<p>In <a href="https://github.com/mlpack/mlpack/pull/696#discussion_r67071582">src/mlpack/methods/edge_boxes/feature_extraction_impl.hpp</a>:</p>
<pre style='color:#555'>> +{
> +
> +}
> +
> +template<typename MatType, typename CubeType>
> +MatType StructuredForests<MatType, CubeType>::
> +LoadData(MatType const &images, MatType const &boundaries,\
> + MatType const &segmentations)
> +{
> + const size_t num_images = this->options["num_images"];
> + const size_t row_size = this->options["row_size"];
> + const size_t col_size = this->options["col_size"];
> + MatType input_data(num_images * row_size * 5, col_size);
> + // we store the input data as follows:
> + // images (3), boundaries (1), segmentations (1).
> + size_t loop_iter = num_images * 5;
</pre>
<p>Why can't we just the images, boundaries and segmentations parameter, I'm not sure I get the reason to use a big matrix instead.</p>
<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">—<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/696/files/b38b688edfc4c2ee8bf461240f8384a70575d3a4#r67071582">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe/AJ4bFJyPvG-I7K5P9fX2WisIoa6b476Wks5qLy6xgaJpZM4I1lnr">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFI8EAP6TsNJJYAAxHBAnLT3KTF4Hks5qLy6xgaJpZM4I1lnr.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/696/files/b38b688edfc4c2ee8bf461240f8384a70575d3a4#r67071582"></link>
<meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>