{"id":43212,"date":"2025-07-30T16:18:40","date_gmt":"2025-07-30T07:18:40","guid":{"rendered":"https:\/\/techgym.jp\/?p=43212"},"modified":"2025-07-30T16:18:44","modified_gmt":"2025-07-30T07:18:44","slug":"python-tensorflow","status":"publish","type":"post","link":"https:\/\/techgym.jp\/column\/python-tensorflow\/","title":{"rendered":"Python\u3067\u6a5f\u68b0\u5b66\u7fd2\u30fb\u6df1\u5c64\u5b66\u7fd2\uff01 TensorFlow\u3092\u5fb9\u5e95\u89e3\u8aac\uff1a\u57fa\u672c\u304b\u3089\u5b9f\u8df5\u307e\u3067"},"content":{"rendered":"\n<div id=\"model-response-message-contentr_5926a3585e601f04\" class=\"markdown markdown-main-panel stronger enable-updated-hr-color\" dir=\"ltr\"><br \/>\n<p>\u00a0<\/p>\n<p>\u300cAI\u3092\u958b\u767a\u3057\u3066\u307f\u305f\u3044\u300d\u300c\u753b\u50cf\u8a8d\u8b58\u3084\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306b\u6311\u6226\u3057\u305f\u3044\u300d\u305d\u3046\u601d\u3063\u305f\u3068\u304d\u3001\u307e\u305a\u540d\u524d\u304c\u6319\u304c\u308b\u306e\u304c**TensorFlow\uff08\u30c6\u30f3\u30bd\u30eb\u30d5\u30ed\u30fc\uff09**\u3067\u3059\u3002Google\u304c\u958b\u767a\u3057\u305f\u3053\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e9\u30a4\u30d6\u30e9\u30ea\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u3001\u7279\u306b\u6df1\u5c64\u5b66\u7fd2\uff08\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\uff09\u306e\u5206\u91ce\u3067\u4e16\u754c\u4e2d\u306e\u7814\u7a76\u8005\u3084\u958b\u767a\u8005\u306b\u5e83\u304f\u5229\u7528\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u3053\u306e\u8a18\u4e8b\u3067\u306f\u3001TensorFlow\u306e\u57fa\u672c\u7684\u306a\u6982\u5ff5\u304b\u3089\u3001\u306a\u305c\u3053\u308c\u307b\u3069\u307e\u3067\u306b\u4eba\u6c17\u304c\u3042\u308b\u306e\u304b\u3001\u305d\u3057\u3066\u5b9f\u969b\u306b\u7c21\u5358\u306a\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u624b\u9806\u307e\u3067\u3001\u521d\u5fc3\u8005\u306e\u65b9\u306b\u3082\u5206\u304b\u308a\u3084\u3059\u304f\u5fb9\u5e95\u7684\u306b\u89e3\u8aac\u3057\u307e\u3059\u3002TensorFlow\u3092\u30de\u30b9\u30bf\u30fc\u3057\u3066\u3001\u6700\u5148\u7aef\u306eAI\u958b\u767a\u306e\u6249\u3092\u958b\u304d\u307e\u3057\u3087\u3046\uff01<\/p>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>TensorFlow\u3068\u306f\uff1f \u306a\u305c\u6a5f\u68b0\u5b66\u7fd2\u306b\u4f7f\u3046\u306e\u304b\uff1f<\/h2>\n<p>\u00a0<\/p>\n<p><b>TensorFlow<\/b>\u306f\u3001\u30c7\u30fc\u30bf\u30d5\u30ed\u30fc\u30b0\u30e9\u30d5\u3092\u7528\u3044\u305f\u6570\u5024\u8a08\u7b97\u306e\u305f\u3081\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002\u7279\u306b\u3001\u5927\u898f\u6a21\u306a\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u3001\u4e2d\u3067\u3082\u6df1\u5c64\u5b66\u7fd2\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u3068\u8a13\u7df4\u306b\u7279\u5316\u3057\u3066\u8a2d\u8a08\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u306a\u305cTensorFlow\u304c\u6a5f\u68b0\u5b66\u7fd2\u30fb\u6df1\u5c64\u5b66\u7fd2\u306b\u3088\u304f\u4f7f\u308f\u308c\u308b\u306e\u3067\u3057\u3087\u3046\u304b\uff1f<\/p>\n<ul>\n<li>\n<p><b>\u6df1\u5c64\u5b66\u7fd2\u306b\u7279\u5316<\/b>: \u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u69cb\u7bc9\u3001\u8a13\u7df4\u3001\u8a55\u4fa1\u306b\u5fc5\u8981\u306a\u3042\u3089\u3086\u308b\u6a5f\u80fd\uff08\u591a\u5c64\u30d1\u30fc\u30bb\u30d7\u30c8\u30ed\u30f3\u3001CNN\u3001RNN\u306a\u3069\uff09\u304c\u63c3\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u9ad8\u901f\u306a\u6570\u5024\u8a08\u7b97<\/b>: \u30c6\u30f3\u30bd\u30eb\uff08\u591a\u6b21\u5143\u914d\u5217\uff09\u3092\u4f7f\u3063\u305f\u8a08\u7b97\u306b\u6700\u9069\u5316\u3055\u308c\u3066\u304a\u308a\u3001CPU\u3060\u3051\u3067\u306a\u304fGPU\uff08\u30b0\u30e9\u30d5\u30a3\u30c3\u30af\u30b9\u51e6\u7406\u30e6\u30cb\u30c3\u30c8\uff09\u3084TPU\uff08\u30c6\u30f3\u30bd\u30eb\u51e6\u7406\u30e6\u30cb\u30c3\u30c8\uff09\u3068\u3044\u3063\u305f\u30cf\u30fc\u30c9\u30a6\u30a7\u30a2\u30a2\u30af\u30bb\u30e9\u30ec\u30fc\u30bf\u3092\u52b9\u7387\u7684\u306b\u5229\u7528\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u306b\u3088\u308a\u3001\u5927\u898f\u6a21\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3068\u8907\u96d1\u306a\u30e2\u30c7\u30eb\u306e\u8a13\u7df4\u6642\u9593\u3092\u5927\u5e45\u306b\u77ed\u7e2e\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u67d4\u8edf\u306a\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3<\/b>: \u30e2\u30c7\u30eb\u306e\u69cb\u7bc9\u65b9\u6cd5\u306b\u9ad8\u3044\u67d4\u8edf\u6027\u304c\u3042\u308a\u3001\u7814\u7a76\u7528\u9014\u304b\u3089\u672c\u756a\u904b\u7528\u307e\u3067\u3001\u591a\u69d8\u306a\u30cb\u30fc\u30ba\u306b\u5bfe\u5fdc\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>Keras\u3068\u306e\u7d71\u5408<\/b>: TensorFlow 2.0\u4ee5\u964d\u3067\u306f\u3001\u9ad8\u30ec\u30d9\u30ebAPI\u3067\u3042\u308bKeras\u304cTensorFlow\u306e\u4e3b\u8981\u306aAPI\u3068\u3057\u3066\u7d71\u5408\u3055\u308c\u3066\u304a\u308a\u3001\u76f4\u611f\u7684\u3067\u7c21\u6f54\u306a\u30b3\u30fc\u30c9\u3067\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3067\u304d\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u5927\u898f\u6a21\u306a\u30a8\u30b3\u30b7\u30b9\u30c6\u30e0<\/b>: \u30e2\u30c7\u30eb\u306e\u30c7\u30d7\u30ed\u30a4\u3001\u30e2\u30d0\u30a4\u30eb\u30c7\u30d0\u30a4\u30b9\u3078\u306e\u6700\u9069\u5316\u3001\u30d6\u30e9\u30a6\u30b6\u3067\u306e\u5b9f\u884c\u306a\u3069\u3001\u958b\u767a\u304b\u3089\u904b\u7528\u307e\u3067\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308b\u5305\u62ec\u7684\u306a\u30c4\u30fc\u30eb\u7fa4\uff08TensorFlow Extended (TFX), TensorFlow.js, TensorFlow Lite\u306a\u3069\uff09\u304c\u63d0\u4f9b\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u6d3b\u767a\u306a\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u3068\u8c4a\u5bcc\u306a\u30ea\u30bd\u30fc\u30b9<\/b>: Google\u304c\u4e3b\u5c0e\u3057\u3066\u304a\u308a\u3001\u4e16\u754c\u4e2d\u306e\u958b\u767a\u8005\u3084\u7814\u7a76\u8005\u306b\u5229\u7528\u3055\u308c\u3066\u3044\u308b\u305f\u3081\u3001\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3001\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3001\u30d5\u30a9\u30fc\u30e9\u30e0\u306a\u3069\u306e\u60c5\u5831\u304c\u975e\u5e38\u306b\u8c4a\u5bcc\u3067\u3059\u3002<\/p>\n<\/li>\n<\/ul>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>TensorFlow\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u65b9\u6cd5<\/h2>\n<p>\u00a0<\/p>\n<p>TensorFlow\u3092\u4f7f\u3046\u306b\u306f\u3001\u307e\u305aPC\u306b\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002Python\u306e\u30d1\u30c3\u30b1\u30fc\u30b8\u7ba1\u7406\u30c4\u30fc\u30eb<code>pip<\/code>\u3092\u4f7f\u3063\u3066\u7c21\u5358\u306b\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3067\u304d\u307e\u3059\u3002\u901a\u5e38\u306fCPU\u7248\u3067\u5341\u5206\u3067\u3059\u304c\u3001GPU\u3092\u4f7f\u3046\u5834\u5408\u306fCUDA Toolkit\u306a\u3069\u306eNVIDIA\u88fd\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u306e\u4e8b\u524d\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u5fc5\u8981\u3067\u3059\u3002<\/p>\n<ol start=\"1\">\n<li>\n<p><b>\u30b3\u30de\u30f3\u30c9\u30d7\u30ed\u30f3\u30d7\u30c8\uff08Windows\uff09<\/b> \u307e\u305f\u306f <b>\u30bf\u30fc\u30df\u30ca\u30eb\uff08macOS\/Linux\uff09<\/b> \u3092\u958b\u304d\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p>\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3057\u307e\u3059\u3002<\/p>\n<div class=\"code-block ng-tns-c1455175435-685 ng-animate-disabled ng-trigger ng-trigger-codeBlockRevealAnimation\">\n<div class=\"code-block-decoration header-formatted gds-title-s ng-tns-c1455175435-685 ng-star-inserted\"><span class=\"ng-tns-c1455175435-685\">Bash<\/span>\n<div class=\"buttons ng-tns-c1455175435-685 ng-star-inserted\">\u00a0<\/div>\n<\/div>\n<div class=\"formatted-code-block-internal-container ng-tns-c1455175435-685\">\n<div class=\"animated-opacity ng-tns-c1455175435-685\">\n<pre class=\"ng-tns-c1455175435-685\"><code class=\"code-container formatted ng-tns-c1455175435-685\" role=\"text\" data-test-id=\"code-content\">pip install tensorflow\n<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<p>GPU\u3092\u5229\u7528\u3059\u308b\u5834\u5408\u306f\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u6307\u5b9a\u3057\u307e\u3059\uff08\u74b0\u5883\u69cb\u7bc9\u304c\u8907\u96d1\u306b\u306a\u308b\u305f\u3081\u3001\u6700\u521d\u306fCPU\u7248\u3067\u8a66\u3059\u306e\u304c\u304a\u3059\u3059\u3081\u3067\u3059\uff09\u3002<\/p>\n<div class=\"code-block ng-tns-c1455175435-686 ng-animate-disabled ng-trigger ng-trigger-codeBlockRevealAnimation\">\n<div class=\"code-block-decoration header-formatted gds-title-s ng-tns-c1455175435-686 ng-star-inserted\"><span