提交 5862ec7b 编写于 作者: T Travis CI

Deploy to GitHub Pages: 65777601

上级 383b27df
......@@ -997,6 +997,7 @@ True, it will use moving mean/variance statistics
during testing. If the parameter is set to False, it
will use the mean and variance of the current batch
of test data.</li>
<li><strong>epsilon</strong> (<em>float.</em>) &#8211; The small constant added to the variance to improve numeric stability.</li>
<li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average computation.
<span class="math">\(runningMean = newMean*(1-factor) + runningMean*factor\)</span></li>
<li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li>
......
因为 它太大了无法显示 source diff 。你可以改为 查看blob
......@@ -1011,6 +1011,7 @@ True, it will use moving mean/variance statistics
during testing. If the parameter is set to False, it
will use the mean and variance of the current batch
of test data.</li>
<li><strong>epsilon</strong> (<em>float.</em>) &#8211; The small constant added to the variance to improve numeric stability.</li>
<li><strong>moving_average_fraction</strong> (<em>float.</em>) &#8211; Factor used in the moving average computation.
<span class="math">\(runningMean = newMean*(1-factor) + runningMean*factor\)</span></li>
<li><strong>mean_var_names</strong> (<em>string list</em>) &#8211; [mean name, variance name]</li>
......
此差异已折叠。
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册