u0648\u0627\u0646\u06cc\u0645 \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc TensorFlow 2.0 \u062e\u0648\u062f \u0631\u0627 \u0622\u0645\u0648\u0632\u0634 \u062f\u0647\u06cc\u0645\u060c \u062a\u0642\u0633\u06cc\u0645 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0628\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u0647\u0627\u06cc \u0622\u0645\u0648\u0632\u0634\u06cc \u0648 \u0622\u0632\u0645\u0627\u06cc\u0634\u06cc \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> sklearn.model_selection <span class=\"hljs-keyword\">import<\/span> train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=<span class=\"hljs-number\">0.20<\/span>, random_state=<span class=\"hljs-number\">42<\/span>)\n<\/code><\/pre>\n<h3 id=\"modeltraining\"><span class=\"ez-toc-section\" id=\"%d8%a2%d9%85%d9%88%d8%b2%d8%b4_%d9%85%d8%af%d9%84\"><\/span>\u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0628\u0631\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644\u060c \u0628\u06cc\u0627\u06cc\u06cc\u062f import \u06a9\u0644\u0627\u0633 \u0647\u0627\u06cc TensorFlow 2.0.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> tensorflow.keras.layers <span class=\"hljs-keyword\">import<\/span> Input, Dense, Activation,Dropout\n<span class=\"hljs-keyword\">from<\/span> tensorflow.keras.models <span class=\"hljs-keyword\">import<\/span> Model\n<\/code><\/pre>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0642\u0628\u0644\u0627\u064b \u06af\u0641\u062a\u0645\u060c TensorFlow 2.0 \u0627\u0632 Keras API \u0628\u0631\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f.  \u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627 \u0645\u0627 \u0627\u0633\u0627\u0633\u0627 import <code>Input<\/code>\u060c <code>Dense<\/code>\u060c <code>Activation<\/code>\u060c \u0648 <code>Dropout<\/code> \u06a9\u0644\u0627\u0633 \u0647\u0627 \u0627\u0632 <code>tensorflow.keras.layers<\/code> \u0645\u062f\u0648\u0644.  \u0628\u0647 \u0647\u0645\u06cc\u0646 \u062a\u0631\u062a\u06cc\u0628\u060c \u0645\u0627 \u0646\u06cc\u0632 <code>import<\/code> \u0631\u0627 <code>Model<\/code> \u06a9\u0644\u0627\u0633 \u0627\u0632 <code>tensorflow.keras.models<\/code> \u0645\u062f\u0648\u0644.<\/p>\n<p>\u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u06cc \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0645\u0627 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">input_layer = Input(shape=(X.shape(<span class=\"hljs-number\">1<\/span>),))\ndense_layer_1 = Dense(<span class=\"hljs-number\">15<\/span>, activation=<span class=\"hljs-string\">'relu'<\/span>)(input_layer)\ndense_layer_2 = Dense(<span class=\"hljs-number\">10<\/span>, activation=<span class=\"hljs-string\">'relu'<\/span>)(dense_layer_1)\noutput = Dense(y.shape(<span class=\"hljs-number\">1<\/span>), activation=<span class=\"hljs-string\">'softmax'<\/span>)(dense_layer_2)\n\nmodel = Model(inputs=input_layer, outputs=output)\nmodel.<span class=\"hljs-built_in\">compile<\/span>(loss=<span class=\"hljs-string\">'categorical_crossentropy'<\/span>, optimizer=<span class=\"hljs-string\">'adam'<\/span>, metrics=(<span class=\"hljs-string\">'acc'<\/span>))\n<\/code><\/pre>\n<p>\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0627\u0632 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u067e\u06cc\u062f\u0627\u0633\u062a\u060c \u0645\u062f\u0644 \u0634\u0627\u0645\u0644 \u0633\u0647 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0627\u0633\u062a.  \u062f\u0648 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0627\u0648\u0644 \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628 \u0634\u0627\u0645\u0644 15 \u0648 10 \u06af\u0631\u0647 \u0628\u0627 <code>relu<\/code> \u0639\u0645\u0644\u06a9\u0631\u062f \u0641\u0639\u0627\u0644 \u0633\u0627\u0632\u06cc  \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0646\u0647\u0627\u06cc\u06cc \u0634\u0627\u0645\u0644 4 \u06af\u0631\u0647 (<code>y.shape(1) == 4<\/code>) \u0648 \u0627\u0644\u0641 <code>softmax<\/code> \u062a\u0627\u0628\u0639 \u0641\u0639\u0627\u0644 \u0633\u0627\u0632\u06cc \u0632\u06cc\u0631\u0627 \u0627\u06cc\u0646 \u06cc\u06a9 \u06a9\u0627\u0631 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0627\u0633\u062a.  \u0645\u062f\u0644 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a <code>categorical_crossentropy<\/code> \u0639\u0645\u0644\u06a9\u0631\u062f \u0627\u0632 \u062f\u0633\u062a \u062f\u0627\u062f\u0646 \u0648 <code>adam<\/code> \u0628\u0647\u06cc\u0646\u0647 \u0633\u0627\u0632  \u0645\u0639\u06cc\u0627\u0631 \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u062f\u0642\u062a \u0627\u0633\u062a.