{"version":"1.0","author_url":"https://blog.hatena.ne.jp/aipacommander/","blog_title":"IT\u306e\u968a\u9577\u306e\u30d6\u30ed\u30b0","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Faipacommander.com%2Fentry%2F2019%2F05%2F14%2F000250\" title=\"Tensorflow2\u7cfb\u3067\u6307\u5b9a\u3057\u305f\u30ec\u30a4\u30e4\u30fc\u304b\u3089\u52fe\u914d\u3092\u53d6\u5f97\u3057\u305f\u3044\u5834\u5408 - IT\u306e\u968a\u9577\u306e\u30d6\u30ed\u30b0\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","image_url":null,"description":"\u30cf\u30de\u3063\u305f import tensorflow as tf # fine tuning\u3057\u305f\u3044\u306e\u3067vgg16\u306e\u30e2\u30c7\u30eb\u3092\u30ed\u30fc\u30c9 vgg16 = tf.keras.applications.VGG16(include_top=False, input_shape=(100, 100, 3)) for l in vgg16.layers: l.trainable = False x = tf.keras.layers.Flatten()(vgg16.output) x = tf.keras.layers.Dense(512, activation='relu')(x) output = tf.keras\u2026","published":"2019-05-14 00:02:50","provider_url":"https://hatena.blog","categories":["Python","Tensorflow"],"type":"rich","author_name":"aipacommander","width":"100%","title":"Tensorflow2\u7cfb\u3067\u6307\u5b9a\u3057\u305f\u30ec\u30a4\u30e4\u30fc\u304b\u3089\u52fe\u914d\u3092\u53d6\u5f97\u3057\u305f\u3044\u5834\u5408","provider_name":"Hatena Blog","blog_url":"https://aipacommander.com/","height":"190","url":"https://aipacommander.com/entry/2019/05/14/000250"}