public static KerasSymbol Logcosh(KerasSymbol y_true, KerasSymbol y_pred)
{
var x = y_pred - y_true;
var _logcosh = x + K.Softplus(-2 * x) - (float)Math.Log(2);
return(K.Mean(_logcosh, axis: -1));
}
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 static KerasSymbol MeanSquaredError(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.Square(y_pred - y_true), axis: -1));
}
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 Hinge(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.Maximum(1 - y_true * y_pred, 0), 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));
}
public static KerasSymbol MeanAbsoluteError(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.Abs(y_pred - y_true), axis: -1));
}
public static KerasSymbol BinaryAccuracy(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.Equal(y_true, K.Round(y_pred)), axis: -1));
}
public static KerasSymbol SparseTopKCategoricalAccuracy(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.InTopK(y_pred, K.Cast(K.Flatten(y_true), "int32"), 5), axis: -1));
}
public static KerasSymbol TopKCategoricalAccuracy(KerasSymbol y_true, KerasSymbol y_pred)
{
return(K.Mean(K.InTopK(y_pred, K.Argmax(y_true, axis: -1), 5), axis: -1));
}