<\/p>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u062e\u0644\u0627\u0635\u0647 \u0645\u062f\u0644 \u0631\u0627 \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-built_in\">print<\/span>(model.summary())\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<pre><code class=\"hljs\">Model: \"model\"\n_________________________________________________________________\nLayer (type)                 Output Shape              Param #\n=================================================================\ninput_1 (InputLayer)         ((None, 21))              0\n_________________________________________________________________\ndense (Dense)                (None, 15)                330\n_________________________________________________________________\ndense_1 (Dense)              (None, 10)                160\n_________________________________________________________________\ndense_2 (Dense)              (None, 4)                 44\n=================================================================\nTotal params: 534\nTrainable params: 534\nNon-trainable params: 0\n_________________________________________________________________\nNone\n<\/code><\/pre>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0628\u0631\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0631\u0627 \u0627\u062c\u0631\u0627 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\">history = model.fit(X_train, y_train, batch_size=<span class=\"hljs-number\">8<\/span>, epochs=<span class=\"hljs-number\">50<\/span>, verbose=<span class=\"hljs-number\">1<\/span>, validation_split=<span class=\"hljs-number\">0.2<\/span>)\n<\/code><\/pre>\n<p>\u0627\u06cc\u0646 \u0645\u062f\u0644 \u0628\u0631\u0627\u06cc 50 \u062f\u0648\u0631\u0647 \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f\u060c \u0627\u0645\u0627 \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0628\u0647 \u062e\u0627\u0637\u0631 \u0641\u0636\u0627\u060c \u0646\u062a\u06cc\u062c\u0647 \u062a\u0646\u0647\u0627 5 \u062f\u0648\u0631\u0647 \u0622\u062e\u0631 \u0646\u0645\u0627\u06cc\u0634 \u062f\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f:<\/p>\n<pre><code class=\"hljs\">Epoch 45\/50\n1105\/1105 (==============================) - 0s 219us\/sample - loss: 0.0114 - acc: 1.0000 - val_loss: 0.0606 - val_acc: 0.9856\nEpoch 46\/50\n1105\/1105 (==============================) - 0s 212us\/sample - loss: 0.0113 - acc: 1.0000 - val_loss: 0.0497 - val_acc: 0.9856\nEpoch 47\/50\n1105\/1105 (==============================) - 0s 219us\/sample - loss: 0.0102 - acc: 1.0000 - val_loss: 0.0517 - val_acc: 0.9856\nEpoch 48\/50\n1105\/1105 (==============================) - 0s 218us\/sample - loss: 0.0091 - acc: 1.0000 - val_loss: 0.0536 - val_acc: 0.9856\nEpoch 49\/50\n1105\/1105 (==============================) - 0s 213us\/sample - loss: 0.0095 - acc: 1.0000 - val_loss: 0.0513 - val_acc: 0.9819\nEpoch 50\/50\n1105\/1105 (==============================) - 0s 209us\/sample - loss: 0.0080 - acc: 1.0000 - val_loss: 0.0536 - val_acc: 0.9856\n<\/code><\/pre>\n<p>\u062f\u0631 \u067e\u0627\u06cc\u0627\u0646 \u062f\u0648\u0631\u0647 50\u060c \u0645\u0627 \u062f\u0642\u062a \u0622\u0645\u0648\u0632\u0634\u06cc 100\u066a \u062f\u0631 \u062d\u0627\u0644\u06cc \u06a9\u0647 \u062f\u0642\u062a \u0627\u0639\u062a\u0628\u0627\u0631 98.56\u066a \u0627\u0633\u062a\u060c \u062f\u0627\u0631\u06cc\u0645 \u06a9\u0647 \u0686\u0634\u0645\u06af\u06cc\u0631 \u0627\u0633\u062a.<\/p>\n<p>\u0627\u062c\u0627\u0632\u0647 \u062f\u0647\u06cc\u062f \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0639\u0645\u0644\u06a9\u0631\u062f \u0645\u062f\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u062e\u0648\u062f \u0631\u0627 \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u06a9\u0646\u06cc\u0645 \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062a\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">score = model.evaluate(X_test, y_test, verbose=<span class=\"hljs-number\">1<\/span>)\n\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"Test Score:\"<\/span>, score(<span class=\"hljs-number\">0<\/span>))\n<span class=\"hljs-built_in\">print<\/span>(<span class=\"hljs-string\">\"Test Accuracy:\"<\/span>, score(<span class=\"hljs-number\">1<\/span>))\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u062e\u0631\u0648\u062c\u06cc \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">WARNING:tensorflow:Falling back from v2 loop because of error: Failed to find data adapter that can handle input: &lt;class 'pandas.core.frame.DataFrame'&gt;, &lt;class 'NoneType'&gt;\n346\/346 (==============================) - 0s 55us\/sample - loss: 0.0605 - acc: 0.9740\nTest Score: 0.06045335989359314\nTest Accuracy: 