[mlpack-git] [mlpack] Enhance class SoftmaxRegression (#456)

Ryan Curtin notifications at github.com
Mon Sep 28 09:44:50 EDT 2015


> +   * @param fitIntercept add intercept term or not.
> +   */
> +  SoftmaxRegression(const size_t inputSize,
> +                    const size_t numClasses,
> +                    const bool fitIntercept = false);
> +
> +  /**
> +   * Construct the SoftmaxRegression class with the provided data and labels.
> +   * This will train the model.
> +   *
> +   * @param fileName name of the files saving the model contents
> +   * @param name name of the structure to be save
> +   * @exception If the file cannot be load, the exception will thrown
> +   */
> +  SoftmaxRegression(const std::string &fileName,
> +                    const std::string& name);

I think we should avoid this constructor, because no other mlpack methods provide a constructor of this sort.  If we implemented this method here, then we'd have to implement it anywhere (for consistency).  I'd prefer that users use `data::Load()` instead (maybe we can revisit this later, but for now I don't have time to create that constructor for every mlpack method before the next release).

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/456/files#r40552799
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150928/f873bd21/attachment.html>


More information about the mlpack-git mailing list