public static KerasSymbol MeanSquaredLogrithmicError(KerasSymbol y_true, KerasSymbol y_pred)
{
var first_log = K.Log(K.Clip(y_pred, K.Epsilon(), null) + 1);
var second_log = K.Log(K.Clip(y_true, K.Epsilon(), null) + 1);
return(K.Mean(K.Square(first_log - second_log), axis: -1));
}
public override KerasSymbol Call(KerasSymbol w)
{
var norms = K.Sqrt(K.Sum(K.Square(w), axis: this.axis, keepdims: true));
var desired = K.Clip(norms, 0, this.max_value);
w *= desired / (K.Epsilon() + norms);
return(w);
}
public override KerasSymbol Call(KerasSymbol w)
{
return(w / (K.Epsilon() + K.Sqrt(K.Sum(K.Square(w), axis: this.axis, keepdims: true))));
}
public static KerasSymbol Poisson(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(y_pred - y_true * K.Log(y_pred + K.Epsilon()), axis: -1));
}
public static KerasSymbol KullbackLeiblerDivergence(KerasSymbol y_true, KerasSymbol y_pred)
{
y_true = K.Clip(y_true, K.Epsilon(), 1);
y_pred = K.Clip(y_pred, K.Epsilon(), 1);
return(K.Sum(y_true * K.Log(y_true / y_pred), axis: -1));
}
public static KerasSymbol MeanAbsolutePercentageError(KerasSymbol y_true, KerasSymbol y_pred)
{
var diff = K.Abs((y_true - y_pred) / K.Clip(K.Abs(y_true), K.Epsilon(), null));
return(100 * K.Mean(diff, axis: -1));
}