0.9739884\n<\/code><\/pre>\n<p>\u0645\u062f\u0644 \u0645\u0627 \u0628\u0647 \u062f\u0642\u062a 97.39\u066a \u062f\u0633\u062a \u0645\u06cc \u06cc\u0627\u0628\u062f \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062a\u0633\u062a  \u0627\u06af\u0631\u0686\u0647 \u06a9\u0645\u06cc \u06a9\u0645\u062a\u0631 \u0627\u0632 \u062f\u0642\u062a \u0622\u0645\u0648\u0632\u0634 100 \u062f\u0631\u0635\u062f \u0627\u0633\u062a\u060c \u0627\u0645\u0627 \u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 \u0627\u06cc\u0646 \u0648\u0627\u0642\u0639\u06cc\u062a \u06a9\u0647 \u0645\u0627 \u0628\u0647 \u0637\u0648\u0631 \u062a\u0635\u0627\u062f\u0641\u06cc \u062a\u0639\u062f\u0627\u062f \u0644\u0627\u06cc\u0647\u200c\u0647\u0627 \u0648 \u06af\u0631\u0647\u200c\u0647\u0627 \u0631\u0627 \u0627\u0646\u062a\u062e\u0627\u0628 \u06a9\u0631\u062f\u06cc\u0645\u060c \u0628\u0633\u06cc\u0627\u0631 \u062e\u0648\u0628 \u0627\u0633\u062a.  \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0644\u0627\u06cc\u0647 \u0647\u0627\u06cc \u0628\u06cc\u0634\u062a\u0631\u06cc \u0631\u0627 \u0628\u0627 \u06af\u0631\u0647 \u0647\u0627\u06cc \u0628\u06cc\u0634\u062a\u0631 \u0628\u0647 \u0645\u062f\u0644 \u0627\u0636\u0627\u0641\u0647 \u06a9\u0646\u06cc\u062f \u0648 \u0628\u0628\u06cc\u0646\u06cc\u062f \u0622\u06cc\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u062f \u0646\u062a\u0627\u06cc\u062c \u0628\u0647\u062a\u0631\u06cc \u0628\u06af\u06cc\u0631\u06cc\u062f \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u0647\u0627\u06cc \u0627\u0639\u062a\u0628\u0627\u0631 \u0633\u0646\u062c\u06cc \u0648 \u062a\u0633\u062a<\/p>\n<h2 id=\"regressionwithtensorflow20\"><span class=\"ez-toc-section\" id=\"%d8%b1%da%af%d8%b1%d8%b3%db%8c%d9%88%d9%86_%d8%a8%d8%a7_tensorflow_20\"><\/span>\u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0628\u0627 TensorFlow 2.0<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>\u062f\u0631 \u0645\u0633\u0626\u0644\u0647 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646\u060c \u0647\u062f\u0641 \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u06cc\u06a9 \u0645\u0642\u062f\u0627\u0631 \u067e\u06cc\u0648\u0633\u062a\u0647 \u0627\u0633\u062a.  \u062f\u0631 \u0627\u06cc\u0646 \u0628\u062e\u0634 \u0631\u0648\u0634 \u062d\u0644 \u0645\u0634\u06a9\u0644 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0628\u0627 TensorFlow 2.0 \u0631\u0627 \u062e\u0648\u0627\u0647\u06cc\u062f \u062f\u06cc\u062f<\/p>\n<h3 id=\"thedataset\"><span class=\"ez-toc-section\" id=\"%d9%85%d8%ac%d9%85%d9%88%d8%b9%d9%87_%d8%af%d8%a7%d8%af%d9%87-2\"><\/span>\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0627\u06cc\u0646 \u0645\u0634\u06a9\u0644 \u0631\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0647 \u0635\u0648\u0631\u062a \u0631\u0627\u06cc\u06af\u0627\u0646 \u0627\u0632 \u0627\u06cc\u0646\u062c\u0627 \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0631\u062f <a rel=\"nofollow noopener\" target=\"_blank\" href=\"https:\/\/drive.google.com\/file\/d\/1mVmGNx6cbfvRHC_DvF12ZL3wGLSHD9f_\/view\">\u0627\u06cc\u0646 \u0644\u06cc\u0646\u06a9<\/a>.  \u0641\u0627\u06cc\u0644 CSV \u0631\u0627 \u062f\u0627\u0646\u0644\u0648\u062f \u06a9\u0646\u06cc\u062f.<\/p>\n<p>\u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0631\u0627 \u0648\u0627\u0631\u062f \u0645\u06cc \u06a9\u0646\u062f.  \u0641\u0631\u0627\u0645\u0648\u0634 \u0646\u06a9\u0646\u06cc\u062f \u06a9\u0647 \u0645\u0633\u06cc\u0631 \u0641\u0627\u06cc\u0644 \u062f\u0627\u062f\u0647 CSV \u062e\u0648\u062f \u0631\u0627 \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0647\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">petrol_cons = pd.read_csv(<span class=\"hljs-string\">r'\/content\/drive\/My Drive\/datasets\/petrol_consumption.csv'<\/span>)\n<\/code><\/pre>\n<p>\u0627\u062c\u0627\u0632\u0647 \u062f\u0647\u06cc\u062f print \u067e\u0646\u062c \u0631\u062f\u06cc\u0641 \u0627\u0648\u0644 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0627\u0632 \u0637\u0631\u06cc\u0642 <code>head()<\/code> \u062a\u0627\u0628\u0639:<\/p>\n<pre><code class=\"hljs\">petrol_cons.head()\n<\/code><\/pre>\n<p><strong>\u062e\u0631\u0648\u062c\u06cc:<\/strong><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/rasanegar.com\/blog\/wp-content\/uploads\/2024\/01\/Introduction-to-tensorflow-2.0-4.PNG\" alt=\"\u0631\u062f\u06cc\u0641 \u0647\u0627\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647\" title=\"\"><\/p>\n<p>\u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u06a9\u0647 \u067e\u0646\u062c \u0633\u062a\u0648\u0646 \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f.  \u0645\u062f\u0644 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0622\u0645\u0648\u0632\u0634 \u062f\u0627\u062f\u0647 \u062e\u0648\u0627\u0647\u062f \u0634\u062f \u0631\u0648\u06cc \u0686\u0647\u0627\u0631 \u0633\u062a\u0648\u0646 \u0627\u0648\u0644\u060c \u06cc\u0639\u0646\u06cc <code>Petrol_tax<\/code>\u060c <code>Average_income<\/code>\u060c <code>Paved_Highways<\/code>\u060c \u0648 <code>Population_Driver_License(%)<\/code>.  \u0645\u0642\u062f\u0627\u0631 \u0622\u062e\u0631\u06cc\u0646 \u0633\u062a\u0648\u0646 \u06cc\u0639\u0646\u06cc <code>Petrol_Consumption<\/code> \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u062e\u0648\u0627\u0647\u062f \u0634\u062f.  \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u0645\u06cc \u0628\u06cc\u0646\u06cc\u062f \u0647\u06cc\u0686 \u0645\u0642\u062f\u0627\u0631 \u06af\u0633\u0633\u062a\u0647 \u0627\u06cc \u0628\u0631\u0627\u06cc \u0633\u062a\u0648\u0646 \u062e\u0631\u0648\u062c\u06cc \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0631\u062f\u060c \u0628\u0644\u06a9\u0647 \u0645\u0642\u062f\u0627\u0631 \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0634\u062f\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0647\u0631 \u0645\u0642\u062f\u0627\u0631 \u067e\u06cc\u0648\u0633\u062a\u0647 \u0628\u0627\u0634\u062f.<\/p>\n<h3 id=\"datapreprocessing\"><span class=\"ez-toc-section\" id=\"%d9%be%db%8c%d8%b4_%d9%be%d8%b1%d8%af%d8%a7%d8%b2%d8%b4_%d8%af%d8%a7%d8%af%d9%87_%d9%87%d8%a7\"><\/span>\u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634 \u062f\u0627\u062f\u0647 \u0647\u0627<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u062f\u0631 \u0645\u0631\u062d\u0644\u0647 \u067e\u06cc\u0634 \u067e\u0631\u062f\u0627\u0632\u0634 \u062f\u0627\u062f\u0647 \u0647\u0627\u060c \u0645\u0627 \u0628\u0647 \u0633\u0627\u062f\u06af\u06cc \u062f\u0627\u062f\u0647 \u0647\u0627 \u0631\u0627 \u0628\u0647 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627 \u0648 \u0628\u0631\u0686\u0633\u0628 \u0647\u0627 \u062a\u0642\u0633\u06cc\u0645 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u0648 \u0633\u067e\u0633 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0631\u0627 \u0628\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u0647\u0627\u06cc \u0622\u0632\u0645\u0627\u06cc\u0634\u06cc \u0648 \u0622\u0645\u0648\u0632\u0634\u06cc \u062a\u0642\u0633\u06cc\u0645 \u0645\u06cc \u06a9\u0646\u06cc\u0645.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u062f\u0627\u062f\u0647 \u0647\u0627 \u0639\u0627\u062f\u06cc \u062e\u0648\u0627\u0647\u0646\u062f \u0634\u062f.  \u0628\u0631\u0627\u06cc \u0645\u0634\u06a9\u0644\u0627\u062a \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0628\u0647 \u0637\u0648\u0631 \u06a9\u0644\u06cc\u060c \u0648 \u0628\u0631\u0627\u06cc \u0645\u0634\u06a9\u0644\u0627\u062a \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0628\u0627 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642\u060c \u0628\u0647 \u0634\u062f\u062a \u062a\u0648\u0635\u06cc\u0647 \u0645\u06cc \u0634\u0648\u062f \u06a9\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u062e\u0648\u062f \u0631\u0627 \u0639\u0627\u062f\u06cc \u06a9\u0646\u06cc\u062f.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u062a\u0645\u0627\u0645 \u0633\u062a\u0648\u0646 \u0647\u0627 \u0639\u062f\u062f\u06cc \u0647\u0633\u062a\u0646\u062f\u060c \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0646\u06cc\u0627\u0632\u06cc \u0628\u0647 \u06a9\u062f\u06af\u0630\u0627\u0631\u06cc \u06cc\u06a9\u0628\u0627\u0631\u0647 \u0633\u062a\u0648\u0646 \u0647\u0627 \u0646\u06cc\u0633\u062a.<\/p>\n<pre><code class=\"hljs\">X = petrol_cons.iloc(:, <span class=\"hljs-number\">0<\/span>:<span class=\"hljs-number\">4<\/span>).values\ny = petrol_cons.iloc(:, <span class=\"hljs-number\">4<\/span>).values\n\n<span class=\"hljs-keyword\">from<\/span> sklearn.model_selection <span class=\"hljs-keyword\">import<\/span> train_test_split\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=<span class=\"hljs-number\">0.2<\/span>, random_state=<span class=\"hljs-number\">0<\/span>)\n\n<span class=\"hljs-keyword\">from<\/span> sklearn.preprocessing <span class=\"hljs-keyword\">import<\/span> StandardScaler\n\nsc = StandardScaler()\nX_train = sc.fit_transform(X_train)\nX_test = sc.transform(X_test)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0628\u0627\u0644\u0627\u060c \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0648\u06cc\u0698\u06af\u06cc <code>X<\/code>\u060c \u0686\u0647\u0627\u0631 \u0633\u062a\u0648\u0646 \u0627\u0648\u0644 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u06af\u0646\u062c\u0627\u0646\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.  \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u0628\u0631\u0686\u0633\u0628 <code>y<\/code>\u060c \u0641\u0642\u0637 \u0633\u062a\u0648\u0646 5 \u06af\u0646\u062c\u0627\u0646\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.  \u062f\u0631 \u0645\u0631\u062d\u0644\u0647 \u0628\u0639\u062f\u060c \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0628\u0647 \u0627\u0646\u062f\u0627\u0632\u0647 \u0622\u0645\u0648\u0632\u0634 \u0648 \u0622\u0632\u0645\u0648\u0646 \u0627\u0632 \u0637\u0631\u06cc\u0642 \u062a\u0642\u0633\u06cc\u0645 \u0645\u06cc \u0634\u0648\u0646\u062f <code>train_test_split<\/code> \u0631\u0648\u0634 \u0627\u0632 <code>sklearn.model_selection<\/code> \u0645\u062f\u0648\u0644.  \u0627\u0631\u0632\u0634 \u0628\u0631\u0627\u06cc <code>test_size<\/code> \u0648\u06cc\u0698\u06af\u06cc 0.2 \u0627\u0633\u062a \u06a9\u0647 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0639\u0646\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0645\u062c\u0645\u0648\u0639\u0647 \u0622\u0632\u0645\u0627\u06cc\u0634\u06cc \u0634\u0627\u0645\u0644 20\u066a \u0627\u0632 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0627\u0635\u0644\u06cc \u0627\u0633\u062a \u0648 \u0645\u062c\u0645\u0648\u0639\u0647 \u0622\u0645\u0648\u0632\u0634\u06cc \u0634\u0627\u0645\u0644 80\u066a \u0628\u0627\u0642\u06cc \u0645\u0627\u0646\u062f\u0647 \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0627\u0635\u0644\u06cc \u0627\u0633\u062a.  \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a\u060c <code>StandardScaler<\/code> \u06a9\u0644\u0627\u0633 \u0627\u0632 <code>sklearn.preprocessing<\/code> \u0645\u0627\u0698\u0648\u0644 \u0628\u0631\u0627\u06cc \u0645\u0642\u06cc\u0627\u0633 \u0628\u0646\u062f\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f.<\/p>\n<h3 id=\"modeltraining\"><span class=\"ez-toc-section\" id=\"%d8%a2%d9%85%d9%88%d8%b2%d8%b4_%d9%85%d8%af%d9%84-2\"><\/span>\u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>\u0642\u062f\u0645 \u0628\u0639\u062f\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u062f\u0644 \u062e\u0648\u062f \u0627\u0633\u062a.  \u0627\u06cc\u0646 process \u06a9\u0627\u0645\u0644\u0627 \u0634\u0628\u06cc\u0647 \u0628\u0647 \u0622\u0645\u0648\u0632\u0634 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0627\u0633\u062a.  \u062a\u0646\u0647\u0627 \u062a\u063a\u06cc\u06cc\u0631 \u062f\u0631 \u062a\u0627\u0628\u0639 \u0636\u0631\u0631 \u0648 \u062a\u0639\u062f\u0627\u062f \u06af\u0631\u0647 \u0647\u0627 \u062f\u0631 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u062e\u0631\u0648\u062c\u06cc \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.  \u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u0627\u06a9\u0646\u0648\u0646 \u06cc\u06a9 \u0645\u0642\u062f\u0627\u0631 \u067e\u06cc\u0648\u0633\u062a\u0647 \u0631\u0627 \u067e\u06cc\u0634\u200c\u0628\u06cc\u0646\u06cc \u0645\u06cc\u200c\u06a9\u0646\u06cc\u0645\u060c \u0644\u0627\u06cc\u0647 \u062e\u0631\u0648\u062c\u06cc \u0641\u0642\u0637 1 \u062e\u0648\u0627\u0647\u062f \u062f\u0627\u0634\u062a node.<\/p>\n<pre><code class=\"hljs\">input_layer = Input(shape=(X.shape(<span class=\"hljs-number\">1<\/span>),))\ndense_layer_1 = Dense(<span class=\"hljs-number\">100<\/span>, activation=<span class=\"hljs-string\">'relu'<\/span>)(input_layer)\ndense_layer_2 = Dense(<span class=\"hljs-number\">50<\/span>, activation=<span class=\"hljs-string\">'relu'<\/span>)(dense_layer_1)\ndense_layer_3 = Dense(<span class=\"hljs-number\">25<\/span>, activation=<span class=\"hljs-string\">'relu'<\/span>)(dense_layer_2)\noutput = Dense(<span class=\"hljs-number\">1<\/span>)(dense_layer_3)\n\nmodel = Model(inputs=input_layer, outputs=output)\nmodel.<span class=\"hljs-built_in\">compile<\/span>(loss=<span class=\"hljs-string\">\"mean_squared_error\"<\/span> , optimizer=<span class=\"hljs-string\">\"adam\"<\/span>, metrics=(<span class=\"hljs-string\">\"mean_squared_error\"<\/span>))\n<\/code><\/pre>\n<p>\u0645\u062f\u0644 \u0645\u0627 \u0627\u0632 \u0686\u0647\u0627\u0631 \u0644\u0627\u06cc\u0647 \u0645\u062a\u0631\u0627\u06a9\u0645 \u0628\u0627 100\u060c 50\u060c 25 \u0648 1 \u062a\u0634\u06a9\u06cc\u0644 \u0634\u062f\u0647 \u0627\u0633\u062a. node\u060c \u0628\u0647 \u062a\u0631\u062a\u06cc\u0628.  \u0628\u0631\u0627\u06cc \u0645\u0634\u06a9\u0644\u0627\u062a \u0631\u06af\u0631\u0633\u06cc\u0648\u0646\u060c \u06cc\u06a9\u06cc \u0627\u0632 \u0645\u062a\u062f\u0627\u0648\u0644 \u062a\u0631\u06cc\u0646 \u062a\u0648\u0627\u0628\u0639 \u0627\u0632 \u062f\u0633\u062a \u062f\u0627\u062f\u0646 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u0634\u0648\u062f <code>mean_squared_error<\/code>.  \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u062e\u0644\u0627\u0635\u0647 \u0627\u06cc \u0627\u0632 \u0645\u062f\u0644 \u0631\u0627 \u0686\u0627\u067e \u0645\u06cc \u06a9\u0646\u062f:<\/p>\n<pre><code class=\"hljs\">Model: \"model_2\"\n_________________________________________________________________\nLayer (type)                 Output Shape              Param #\n=================================================================\ninput_4 (InputLayer)         ((None, 4))               0\n_________________________________________________________________\ndense_10 (Dense)             (None, 100)               500\n_________________________________________________________________\ndense_11 (Dense)             (None, 50)                5050\n_________________________________________________________________\ndense_12 (Dense)             (None, 25)                1275\n_________________________________________________________________\ndense_13 (Dense)             (None, 1)                 26\n=================================================================\nTotal params: 6,851\nTrainable params: 6,851\nNon-trainable params: 0\n<\/code><\/pre>\n<p>\u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u0645\u06cc\u200c\u062a\u0648\u0627\u0646\u06cc\u0645 \u0645\u062f\u0644 \u0631\u0627 \u0628\u0627 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0622\u0645\u0648\u0632\u0634 \u062f\u0647\u06cc\u0645:<\/p>\n<pre><code class=\"hljs\">history = model.fit(X_train, y_train, batch_size=<span class=\"hljs-number\">2<\/span>, epochs=<span class=\"hljs-number\">100<\/span>, verbose=<span class=\"hljs-number\">1<\/span>, validation_split=<span class=\"hljs-number\">0.2<\/span>)\n<\/code><\/pre>\n<p>\u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0646\u062a\u06cc\u062c\u0647 5 \u062f\u0648\u0631\u0647 \u0622\u0645\u0648\u0632\u0634\u06cc \u06af\u0630\u0634\u062a\u0647 \u0627\u0633\u062a:<\/p>\n<pre><code class=\"hljs\">Epoch 96\/100\n30\/30 (==============================) - 0s 2ms\/sample - loss: 510.3316 - mean_squared_error: 510.3317 - val_loss: 10383.5234 - val_mean_squared_error: 10383.5234\nEpoch 97\/100\n30\/30 (==============================) - 0s 2ms\/sample - loss: 523.3454 - mean_squared_error: 523.3453 - val_loss: 10488.3036 - val_mean_squared_error: 10488.3037\nEpoch 98\/100\n30\/30 (==============================) - 0s 2ms\/sample - loss: 514.8281 - mean_squared_error: 514.8281 - val_loss: 10379.5087 - val_mean_squared_error: 10379.5088\nEpoch 99\/100\n30\/30 (==============================) - 0s 2ms\/sample - loss: 504.0919 - mean_squared_error: 504.0919 - val_loss: 10301.3304 - val_mean_squared_error: 10301.3311\nEpoch 100\/100\n30\/30 (==============================) - 0s 2ms\/sample - loss: 532.7809 - mean_squared_error: 532.7809 - val_loss: 10325.1699 - val_mean_squared_error: 10325.1709\n<\/code><\/pre>\n<p>\u0628\u0631\u0627\u06cc \u0627\u0631\u0632\u06cc\u0627\u0628\u06cc \u0639\u0645\u0644\u06a9\u0631\u062f \u06cc\u06a9 \u0645\u062f\u0644 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0631\u0648\u06cc \u06cc\u06a9 \u0645\u062c\u0645\u0648\u0639\u0647 \u062a\u0633\u062a\u060c \u06cc\u06a9\u06cc \u0627\u0632 \u0645\u062a\u062f\u0627\u0648\u0644 \u062a\u0631\u06cc\u0646 \u0645\u0639\u06cc\u0627\u0631\u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0633\u062a root \u062e\u0637\u0627\u06cc \u0645\u06cc\u0627\u0646\u06af\u06cc\u0646 \u0645\u0631\u0628\u0639\u0627\u062a.  \u0645\u0627 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0645\u06cc\u0627\u0646\u06af\u06cc\u0646 \u0645\u0631\u0628\u0639\u0627\u062a \u062e\u0637\u0627 \u0631\u0627 \u0628\u06cc\u0646 \u0645\u0642\u0627\u062f\u06cc\u0631 \u067e\u06cc\u0634 \u0628\u06cc\u0646\u06cc \u0634\u062f\u0647 \u0648 \u0648\u0627\u0642\u0639\u06cc \u0627\u0632 \u0637\u0631\u06cc\u0642 the \u067e\u06cc\u062f\u0627 \u06a9\u0646\u06cc\u0645 <code>mean_squared_error<\/code> \u06a9\u0644\u0627\u0633 \u0627\u0632 <code>sklearn.metrics<\/code> \u0645\u062f\u0648\u0644.  \u0633\u067e\u0633 \u0645\u06cc \u062a\u0648\u0627\u0646\u06cc\u0645 \u0645\u0631\u0628\u0639 \u0631\u0627 \u0628\u06af\u06cc\u0631\u06cc\u0645 root \u0627\u0632 \u0645\u06cc\u0627\u0646\u06af\u06cc\u0646 \u0645\u062c\u0630\u0648\u0631 \u062e\u0637\u0627\u06cc \u062d\u0627\u0635\u0644.  \u0628\u0647 \u0627\u0633\u06a9\u0631\u06cc\u067e\u062a \u0632\u06cc\u0631 \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f:<\/p>\n<pre><code class=\"hljs\"><span class=\"hljs-keyword\">from<\/span> sklearn.metrics <span class=\"hljs-keyword\">import<\/span> mean_squared_error\n<span class=\"hljs-keyword\">from<\/span> math <span class=\"hljs-keyword\">import<\/span> sqrt\n\npred_train = model.predict(X_train)\n<span class=\"hljs-built_in\">print<\/span>(np.sqrt(mean_squared_error(y_train,pred_train)))\n\npred = model.predict(X_test)\n<span class=\"hljs-built_in\">print<\/span>(np.sqrt(mean_squared_error(y_test,pred)))\n<\/code><\/pre>\n<p>\u062e\u0631\u0648\u062c\u06cc \u0645\u06cc\u0627\u0646\u06af\u06cc\u0646 \u0645\u0631\u0628\u0639\u0627\u062a \u062e\u0637\u0627 \u0631\u0627 \u0628\u0631\u0627\u06cc \u0647\u0631 \u062f\u0648 \u0645\u062c\u0645\u0648\u0639\u0647 \u0622\u0645\u0648\u0632\u0634\u06cc \u0648 \u0622\u0632\u0645\u0627\u06cc\u0634\u06cc \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f.  \u0646\u062a\u0627\u06cc\u062c \u0646\u0634\u0627\u0646 \u0645\u06cc \u062f\u0647\u062f \u06a9\u0647 \u0639\u0645\u0644\u06a9\u0631\u062f \u0645\u062f\u0644 \u0628\u0647\u062a\u0631 \u0627\u0633\u062a \u0631\u0648\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u0622\u0645\u0648\u0632\u0634\u06cc \u0627\u0632 \u0632\u0645\u0627\u0646 root \u0645\u06cc\u0627\u0646\u06af\u06cc\u0646 \u0645\u0642\u062f\u0627\u0631 \u062e\u0637\u0627\u06cc \u0645\u0631\u0628\u0639 \u0628\u0631\u0627\u06cc \u0645\u062c\u0645\u0648\u0639\u0647 \u0622\u0645\u0648\u0632\u0634\u06cc \u06a9\u0645\u062a\u0631 \u0627\u0633\u062a.  \u0645\u062f\u0644 \u0645\u0627 \u0628\u06cc\u0634 \u0627\u0632 \u062d\u062f \u0645\u0646\u0627\u0633\u0628 \u0627\u0633\u062a.  \u062f\u0644\u06cc\u0644 \u0622\u0646 \u0648\u0627\u0636\u062d \u0627\u0633\u062a\u060c \u0645\u0627 \u0641\u0642\u0637 48 \u0631\u06a9\u0648\u0631\u062f \u062f\u0631 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u062f\u0627\u0634\u062a\u06cc\u0645.  \u0633\u0639\u06cc \u06a9\u0646\u06cc\u062f \u0645\u062f\u0644 \u0647\u0627\u06cc \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0631\u0627 \u0628\u0627 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 \u0628\u0632\u0631\u06af\u062a\u0631 \u0622\u0645\u0648\u0632\u0634 \u062f\u0647\u06cc\u062f \u062a\u0627 \u0646\u062a\u0627\u06cc\u062c \u0628\u0647\u062a\u0631\u06cc \u0628\u06af\u06cc\u0631\u06cc\u062f.<\/p>\n<pre><code class=\"hljs\">50.43599665058207\n84.31961060849562\n<\/code><\/pre>\n<h2 id=\"conclusion\"><span class=\"ez-toc-section\" id=\"%d9%86%d8%aa%db%8c%d8%ac%d9%87\"><\/span>\u0646\u062a\u06cc\u062c\u0647<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>TensorFlow 2.0 \u0622\u062e\u0631\u06cc\u0646 \u0646\u0633\u062e\u0647 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 TensorFlow \u06af\u0648\u06af\u0644 \u0628\u0631\u0627\u06cc \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0627\u0633\u062a.  \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0631\u0648\u0634 \u0627\u06cc\u062c\u0627\u062f \u0645\u062f\u0644 \u0647\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0631\u0627 \u0628\u0627 TensorFlow 2.0 \u067e\u0648\u0634\u0634 \u0645\u06cc \u062f\u0647\u062f.  \u062f\u0633\u062a \u062f\u0627\u0634\u062a\u0646 -\u0631\u0648\u06cc \u067e\u06cc\u0634\u0646\u0647\u0627\u062f \u0645\u06cc\u200c\u06a9\u0646\u0645 \u0645\u062b\u0627\u0644\u200c\u0647\u0627\u06cc \u0627\u0631\u0627\u0626\u0647 \u0634\u062f\u0647 \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0631\u0627 \u062a\u0645\u0631\u06cc\u0646 \u06a9\u0646\u06cc\u062f \u0648 \u0633\u0639\u06cc \u06a9\u0646\u06cc\u062f \u0645\u062f\u0644\u200c\u0647\u0627\u06cc \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0648 \u0637\u0628\u0642\u0647\u200c\u0628\u0646\u062f\u06cc \u0633\u0627\u062f\u0647 \u0631\u0627 \u0628\u0627 TensorFlow 2.0 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647\u200c\u0647\u0627\u06cc \u062f\u0627\u062f\u0647 \u062f\u06cc\u06af\u0631 \u0627\u06cc\u062c\u0627\u062f \u06a9\u0646\u06cc\u062f.<\/p>\n<\/div>\n<p><script>\n                        !function(f,b,e,v,n,t,s)\n                        {if(f.fbq)return;n=f.fbq=function(){n.callMethod?\n                        n.callMethod.apply(n,arguments):n.queue.push(arguments)};\n                        if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';\n                        n.queue=();t=b.createElement(e);t.async=!0;\n                        t.src=v;s=b.getElementsByTagName(e)(0);\n                        s.parentNode.insertBefore(t,s)}(window, document,'script',\n                        'https:\/\/connect.facebook.net\/en_US\/fbevents.js');\n                        fbq('init', '525232124909042');\n                        fbq('track', 'PageView');\n                    <\/script>    (\u0628\u0631\u0686\u0633\u0628\u200c\u0647\u0627 \u0628\u0647 \u062a\u0631\u062c\u0645\u0647)# python<br \/>\n<br \/><br \/>\n<br \/>\u0645\u0646\u062a\u0634\u0631 \u0634\u062f\u0647 \u062f\u0631 1403-01-19 09:17:03<br \/>\n<\/p>\n\n\n<div class=\"kk-star-ratings kksr-auto kksr-align-center kksr-valign-bottom\"\n    data-payload='{&quot;align&quot;:&quot;center&quot;,&quot;id&quot;:&quot;15975&quot;,&quot;slug&quot;:&quot;default&quot;,&quot;valign&quot;:&quot;bottom&quot;,&quot;ignore&quot;:&quot;&quot;,&quot;reference&quot;:&quot;auto&quot;,&quot;class&quot;:&quot;&quot;,&quot;count&quot;:&quot;0&quot;,&quot;legendonly&quot;:&quot;&quot;,&quot;readonly&quot;:&quot;&quot;,&quot;score&quot;:&quot;0&quot;,&quot;starsonly&quot;:&quot;&quot;,&quot;best&quot;:&quot;5&quot;,&quot;gap&quot;:&quot;5&quot;,&quot;greet&quot;:&quot;\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628&quot;,&quot;legend&quot;:&quot;0\\\/5 (0 \u0631\u0627\u06cc)&quot;,&quot;size&quot;:&quot;30&quot;,&quot;title&quot;:&quot;Tensorflow 2.0: \u062d\u0644 \u0645\u0633\u0627\u0626\u0644 \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646&quot;,&quot;width&quot;:&quot;0&quot;,&quot;_legend&quot;:&quot;{score}\\\/{best} ({count} \u0631\u0627\u06cc)&quot;,&quot;font_factor&quot;:&quot;1.25&quot;}'>\n            \n<div class=\"kksr-stars\">\n    \n<div class=\"kksr-stars-inactive\">\n            <div class=\"kksr-star\" data-star=\"1\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"2\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"3\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"4\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" data-star=\"5\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n    \n<div class=\"kksr-stars-active\" style=\"width: 0px;\">\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n            <div class=\"kksr-star\" style=\"padding-left: 5px\">\n            \n\n<div class=\"kksr-icon\" style=\"width: 30px; height: 30px;\"><\/div>\n        <\/div>\n    <\/div>\n<\/div>\n                \n\n<div class=\"kksr-legend\" style=\"font-size: 24px;\">\n            <span class=\"kksr-muted\">\u0627\u0645\u062a\u06cc\u0627\u0632 \u0634\u0645\u0627 \u0628\u0647 \u0627\u06cc\u0646 \u0645\u0637\u0644\u0628<\/span>\n    <\/div>\n    <\/div>\n","protected":false},"excerpt":{"rendered":"<p><span class=\"span-reading-time rt-reading-time\" style=\"display: block;\"><span class=\"rt-label rt-prefix\">\u0632\u0645\u0627\u0646 \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0645\u0637\u0627\u0644\u0639\u0647: <\/span> <span class=\"rt-time\"> 9<\/span> <span class=\"rt-label rt-postfix\">\u062f\u0642\u06cc\u0642\u0647<\/span><\/span>\u067e\u0633 \u0627\u0632 \u0647\u06cc\u0627\u0647\u0648\u06cc \u0628\u0633\u06cc\u0627\u0631\u060c \u0633\u0631\u0627\u0646\u062c\u0627\u0645 \u06af\u0648\u06af\u0644 \u0645\u0646\u062a\u0634\u0631 \u0634\u062f TensorFlow 2.0 \u06a9\u0647 \u0622\u062e\u0631\u06cc\u0646 \u0646\u0633\u062e\u0647 \u067e\u0644\u062a\u0641\u0631\u0645 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u067e\u0631\u0686\u0645\u062f\u0627\u0631 \u06af\u0648\u06af\u0644 \u0627\u0633\u062a. \u0628\u0633\u06cc\u0627\u0631\u06cc \u0627\u0632 \u0648\u06cc\u0698\u06af\u06cc\u200c\u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0627\u0646\u062a\u0638\u0627\u0631 \u062f\u0631 TensorFlow 2.0 \u0645\u0639\u0631\u0641\u06cc \u0634\u062f\u0647\u200c\u0627\u0646\u062f. \u0627\u06cc\u0646 \u0645\u0642\u0627\u0644\u0647 \u0628\u0647 \u0637\u0648\u0631 \u062e\u0644\u0627\u0635\u0647 \u0631\u0648\u0634 \u062a\u0648\u0633\u0639\u0647 \u0645\u062f\u0644 \u0647\u0627\u06cc \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0648 \u0631\u06af\u0631\u0633\u06cc\u0648\u0646 \u0633\u0627\u062f\u0647 \u0631\u0627 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 TensorFlow 2.0 \u067e\u0648\u0634\u0634 \u0645\u06cc \u062f\u0647\u062f. \u0637\u0628\u0642\u0647 \u0628\u0646\u062f\u06cc \u0628\u0627 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":15976,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1743,620],"tags":[],"class_list":["post-15975","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-python","category-programming"],"acf":[],"_links":{"self":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/15975","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/comments?post=15975"}],"version-history":[{"count":0,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/posts\/15975\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media\/15976"}],"wp:attachment":[{"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/media?parent=15975"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/categories?post=15975"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rasanegaar.com\/blog\/wp-json\/wp\/v2\/tags?post=15975"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}