1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

How to Train CNN for Regression Task

Discussion in 'Education' started by Qianlong Lan, Oct 8, 2018.

  1. Qianlong Lan

    Qianlong Lan Guest

    As I want to use the discriminative and generative CNN for Regression in https://github.com/ajbrock/Generative-and-Discriminative-Voxel-Modeling. Where I change the loss function to regression_loss= (abs(y_hat-y).sum(axis=1)).mean()+lasagne.objectives.squared_error(lasagne.nonlinearities.linear(y_hat), y).mean(). But it was still not working. Does anyone have done something like using CNN as feature extractor and finally used for regression task?

    Login To add answer/comment
     

Share This Page