class=\"ng-tns-c1455175435-686\">Bash<\/span>\n<div class=\"buttons ng-tns-c1455175435-686 ng-star-inserted\">\u00a0<\/div>\n<\/div>\n<div class=\"formatted-code-block-internal-container ng-tns-c1455175435-686\">\n<div class=\"animated-opacity ng-tns-c1455175435-686\">\n<pre class=\"ng-tns-c1455175435-686\"><code class=\"code-container formatted ng-tns-c1455175435-686\" role=\"text\" data-test-id=\"code-content\">pip install tensorflow[and-cuda] <span class=\"hljs-comment\"># TensorFlow 2.10 \u4ee5\u964d<\/span>\n<span class=\"hljs-comment\"># \u307e\u305f\u306f pip install tensorflow-gpu (\u53e4\u3044\u30d0\u30fc\u30b8\u30e7\u30f3)<\/span>\n<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<\/li>\n<\/ol>\n<p>\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u304c\u6210\u529f\u3057\u305f\u304b\u78ba\u8a8d\u3059\u308b\u306b\u306f\u3001Python\u306e\u30a4\u30f3\u30bf\u30e9\u30af\u30c6\u30a3\u30d6\u30b7\u30a7\u30eb\u3067<code>import tensorflow as tf<\/code>\u3068\u5165\u529b\u3057\u3001\u30a8\u30e9\u30fc\u304c\u51fa\u306a\u3051\u308c\u3070OK\u3067\u3059\u3002<\/p>\n<div class=\"code-block ng-tns-c1455175435-687 ng-animate-disabled ng-trigger ng-trigger-codeBlockRevealAnimation\">\n<div class=\"code-block-decoration header-formatted gds-title-s ng-tns-c1455175435-687 ng-star-inserted\"><span class=\"ng-tns-c1455175435-687\">Python<\/span>\n<div class=\"buttons ng-tns-c1455175435-687 ng-star-inserted\">\u00a0<\/div>\n<\/div>\n<div class=\"formatted-code-block-internal-container ng-tns-c1455175435-687\">\n<div class=\"animated-opacity ng-tns-c1455175435-687\">\n<pre class=\"ng-tns-c1455175435-687\"><code class=\"code-container formatted ng-tns-c1455175435-687\" role=\"text\" data-test-id=\"code-content\"><span class=\"hljs-keyword\">import<\/span> tensorflow <span class=\"hljs-keyword\">as<\/span> tf\nprint(tf.__version__)\n<span class=\"hljs-comment\"># \u51fa\u529b\u4f8b: 2.x.x<\/span>\n<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>TensorFlow\u3067\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u958b\u767a\u306e\u57fa\u672c\u30b9\u30c6\u30c3\u30d7<\/h2>\n<p>\u00a0<\/p>\n<p>TensorFlow\uff08Keras API\uff09\u3092\u4f7f\u3063\u3066\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u958b\u767a\u3059\u308b\u969b\u306e\u57fa\u672c\u7684\u306a\u6d41\u308c\u306f\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n<ol start=\"1\">\n<li>\n<p><b>\u30c7\u30fc\u30bf\u306e\u6e96\u5099<\/b>: \u30e2\u30c7\u30eb\u306b\u5165\u529b\u3059\u308b\u30c7\u30fc\u30bf\uff08\u7279\u5fb4\u91cf\u3068\u30e9\u30d9\u30eb\uff09\u3092\u6e96\u5099\u3057\u307e\u3059\u3002\u901a\u5e38\u306fNumPy\u914d\u5217\u3084Pandas DataFrame\u3068\u3057\u3066\u6271\u308f\u308c\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30e2\u30c7\u30eb\u306e\u69cb\u7bc9<\/b>: \u3069\u306e\u3088\u3046\u306a\u7a2e\u985e\u306e\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\uff08\u5c64\u306e\u6570\u3001\u5404\u5c64\u306e\u30cb\u30e5\u30fc\u30ed\u30f3\u6570\u3001\u6d3b\u6027\u5316\u95a2\u6570\u306a\u3069\uff09\u3092\u4f7f\u7528\u3059\u308b\u304b\u3092\u5b9a\u7fa9\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30e2\u30c7\u30eb\u306e\u30b3\u30f3\u30d1\u30a4\u30eb<\/b>: \u8a13\u7df4\u30d7\u30ed\u30bb\u30b9\u3092\u5b9a\u7fa9\u3057\u307e\u3059\u3002\u5177\u4f53\u7684\u306b\u306f\u3001\u6700\u9069\u5316\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\uff08Optimizer\uff09\u3001\u640d\u5931\u95a2\u6570\uff08Loss Function\uff09\u3001\u8a55\u4fa1\u6307\u6a19\uff08Metrics\uff09\u3092\u8a2d\u5b9a\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30e2\u30c7\u30eb\u306e\u8a13\u7df4 (\u5b66\u7fd2)<\/b>: \u6e96\u5099\u3057\u305f\u30c7\u30fc\u30bf\u3092\u4f7f\u3063\u3066\u30e2\u30c7\u30eb\u3092\u8a13\u7df4\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1<\/b>: \u8a13\u7df4\u3055\u308c\u3066\u3044\u306a\u3044\u30c7\u30fc\u30bf\uff08\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\uff09\u3092\u4f7f\u3063\u3066\u3001\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u4e88\u6e2c<\/b>: \u8a13\u7df4\u6e08\u307f\u30e2\u30c7\u30eb\u3092\u4f7f\u3063\u3066\u3001\u65b0\u3057\u3044\u30c7\u30fc\u30bf\u306b\u5bfe\u3059\u308b\u4e88\u6e2c\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n<\/li>\n<\/ol>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>TensorFlow\u3067\u7c21\u5358\u306a\u7dda\u5f62\u56de\u5e30\u30e2\u30c7\u30eb\u3092\u4f5c\u3063\u3066\u307f\u3088\u3046\uff01<\/h2>\n<p>\u00a0<\/p>\n<p>\u3053\u3053\u3067\u306f\u3001\u6700\u3082\u30b7\u30f3\u30d7\u30eb\u306a\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u306e\u4e00\u3064\u3067\u3042\u308b<b>\u7dda\u5f62\u56de\u5e30<\/b>\u3092TensorFlow\uff08Keras