rweed

Is there anyway to save a regression model once you fit it (like you can with keras etc). If not this should be added

Can you make fpm ignore a USE statement inside a preprocessor #ifdef #endif block

7

### Description I'm trying to compile a code where I have the following logic ```fortran #ifdef USE_MPI USE MPI #else #ifdef USE_MPIF90_STUBS USE mpif90_stubs #endif #endif ``` fpm build gives...

Here are five things I would like to see added to neural-fortran 1. [ ] Batch normalization layers 2. [ ] Dropout layers (although for what I'm working on now...