<blockquote>
<p>Does my idea make sense here, or maybe am I misunderstanding something?</p>
</blockquote>

<p>I am not sure about this one, reshape the maximal inputs into a square block looks like a default way to visualize the features learned by autoencoder, don't know the other settings(block width * block height) meaningful or not. </p>

<p>However, if you prefer to make the class more general, I will make the constructor provide a constructor with blockWidth and blockHeight with default value equal to 0, explain the purpose of them by the comments.</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br>Reply to this email directly or <a href="https://github.com/mlpack/mlpack/pull/465#issuecomment-159499081">view it on GitHub</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFCJOqg40Lzn5PUpN_F00HrLoVtL0ks5pJUS_gaJpZM4GWT_f.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
  <link itemprop="url" href="https://github.com/mlpack/mlpack/pull/465#issuecomment-159499081"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>