API\uff09\u3067\u5b9f\u88c5\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002\u3053\u308c\u306f\u3001\u4e0e\u3048\u3089\u308c\u305f\u5165\u529b\u3068\u51fa\u529b\u306e\u95a2\u4fc2\u3092\u76f4\u7dda\u3067\u8fd1\u4f3c\u3059\u308b\u30e2\u30c7\u30eb\u3067\u3059\u3002<\/p>\n<div class=\"code-block ng-tns-c1455175435-688 ng-animate-disabled ng-trigger ng-trigger-codeBlockRevealAnimation\">\n<div class=\"code-block-decoration header-formatted gds-title-s ng-tns-c1455175435-688 ng-star-inserted\"><span class=\"ng-tns-c1455175435-688\">Python<\/span>\n<div class=\"buttons ng-tns-c1455175435-688 ng-star-inserted\">\u00a0<\/div>\n<\/div>\n<div class=\"formatted-code-block-internal-container ng-tns-c1455175435-688\">\n<div class=\"animated-opacity ng-tns-c1455175435-688\">\n<pre class=\"ng-tns-c1455175435-688\"><code class=\"code-container formatted ng-tns-c1455175435-688\" role=\"text\" data-test-id=\"code-content\"><span class=\"hljs-keyword\">import<\/span> tensorflow <span class=\"hljs-keyword\">as<\/span> tf\n<span class=\"hljs-keyword\">import<\/span> numpy <span class=\"hljs-keyword\">as<\/span> np\n\n<span class=\"hljs-comment\"># 1. \u30c7\u30fc\u30bf\u306e\u6e96\u5099<\/span>\n<span class=\"hljs-comment\"># \u4f8b: y = 2x + 1 \u3068\u3044\u3046\u95a2\u4fc2\u306e\u30c7\u30fc\u30bf<\/span>\nX = np.array([<span class=\"hljs-number\">0<\/span>, <span class=\"hljs-number\">1<\/span>, <span class=\"hljs-number\">2<\/span>, <span class=\"hljs-number\">3<\/span>, <span class=\"hljs-number\">4<\/span>, <span class=\"hljs-number\">5<\/span>, <span class=\"hljs-number\">6<\/span>, <span class=\"hljs-number\">7<\/span>, <span class=\"hljs-number\">8<\/span>, <span class=\"hljs-number\">9<\/span>], dtype=<span class=\"hljs-built_in\">float<\/span>)\ny = np.array([<span class=\"hljs-number\">1<\/span>, <span class=\"hljs-number\">3<\/span>, <span class=\"hljs-number\">5<\/span>, <span class=\"hljs-number\">7<\/span>, <span class=\"hljs-number\">9<\/span>, <span class=\"hljs-number\">11<\/span>, <span class=\"hljs-number\">13<\/span>, <span class=\"hljs-number\">15<\/span>, <span class=\"hljs-number\">17<\/span>, <span class=\"hljs-number\">19<\/span>], dtype=<span class=\"hljs-built_in\">float<\/span>)\n\n<span class=\"hljs-comment\"># 2. \u30e2\u30c7\u30eb\u306e\u69cb\u7bc9 (Keras Sequential API\u3092\u4f7f\u7528)<\/span>\n<span class=\"hljs-comment\"># \u975e\u5e38\u306b\u30b7\u30f3\u30d7\u30eb\u306a\u5358\u4e00\u306e\u30cb\u30e5\u30fc\u30ed\u30f3\uff08\u7dda\u5f62\u5c64\uff09\u30e2\u30c7\u30eb<\/span>\nmodel = tf.keras.Sequential([\n    tf.keras.layers.Dense(units=<span class=\"hljs-number\">1<\/span>, input_shape=[<span class=\"hljs-number\">1<\/span>]) <span class=\"hljs-comment\"># \u5165\u529b1\u6b21\u5143\u3001\u51fa\u529b1\u6b21\u5143\u306e\u5c64<\/span>\n])\n\n<span class=\"hljs-comment\"># 3. \u30e2\u30c7\u30eb\u306e\u30b3\u30f3\u30d1\u30a4\u30eb<\/span>\n<span class=\"hljs-comment\"># \u6700\u9069\u5316\u624b\u6cd5: Adam, \u640d\u5931\u95a2\u6570: \u5e73\u5747\u4e8c\u4e57\u8aa4\u5dee (MSE)<\/span>\nmodel.<span class=\"hljs-built_in\">compile<\/span>(optimizer=<span class=\"hljs-string\">'adam'<\/span>, loss=<span class=\"hljs-string\">'mean_squared_error'<\/span>)\n\n<span class=\"hljs-comment\"># 4. \u30e2\u30c7\u30eb\u306e\u8a13\u7df4 (\u5b66\u7fd2)<\/span>\n<span class=\"hljs-comment\"># \u30a8\u30dd\u30c3\u30af\u6570 (\u8a13\u7df4\u306e\u7e70\u308a\u8fd4\u3057\u56de\u6570) \u3092\u6307\u5b9a<\/span>\nprint(<span class=\"hljs-string\">\"\u30e2\u30c7\u30eb\u8a13\u7df4\u4e2d...