[mlpack-git] [mlpack/mlpack] Neural evolution algorithms implementation (CNE, NEAT, HyperNEAT) (#686)

[Excalibur]

Yeah, this function is good for print informations of a neural network.

Actually, I am thinking about using Boost library to generate Graphviz file
for visualizing network. Do you think it is good?

2016-07-16 12:48 GMT-06:00 Marcus Edel <notifications at github.com>:

> Maybe useful, I use the following function in the Genome class to print
> the lastBestGenome in the neat Reproduce function:
>
> void Print()
>  {
>     std::cout << "--------------------------------------------------------------------------\n";
>     const char* enumNeuronTypetring[] = { "NONE", "INPUT", "BIAS", "HIDDEN", "OUTPUT" };
>     const char* enumActivationFuncTypeString[] = { "SIGMOID", "TANH", "LINEAR", "RELU" };
>     const char* boolEnabledString[] = { "False", "True" };
>
>     std::cout << "Genes: " << aNeuronGenes.size() << std::endl;
>
>     for(size_t i = 0; i < aNeuronGenes.size(); ++i)
>     {
>       printf("  Gene:(id=%i, type=%s, activation=%s, response=%f, depth=%.3f)\n",
>           aNeuronGenes[i].Id(),
>           enumNeuronTypetring[aNeuronGenes[i].Type()],
>           enumActivationFuncTypeString[aNeuronGenes[i].ActFuncType()],
>           aNeuronGenes[i].Activation(),
>           aNeuronGenes[i].Depth());
>     }
>
>     std::cout << "Links: " << aLinkGenes.size() << std::endl;
>
>     for(size_t i = 0; i < aLinkGenes.size(); ++i)
>     {
>       printf("  Link:(in=%i, out=%i, weight=%f, enabled=%s innovation=%i)\n",
>           aLinkGenes[i].FromNeuronId(),
>           aLinkGenes[i].ToNeuronId(),
>           aLinkGenes[i].Weight(),
>           boolEnabledString[aLinkGenes[i].Enabled()],
>           aLinkGenes[i].InnovationId());
>     }
>
>     std::cout << "--------------------------------------------------------------------------\n";
>  }
>
> —
> You are receiving this because you commented.
> Reply to this email directly, view it on GitHub
> <https://github.com/mlpack/mlpack/pull/686#issuecomment-233145071>, or mute
> the thread
> <https://github.com/notifications/unsubscribe-auth/AD9tIV5NoKwinWJ6XW2ej4g7giK6gPlsks5qWSeRgaJpZM4IwJa6>
> .
>


---
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/686#issuecomment-233158805
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160716/b62e6648/attachment.html>