Closed rizar closed 9 years ago
I think we should leave both of them. If anyone tries to train some of our models on non-text datasets, either linear or sigmoid output will be most widely used.
Let me try to convince you:
MSELayer
and CrossEntropyLayer
. If people start using these current layers, the cost of fixing this design flow will increase.Go ahead with removing those. Just make sure to leave their names in commit comments so that we can search for them later, if we need it.
This issue is a part of my initiative to leave only useful/used code in this main fork of Grounhog.
The following classes from groundhog.layers.cost_layers:
are not used in any groundhog-based project I know. May I just delete them?