\"<\/span>)\nhistory = model.fit(X, y, epochs=<span class=\"hljs-number\">500<\/span>, verbose=<span class=\"hljs-number\">0<\/span>) <span class=\"hljs-comment\"># verbose=0 \u3067\u8a13\u7df4\u4e2d\u306e\u51fa\u529b\u6291\u5236<\/span>\nprint(<span class=\"hljs-string\">\"\u8a13\u7df4\u5b8c\u4e86\uff01\"<\/span>)\n\n<span class=\"hljs-comment\"># 5. \u30e2\u30c7\u30eb\u306e\u8a55\u4fa1 (\u3053\u3053\u3067\u306f\u8a13\u7df4\u30c7\u30fc\u30bf\u3067\u7c21\u6613\u7684\u306b\u8a55\u4fa1)<\/span>\nloss = model.evaluate(X, y, verbose=<span class=\"hljs-number\">0<\/span>)\nprint(<span class=\"hljs-string\">f\"\u8a13\u7df4\u30c7\u30fc\u30bf\u3067\u306e\u6700\u7d42\u640d\u5931: <span class=\"hljs-subst\">{loss:<span class=\"hljs-number\">.4<\/span>f}<\/span>\"<\/span>)\n\n<span class=\"hljs-comment\"># 6. \u4e88\u6e2c<\/span>\ntest_X = np.array([<span class=\"hljs-number\">10.0<\/span>, <span class=\"hljs-number\">15.0<\/span>], dtype=<span class=\"hljs-built_in\">float<\/span>)\npredictions = model.predict(test_X)\nprint(<span class=\"hljs-string\">f\"\u5165\u529b <span class=\"hljs-subst\">{test_X[<span class=\"hljs-number\">0<\/span>]}<\/span> \u306e\u4e88\u6e2c: <span class=\"hljs-subst\">{predictions[<span class=\"hljs-number\">0<\/span>][<span class=\"hljs-number\">0<\/span>]:<span class=\"hljs-number\">.2<\/span>f}<\/span>\"<\/span>)\nprint(<span class=\"hljs-string\">f\"\u5165\u529b <span class=\"hljs-subst\">{test_X[<span class=\"hljs-number\">1<\/span>]}<\/span> \u306e\u4e88\u6e2c: <span class=\"hljs-subst\">{predictions[<span class=\"hljs-number\">1<\/span>][<span class=\"hljs-number\">0<\/span>]:<span class=\"hljs-number\">.2<\/span>f}<\/span>\"<\/span>)\n\n<span class=\"hljs-comment\"># \u30e2\u30c7\u30eb\u306e\u91cd\u307f\u3068\u30d0\u30a4\u30a2\u30b9\u3092\u78ba\u8a8d (\u5b66\u7fd2\u7d50\u679c)<\/span>\nweights, bias = model.layers[<span class=\"hljs-number\">0<\/span>].get_weights()\nprint(<span class=\"hljs-string\">f\"\u5b66\u7fd2\u3055\u308c\u305f\u91cd\u307f (W): <span class=\"hljs-subst\">{weights[<span class=\"hljs-number\">0<\/span>][<span class=\"hljs-number\">0<\/span>]:<span class=\"hljs-number\">.2<\/span>f}<\/span>\"<\/span>)\nprint(<span class=\"hljs-string\">f\"\u5b66\u7fd2\u3055\u308c\u305f\u30d0\u30a4\u30a2\u30b9 (b): <span class=\"hljs-subst\">{bias[<span class=\"hljs-number\">0<\/span>]:<span class=\"hljs-number\">.2<\/span>f}<\/span>\"<\/span>)\n<span class=\"hljs-comment\"># \u671f\u5f85\u3055\u308c\u308b\u51fa\u529b: W \u2248 2.00, b \u2248 1.00 (y = 2x + 1 \u306b\u8fd1\u3044\u5024)<\/span>\n<\/code><\/pre>\n<\/div>\n<\/div>\n<\/div>\n<p>\u00a0<\/p>\n<h3>\u30b3\u30fc\u30c9\u306e\u89e3\u8aac<\/h3>\n<p>\u00a0<\/p>\n<ul>\n<li>\n<p><b><code>import tensorflow as tf<\/code><\/b>: TensorFlow\u3092<code>tf<\/code>\u3068\u3044\u3046\u30a8\u30a4\u30ea\u30a2\u30b9\u3067\u30a4\u30f3\u30dd\u30fc\u30c8\u3059\u308b\u4e00\u822c\u7684\u306a\u6163\u7fd2\u3067\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b><code>import numpy as np<\/code><\/b>: \u30c7\u30fc\u30bf\u64cd\u4f5c\u306b\u4fbf\u5229\u306aNumPy\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b><code>X<\/code>, <code>y<\/code><\/b>: <code>X<\/code>\u304c\u5165\u529b\u30c7\u30fc\u30bf\uff08\u7279\u5fb4\u91cf\uff09\u3001<code>y<\/code>\u304c\u51fa\u529b\u30c7\u30fc\u30bf\uff08\u30e9\u30d9\u30eb\uff09\u3067\u3059\u3002NumPy\u914d\u5217\u3068\u3057\u3066\u6e96\u5099\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b><code>tf.keras.Sequential([...])<\/code><\/b>: Keras\u306eSequential API\u3092\u4f7f\u3063\u3066\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u3053\u308c\u306f\u5c64\u3092\u7a4d\u307f\u91cd\u306d\u308b\u3088\u3046\u306b\u3057\u3066\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9\u3059\u308b\u6700\u3082\u7c21\u5358\u306a\u65b9\u6cd5\u3067\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b><code>tf.keras.layers.Dense(...)<\/code><\/b>: \u6700\u3082\u57fa\u672c\u7684\u306a\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u5c64\uff08\u5168\u7d50\u5408\u5c64\uff09\u3067\u3059\u3002<\/p>\n<ul>\n<li>\n<p><code>units=1<\/code>: \u3053\u306e\u5c64\u304c1\u3064\u306e\u51fa\u529b\uff08\u30cb\u30e5\u30fc\u30ed\u30f3\uff09\u3092\u6301\u3064\u3053\u3068\u3092\u610f\u5473\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><code>input_shape=[1]<\/code>: \u5165\u529b\u30c7\u30fc\u30bf\u304c1\u6b21\u5143\u3067\u3042\u308b\u3053\u3068\u3092\u793a\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><b><code>model.compile(...)