<p>In <a href="https://github.com/mlpack/mlpack/pull/703#discussion_r74704389">src/mlpack/methods/edge_boxes/feature_extraction_impl.hpp</a>:</p>
<pre style='color:#555'>&gt; +    size_t y = loc(i, 1);
&gt; +
&gt; +    /*(x,y) in channels, is ((x+p), (y+p)) in incCh*/
&gt; +    CubeType patch = incCh.tube((x + p) - p, (y + p) - p,
&gt; +                          (x + p) + p - 1, (y + p) + p - 1);
&gt; +    // since each patch has 13 channel we have to increase the index by 13    
&gt; +    features.slices(channel, channel + 12) = patch;
&gt; +    channel += 13;
&gt; +  }
&gt; +}
&gt; +
&gt; +template&lt;typename MatType, typename CubeType&gt;
&gt; +void StructuredForests&lt;MatType, CubeType&gt;::
&gt; +Rearrange(const CubeType&amp; channels, CubeType&amp; ch)
&gt; +{
&gt; +  //we do (16,16,13*1000) to 256, 1000, 13, in vectorized code.
</pre>
<p>Can you explain why we use 256, I think we could also use a value &gt; 256.</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/703/files/72eb1ef22c7db1ea33af3de1cd043cdb277ec562#r74704389">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe-auth/AJ4bFKY2oxG0W1gpG0NGZ586vtefdGewks5qfz0mgaJpZM4I5X__">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFIYO1x8vNFsjDPzeLc8EtrcJdQn9ks5qfz0mgaJpZM4I5X__.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/703/files/72eb1ef22c7db1ea33af3de1cd043cdb277ec562#r74704389"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>

<script type="application/json" data-scope="inboxmarkup">{"api_version":"1.0","publisher":{"api_key":"05dde50f1d1a384dd78767c55493e4bb","name":"GitHub"},"entity":{"external_key":"github/mlpack/mlpack","title":"mlpack/mlpack","subtitle":"GitHub repository","main_image_url":"https://cloud.githubusercontent.com/assets/143418/17495839/a5054eac-5d88-11e6-95fc-7290892c7bb5.png","avatar_image_url":"https://cloud.githubusercontent.com/assets/143418/15842166/7c72db34-2c0b-11e6-9aed-b52498112777.png","action":{"name":"Open in GitHub","url":"https://github.com/mlpack/mlpack"}},"updates":{"snippets":[{"icon":"PERSON","message":"@zoq in #703: Can you explain why we use 256, I think we could also use a value \u003e 256."}],"action":{"name":"View Pull Request","url":"https://github.com/mlpack/mlpack/pull/703/files/72eb1ef22c7db1ea33af3de1cd043cdb277ec562#r74704389"}}}</script>