{"blog_title":"AI_ML_DL\u2019s diary","height":"190","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/A/AI_ML_DL/20200520/20200520085215.png","type":"rich","author_name":"AI_ML_DL","version":"1.0","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fai-ml-dl.hatenablog.com%2Fentry%2F2020%2F05%2F20%2F085248\" title=\"Chapter 12  Custom Models and Training with TensorFlow - AI_ML_DL\u2019s diary\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_url":"https://ai-ml-dl.hatenablog.com/","title":"Chapter 12  Custom Models and Training with TensorFlow","provider_name":"Hatena Blog","description":"Chapter 12 Custom Models and Training with TensorFlow Hands-On Machine Learning with Scikit-Learn, Keras & Tensorflow 2nd Edition by A. Geron Up until now, we've used only TensorFlow's high-level API, tf.keras, but it already got us pretty far: we built various neural network architectures, includin\u2026","provider_url":"https://hatena.blog","url":"https://ai-ml-dl.hatenablog.com/entry/2020/05/20/085248","width":"100%","categories":[],"author_url":"https://blog.hatena.ne.jp/AI_ML_DL/","published":"2020-05-20 08:52:48"}