<\/code><\/b>: \u30e2\u30c7\u30eb\u306e\u8a13\u7df4\u65b9\u6cd5\u3092\u8a2d\u5b9a\u3057\u307e\u3059\u3002<\/p>\n<ul>\n<li>\n<p><code>optimizer='adam'<\/code>: \u8a13\u7df4\u30d7\u30ed\u30bb\u30b9\u3092\u6700\u9069\u5316\u3059\u308b\u305f\u3081\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\uff08\u52fe\u914d\u964d\u4e0b\u6cd5\u306e\u9032\u5316\u7248\uff09\u3092\u6307\u5b9a\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><code>loss='mean_squared_error'<\/code>: \u30e2\u30c7\u30eb\u306e\u4e88\u6e2c\u304c\u3069\u308c\u3060\u3051\u5b9f\u969b\u306e\u5024\u3068\u7570\u306a\u308b\u304b\u3092\u6e2c\u308b\u305f\u3081\u306e\u95a2\u6570\uff08\u7dda\u5f62\u56de\u5e30\u3067\u306f\u3088\u304f\u4f7f\u308f\u308c\u307e\u3059\uff09\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><b><code>model.fit(X, y, epochs=500, verbose=0)<\/code><\/b>: \u30e2\u30c7\u30eb\u3092\u8a13\u7df4\u3057\u307e\u3059\u3002<\/p>\n<ul>\n<li>\n<p><code>X<\/code>, <code>y<\/code>: \u8a13\u7df4\u30c7\u30fc\u30bf\u306e\u7279\u5fb4\u91cf\u3068\u30e9\u30d9\u30eb\u3002<\/p>\n<\/li>\n<li>\n<p><code>epochs=500<\/code>: \u8a13\u7df4\u30c7\u30fc\u30bf\u3092500\u56de\u7e70\u308a\u8fd4\u3057\u5b66\u7fd2\u3055\u305b\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><code>verbose=0<\/code>: \u8a13\u7df4\u4e2d\u306e\u30ed\u30b0\u51fa\u529b\u3092\u6291\u5236\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<\/ul>\n<\/li>\n<li>\n<p><b><code>model.evaluate(X, y, verbose=0)<\/code><\/b>: \u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u8a55\u4fa1\u3057\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u8a13\u7df4\u30c7\u30fc\u30bf\u305d\u306e\u3082\u306e\u3067\u8a55\u4fa1\u3057\u3066\u3044\u307e\u3059\u304c\u3001\u901a\u5e38\u306f\u8a13\u7df4\u7528\u3068\u30c6\u30b9\u30c8\u7528\u3067\u30c7\u30fc\u30bf\u3092\u5206\u5272\u3057\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b><code>model.predict(test_X)<\/code><\/b>: \u8a13\u7df4\u6e08\u307f\u306e\u30e2\u30c7\u30eb\u3092\u4f7f\u3063\u3066\u3001\u65b0\u3057\u3044\u5165\u529b\u30c7\u30fc\u30bf\u306b\u5bfe\u3059\u308b\u4e88\u6e2c\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n<\/li>\n<\/ul>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>TensorFlow\u958b\u767a\u306e\u6b21\u306e\u30b9\u30c6\u30c3\u30d7<\/h2>\n<p>\u00a0<\/p>\n<p>\u3053\u306e\u7c21\u5358\u306a\u7dda\u5f62\u56de\u5e30\u30e2\u30c7\u30eb\u306fTensorFlow\u306e\u307b\u3093\u306e\u89e6\u308a\u306e\u90e8\u5206\u3067\u3059\u3002\u3053\u3053\u304b\u3089\u3055\u3089\u306b\u69d8\u3005\u306a\u8981\u7d20\u3092\u8ffd\u52a0\u3057\u3066\u3044\u304f\u3053\u3068\u3067\u3001\u8907\u96d1\u306a\u554f\u984c\u306b\u53d6\u308a\u7d44\u3081\u307e\u3059\u3002<\/p>\n<ul>\n<li>\n<p><b>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u5206\u5272<\/b>: \u8a13\u7df4\u30c7\u30fc\u30bf\u3001\u691c\u8a3c\u30c7\u30fc\u30bf\u3001\u30c6\u30b9\u30c8\u30c7\u30fc\u30bf\u306b\u9069\u5207\u306b\u5206\u5272\u3057\u3001\u904e\u5b66\u7fd2\uff08Overfitting\uff09\u3092\u9632\u3050\u65b9\u6cd5\u3092\u5b66\u3073\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u5206\u985e\u554f\u984c<\/b>: MNIST\u624b\u66f8\u304d\u6570\u5b57\u8a8d\u8b58\u306e\u3088\u3046\u306a\u753b\u50cf\u5206\u985e\u3084\u3001\u30b9\u30d1\u30e0\u30e1\u30fc\u30eb\u5206\u985e\u306e\u3088\u3046\u306a\u30c6\u30ad\u30b9\u30c8\u5206\u985e\u306b\u6311\u6226\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u7573\u307f\u8fbc\u307f\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af (CNN)<\/b>: \u753b\u50cf\u51e6\u7406\u306b\u7279\u5316\u3057\u305f\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u69cb\u7bc9\u3057\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30ea\u30ab\u30ec\u30f3\u30c8\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af (RNN)<\/b>: \u6642\u7cfb\u5217\u30c7\u30fc\u30bf\u3084\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306b\u5229\u7528\u3055\u308c\u308b\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u5b66\u3093\u3067\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30e2\u30c7\u30eb\u306e\u4fdd\u5b58\u3068\u30ed\u30fc\u30c9<\/b>: \u8a13\u7df4\u6e08\u307f\u306e\u30e2\u30c7\u30eb\u3092\u4fdd\u5b58\u3057\u3001\u5f8c\u3067\u518d\u5229\u7528\u3059\u308b\u65b9\u6cd5\u3092\u5b66\u3073\u307e\u3059\u3002<\/p>\n<\/li>\n<li>\n<p><b>TensorBoard<\/b>: \u30e2\u30c7\u30eb\u306e\u8a13\u7df4\u30d7\u30ed\u30bb\u30b9\u3092\u53ef\u8996\u5316\u3057\u3001\u30c7\u30d0\u30c3\u30b0\u3084\u6539\u5584\u306b\u5f79\u7acb\u3064\u30c4\u30fc\u30eb\u3092\u4f7f\u3063\u3066\u307f\u307e\u3057\u3087\u3046\u3002<\/p>\n<\/li>\n<\/ul>\n<hr \/>\n<p>\u00a0<\/p>\n<h2>\u307e\u3068\u3081<\/h2>\n<p>\u00a0<\/p>\n<p>TensorFlow\u306f\u3001Python\u3067\u6a5f\u68b0\u5b66\u7fd2\u3084\u6df1\u5c64\u5b66\u7fd2\u306e\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u3001\u8a13\u7df4\u3059\u308b\u305f\u3081\u306e\u975e\u5e38\u306b\u5f37\u529b\u3067\u67d4\u8edf\u306a\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3059\u3002Keras API\u3068\u306e\u7d71\u5408\u306b\u3088\u308a\u3001\u76f4\u611f\u7684\u304b\u3064\u7c21\u6f54\u306b\u30b3\u30fc\u30c9\u3092\u8a18\u8ff0\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002<\/p>\n<ul>\n<li>\n<p><b>\u6df1\u5c64\u5b66\u7fd2\u30e2\u30c7\u30eb<\/b>\u306e\u958b\u767a\u3068\u8a13\u7df4\u306b\u7279\u5316\u3002<\/p>\n<\/li>\n<li>\n<p><b>GPU\/TPU<\/b>\u3092\u6d3b\u7528\u3057\u3066\u9ad8\u901f\u8a08\u7b97\u3002<\/p>\n<\/li>\n<li>\n<p><b>Keras API<\/b>\u306b\u3088\u308a\u30e2\u30c7\u30eb\u69cb\u7bc9\u304c\u5bb9\u6613\u3002<\/p>\n<\/li>\n<li>\n<p><b>\u30c7\u30fc\u30bf\u6e96\u5099 \u2192 \u30e2\u30c7\u30eb\u69cb\u7bc9 \u2192 \u30b3\u30f3\u30d1\u30a4\u30eb \u2192 \u8a13\u7df4 \u2192 \u8a55\u4fa1 \u2192 \u4e88\u6e2c<\/b> \u306e\u6d41\u308c\u304c\u57fa\u672c\u3002<\/p>\n<\/li>\n<\/ul>\n<p>\u305c\u3072\u3053\u306e\u6a5f\u4f1a\u306bTensorFlow\u306e\u4e16\u754c\u306b\u98db\u3073\u8fbc\u3093\u3067\u3001\u753b\u50cf\u8a8d\u8b58\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3001\u30c7\u30fc\u30bf\u4e88\u6e2c\u306a\u3069\u3001\u6700\u5148\u7aef\u306eAI\u6280\u8853\u3092\u3042\u306a\u305f\u306e\u624b\u3067\u5b9f\u73fe\u3059\u308b\u697d\u3057\u3055\u3092\u4f53\u9a13\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\uff01<\/p>\n<hr \/>\n<p>\u00a0<\/p>\n<\/div>\n\n\n\n<p>\u25a0\u30d7\u30ed\u30f3\u30d7\u30c8\u3060\u3051\u3067\u30aa\u30ea\u30b8\u30ca\u30eb\u30a2\u30d7\u30ea\u3092\u958b\u767a\u30fb\u516c\u958b\u3057\u3066\u307f\u305f\uff01\uff01<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"MLphYKValL\"><a href=\"https:\/\/techgym.jp\/column\/ori-app\/\">\u30d7\u30ed\u30f3\u30d7\u30c8\u3060\u3051\u3067\u30aa\u30ea\u30b8\u30ca\u30eb\u30a2\u30d7\u30ea\u3092\u958b\u767a\u30fb\u516c\u958b\u3057\u3066\u307f\u305f\uff01\uff01<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;\u30d7\u30ed\u30f3\u30d7\u30c8\u3060\u3051\u3067\u30aa\u30ea\u30b8\u30ca\u30eb\u30a2\u30d7\u30ea\u3092\u958b\u767a\u30fb\u516c\u958b\u3057\u3066\u307f\u305f\uff01\uff01&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/column\/ori-app\/embed\/#?secret=jn4JroeqlZ#?secret=MLphYKValL\" data-secret=\"MLphYKValL\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>\u25a0AI\u6642\u4ee3\u306e\u7b2c\u4e00\u6b69\uff01\u300cAI\u99c6\u52d5\u958b\u767a\u30b3\u30fc\u30b9\u300d\u306f\u3058\u3081\u307e\u3057\u305f\uff01<\/p>\n\n\n\n<p>\u30c6\u30c3\u30af\u30b8\u30e0\u6771\u4eac\u672c\u6821\u3067\u5148\u884c\u958b\u59cb\u3002<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"hsX2Kp7LH4\"><a href=\"https:\/\/techgym.jp\/about\/ai-driven-development\/\">AI\u99c6\u52d5\u958b\u767a\/\u751f\u6210AI\u30a8\u30f3\u30b8\u30cb\u30a2\u30b3\u30fc\u30b9\uff08\u521d\u5fc3\u8005\u5411\u3051\uff09<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;AI\u99c6\u52d5\u958b\u767a\/\u751f\u6210AI\u30a8\u30f3\u30b8\u30cb\u30a2\u30b3\u30fc\u30b9\uff08\u521d\u5fc3\u8005\u5411\u3051\uff09&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/about\/ai-driven-development\/embed\/#?secret=OBivCRtzAR#?secret=hsX2Kp7LH4\" data-secret=\"hsX2Kp7LH4\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>\u25a0\u30c6\u30c3\u30af\u30b8\u30e0\u6771\u4eac\u672c\u6821<\/p>\n\n\n\n<p>\u300c\u6b66\u7530\u587e\u300d\u306e\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u7248\u3068\u3044\u3048\u3070\u300c\u30c6\u30c3\u30af\u30b8\u30e0\u300d\u3002<br>\u8b1b\u7fa9\u52d5\u753b\u306a\u3057\u3001\u6559\u79d1\u66f8\u306a\u3057\u3002\u300c\u9032\u6357\u7ba1\u7406\u3068\u30b3\u30fc\u30c1\u30f3\u30b0\u300d\u3067\u52b9\u7387\u5b66\u7fd2\u3002<br>\u3088\u308a\u65e9\u304f\u3001\u3088\u308a\u5b89\u304f\u3001\u3057\u304b\u3082\u5bfe\u9762\u578b\u306e\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\u3067\u3059\u3002<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"NhuTQscAqW\"><a href=\"https:\/\/techgym.jp\/tokyo\/tokyo_honko\/\">\u30c6\u30c3\u30af\u30b8\u30e0\u6771\u4eac\u672c\u6821<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;\u30c6\u30c3\u30af\u30b8\u30e0\u6771\u4eac\u672c\u6821&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/tokyo\/tokyo_honko\/embed\/#?secret=F0iXYuqFzR#?secret=NhuTQscAqW\" data-secret=\"NhuTQscAqW\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>\uff1c\u77ed\u671f\u8b1b\u7fd2\uff1e5\u65e5\u30675\u4e07\u5186\u306e\u300cPython\u30df\u30cb\u30ad\u30e3\u30f3\u30d7\u300d\u958b\u50ac\u4e2d\u3002<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"hYwpMXeZ7S\"><a