KLDivergence

Calcula la pérdida de divergencia de Kullback-Leibler entre etiquetas y predicciones.

loss = labels * log(labels / predictions)

Uso independiente:

    Operand<TFloat32> labels =
        tf.constant(new float[][] { {0.f, 1.f}, {0.f, 0.f} });
    Operand<TFloat32> predictions =
        tf.constant(new float[][] { {0.6f, 0.4f}, {0.4f, 0.6f} });
    KLDivergence kld = new KLDivergence(tf);
    Operand<TFloat32> result = kld.call(labels, predictions);
    // produces 0.458
 

Llamar con peso de muestra:

    Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.8f, 0.2f});
    Operand<TFloat32> result = kld.call(labels, predictions, sampleWeight);
    // produces 0.366f
 

Usando el tipo de reducción SUM :

    KLDivergence kld = new KLDivergence(tf, Reduction.SUM);
    Operand<TFloat32> result = kld.call(labels, predictions);
    // produces 0.916f
 

Usando NONE tipo de reducción:

    KLDivergence kld = new KLDivergence(tf, Reduction.NONE);
    Operand<TFloat32> result = kld.call(labels, predictions);
    // produces [0.916f, -3.08e-06f]