constraints

Weight constraints

Description

Functions that impose constraints on weight values.

Usage

 
constraint_maxnorm(max_value = 2, axis = 0) 
 
constraint_nonneg() 
 
constraint_unitnorm(axis = 0) 
 
constraint_minmaxnorm(min_value = 0, max_value = 1, rate = 1, axis = 0)

Arguments

Arguments	Description
max_value	The maximum norm for the incoming weights.
axis	The axis along which to calculate weight norms. For instance, in a dense layer the weight matrix has shape `input_dim, output_dim`, set `axis` to `0` to constrain each weight vector of length `input_dim,`. In a convolution 2D layer with `dim_ordering="tf"`, the weight tensor has shape `rows, cols, input_depth, output_depth`, set `axis` to `c(0, 1, 2)` to constrain the weights of each filter tensor of size `rows, cols, input_depth`.
min_value	The minimum norm for the incoming weights.
rate	The rate for enforcing the constraint: weights will be rescaled to yield (1 - rate) * norm + rate * norm.clip(low, high). Effectively, this means that rate=1.0 stands for strict enforcement of the constraint, while rate<1.0 means that weights will be rescaled at each step to slowly move towards a value inside the desired interval.

Details

constraint_maxnorm() constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value.
constraint_nonneg() constraints the weights to be non-negative
constraint_unitnorm() constrains the weights incident to each hidden unit to have unit norm.
constraint_minmaxnorm() constrains the weights incident to each hidden unit to have the norm between a lower bound and an upper bound.

Section

Custom constraints

You can implement your own constraint functions in R. A custom constraint is an R function that takes weights (w) as input and returns modified weights. Note that keras backend() tensor functions (e.g. k_greater_equal()) should be used in the implementation of custom constraints. For example: ```

nonneg_constraint <- function(w) {

w * k_cast(k_greater_equal(w, 0), k_floatx())

}

layer_dense(units = 32, input_shape = c(784),

        kernel_constraint = nonneg_constraint)

``Note that models which use custom constraints cannot be serialized usingsave_model_hdf5(). Rather, the weights of the model should be saved and restored usingsave_model_weights_hdf5()`.