A parallel framework for deep learning
network % evaluate
by @jvdp1 in https://github.com/modern-fortran/neural-fortran/pull/182
pack
replaced by pointers in get_params
and get_gradients
by @jvdp1 in https://github.com/modern-fortran/neural-fortran/pull/183
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.16.1...v0.17.0
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.16.0...v0.16.1
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.15.1...v0.16.0
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.15.0...v0.15.1
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.14.0...v0.15.0
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.13.0...v0.14.0
conv2d_layer
by @milancurcic in https://github.com/modern-fortran/neural-fortran/pull/141
flatten
, conv2d
, and maxpool2d
layers in backward pass by @milancurcic in https://github.com/modern-fortran/neural-fortran/pull/142
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.12.0...v0.13.0
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.11.0...v0.12.0
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.10.0...v0.11.0
This release introduces get_num_params
, get_params
, and set_params
methods to network
and layer
derived types, and allow you to more easily get and set network hyperparameters from custom Fortran code or other libraries. See the example to learn how it works.
Thanks to Christopher Zapart @jvo203 for this feature contribution.
Full Changelog: https://github.com/modern-fortran/neural-fortran/compare/v0.9.0...v0.10.0