Base R6 class for Keras constraints
Base R6 class for Keras constraints
An R6Class generator object
You can implement a custom constraint either by creating an
R function that accepts a weights (w) parameter, or by creating
an R6 class that derives from KerasConstraint and implements a
call method.
call(w)Constrain the specified weights.
Models which use custom constraints cannot be serialized using
save_model_hdf5(). Rather, the weights of the model should be saved
and restored using save_model_weights_hdf5().
## Not run:
CustomNonNegConstraint <- R6::R6Class(
"CustomNonNegConstraint",
inherit = KerasConstraint,
public = list(
call = function(x) {
w * k_cast(k_greater_equal(w, 0), k_floatx())
}
)
)
layer_dense(units = 32, input_shape = c(784),
kernel_constraint = CustomNonNegConstraint$new())
## End(Not run)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.