href=\"https:\/\/techgym.jp\/event\/nagatacho_camp\/\">\u72ec\u5b66\u3082\u30aa\u30f3\u30e9\u30a4\u30f3\u3082\u7121\u7406\u3060\u304b\u3089\u3001\u6709\u7d66\u3068\u3063\u3066\u300cPython\u30df\u30cb\u30ad\u30e3\u30f3\u30d7\u300d\u3078\u30105\u65e5\u9593\u30675\u4e07\u5186\u3011<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;\u72ec\u5b66\u3082\u30aa\u30f3\u30e9\u30a4\u30f3\u3082\u7121\u7406\u3060\u304b\u3089\u3001\u6709\u7d66\u3068\u3063\u3066\u300cPython\u30df\u30cb\u30ad\u30e3\u30f3\u30d7\u300d\u3078\u30105\u65e5\u9593\u30675\u4e07\u5186\u3011&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/event\/nagatacho_camp\/embed\/#?secret=ZmpGmy5oug#?secret=hYwpMXeZ7S\" data-secret=\"hYwpMXeZ7S\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>\uff1c\u67081\u958b\u50ac\uff1e\u653e\u9001\u4f5c\u5bb6\u306b\u3088\u308b\u6620\u50cf\u30c7\u30a3\u30ec\u30af\u30bf\u30fc\u990a\u6210\u8b1b\u5ea7<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"k2cVHfwsQF\"><a href=\"https:\/\/techgym.jp\/event\/video_director\/\">\u73fe\u5f79\u653e\u9001\u4f5c\u5bb6\u304c\u6559\u3048\u308b\u52d5\u753b\u8b1b\u5ea7\uff01\u300e\uff24\uff2f\uff27\uff21\u300f<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;\u73fe\u5f79\u653e\u9001\u4f5c\u5bb6\u304c\u6559\u3048\u308b\u52d5\u753b\u8b1b\u5ea7\uff01\u300e\uff24\uff2f\uff27\uff21\u300f&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/event\/video_director\/embed\/#?secret=y2RkbVBZ1h#?secret=k2cVHfwsQF\" data-secret=\"k2cVHfwsQF\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>\uff1c\u30aa\u30f3\u30e9\u30a4\u30f3\u7121\u6599\uff1e\u30bc\u30ed\u304b\u3089\u59cb\u3081\u308bPython\u7206\u901f\u8b1b\u5ea7<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"7YzEhm5thA\"><a href=\"https:\/\/techgym.jp\/tokyo_python\/\">\u30bc\u30ed\u304b\u3089\u59cb\u3081\u308bPython\u7206\u901f\u8b1b\u5ea7\uff08\u7406\u7cfb\u30fb\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u521d\u5fc3\u8005\u5411\u3051\uff09<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;\u30bc\u30ed\u304b\u3089\u59cb\u3081\u308bPython\u7206\u901f\u8b1b\u5ea7\uff08\u7406\u7cfb\u30fb\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u521d\u5fc3\u8005\u5411\u3051\uff09&#8221; &#8212; \u3010\u30c6\u30c3\u30af\u30b8\u30e0\u3011\u683c\u5b89\u30fb\u5bfe\u9762\u578b\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30b9\u30af\u30fc\u30eb\" src=\"https:\/\/techgym.jp\/tokyo_python\/embed\/#?secret=MqK8wCnEEo#?secret=7YzEhm5thA\" data-secret=\"7YzEhm5thA\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>\u00a0 \u300cAI\u3092\u958b\u767a\u3057\u3066\u307f\u305f\u3044\u300d\u300c\u753b\u50cf\u8a8d\u8b58\u3084\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306b\u6311\u6226\u3057\u305f\u3044\u300d\u305d\u3046\u601d\u3063\u305f\u3068\u304d\u3001\u307e\u305a\u540d\u524d\u304c\u6319\u304c\u308b\u306e\u304c**TensorFlow\uff08\u30c6\u30f3\u30bd\u30eb\u30d5\u30ed\u30fc\uff09**\u3067\u3059\u3002Google\u304c\u958b\u767a\u3057\u305f\u3053\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e9\u30a4\u30d6\u30e9\u30ea\u306f\u3001\u6a5f\u68b0\u5b66\u7fd2\u3001\u7279 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":42501,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[5],"tags":[],"class_list":["post-43212","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-column"],"views":50,"jetpack_featured_media_url":"\/wp-content\/uploads\/2025\/07\/f3403acf5c65aedec0dba821c4c26404.png","jetpack_sharing_enabled":true,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/posts\/43212","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/comments?post=43212"}],"version-history":[{"count":0,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/posts\/43212\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/media\/42501"}],"wp:attachment":[{"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/media?parent=43212"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/categories?post=43212"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techgym.jp\/wp-json\/wp\/v2\/tags?post=43212"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}