0

I see very large file sizes when I try to save my trained NN model using neuralnet in R. I know one (main) reason for that is that the model contains extra information that I may not need in order to reuse the model, like, the results (net$net.result), and some other elements that are saved with the network.

Anyway I can remove them from the model before saving?

Vahid Zadeh
  • 564
  • 4
  • 25
  • I did a bit of research and found a blog post on glm method. http://www.win-vector.com/blog/2014/05/trimming-the-fat-from-glm-models-in-r/ I'll dig more and share my answer for neuralnet later on. – Vahid Zadeh Aug 03 '17 at 15:21
  • Also another one about object class lm: https://stackoverflow.com/questions/21896265/how-to-minimize-size-of-object-of-class-lm-without-compromising-it-being-passe – Vahid Zadeh Aug 03 '17 at 15:23

0 Answers0