[mlpack-git] [mlpack] [Proposal]Develop a scalable Finetune class to fine tune the paramters of deep network (#458)

stereomatchingkiss notifications at github.com
Tue Oct 6 13:50:18 EDT 2015


The test of softmax_regression do work after the alternation, but the test case "SoftmaxRegressionFunctionGradient" must add two more lines(at line 131 and 132)

    // Get gradients for the current parameters.
    arma::mat gradient1, gradient2;
    //add these two function calls to evaluate the objective value first, else the probabilites matrix
    //would not build
    srf1.Evaluate(parameters);
    srf2.Evaluate(parameters);



---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/458#issuecomment-145944450
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151006/d14f87e7/attachment.html>


More information about the mlpack-git mailing list