[mlpack-git] [mlpack] Mean shift clustering (#388)

[Shangtong Zhang]

> +  }
> +  
> +  // Make sure we have an output file if we're not doing the work in-place.
> +  if (!CLI::HasParam("in_place") && !CLI::HasParam("output_file") &&
> +      !CLI::HasParam("centroid_file")) {
> +    Log::Warn << "--output_file, --in_place, and --centroid_file are not set; "
> +    << "no results will be saved." << std::endl;
> +  }
> +  
> +  arma::mat dataset;
> +  data::Load(inputFile, dataset, true); // Fatal upon failure.
> +  arma::mat centroids;
> +  arma::Col<size_t> assignments;
> +  
> +  kernel::GaussianKernel kernel;
> +  kernel.Bandwidth(bandwidth);

Because the bandwidth is a param of Gaussian kernel, not the param of MeanShift class. In the executable program, I don't provide param to choose kernel, the executable can only use Gaussian kernel, and there is a param to set the bandwidth of Gaussian kernel in the executable. But advanced user can use their own kernel by using class MeanShift.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/388/files#r23590369
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150126/1f4c1605/attachment.html>