[mlpack-git] [mlpack/mlpack] Inception layer (#757)

[Nilay Jain]

> +
> +The output array has the same spatial size as the input. In order to
> +satisfy this, Inception module uses appropriate padding for each
> +convolution and pooling.
> +
> +See: `Going Deeper with Convolutions <http://arxiv.org/abs/1409.4842>`_.
> +
> +*/
> +
> +template<typename InputDataType = arma::cube,
> +         typename OutputDataType = arma::cube>
> +class InceptionLayer
> +{
> + public:
> +  //! Locally-stored number of input maps.
> +  size_t inMaps;

When writing tests I access the layers from the InceptionLayer object. I will put the variables as private and let layers remain as public.

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/757/files/06d923321f246f2c6ead9ad56e99309fe24a6f5c#r74701477
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160814/d5914128/attachment.html>