modern-fortran / neural-fortran

A parallel framework for deep learning
MIT License
395 stars 82 forks source link

Example program that shows how to access internal layer parameters #140

Closed milancurcic closed 1 year ago

milancurcic commented 1 year ago

@Spnetic-5 this PR introduces an example program that shows how to access internal layer parameters (weights and biases). The same approach can be used to access gradients as well, stored as dw for weights and db for biases.

Spnetic-5 commented 1 year ago

Thank you @milancurcic for this code, I'll try this in my implementation and will get back to you.