<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<oembed>
  <author_name>KZKY</author_name>
  <author_url>https://blog.hatena.ne.jp/KZKY/</author_url>
  <blog_title>KZKY memo</blog_title>
  <blog_url>https://kzky.hatenablog.com/</blog_url>
  <categories>
    <anon>python</anon>
    <anon>tensorflow</anon>
    <anon>deeplearning</anon>
  </categories>
  <description>この記事を書いている時点では，0.6.0が最新なので，それを参考にまとめている． Variables: Creation, Initializing, Saving, and Restoring Variableはin-memory buffferだからtrainingが終わっったら，永続化させてevalutionとかしたい． The tf.Variable class The tf.train.Saver class の説明 Creation # Create two variables. weights = tf.Variable(tf.random_normal([784, 200], …</description>
  <height>190</height>
  <html>&lt;iframe src=&quot;https://hatenablog-parts.com/embed?url=https%3A%2F%2Fkzky.hatenablog.com%2Fentry%2F2015%2F12%2F24%2FTensor_Flow%253A_How_To&quot; title=&quot;Tensor Flow: How To - KZKY memo&quot; class=&quot;embed-card embed-blogcard&quot; scrolling=&quot;no&quot; frameborder=&quot;0&quot; style=&quot;display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;&quot;&gt;&lt;/iframe&gt;</html>
  <image_url></image_url>
  <provider_name>Hatena Blog</provider_name>
  <provider_url>https://hatena.blog</provider_url>
  <published>2015-12-24 18:48:39</published>
  <title>Tensor Flow: How To</title>
  <type>rich</type>
  <url>https://kzky.hatenablog.com/entry/2015/12/24/Tensor_Flow%3A_How_To</url>
  <version>1.0</version>
  <width>100%</width>
</oembed>
