Huber

Menghitung kerugian Huber antara label dan prediksi.

Untuk setiap nilai x dalam error = labels - predictions :

     loss = 0.5 * x^2                  if |x| <= d
     loss = 0.5 * d^2 + d * (|x| - d)  if |x| > d
 

dimana d adalah delta.

Penggunaan mandiri:

    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} });
    Huber huberLoss = new Huber(tf);
    Operand<TFloat32> result = huberLoss.call(labels, predictions);
    // produces 0.155
 

Memanggil dengan berat sampel:

    Operand<TFloat32> sampleWeight = tf.constant(new float[] {1.f, 0.f});
    Operand<TFloat32> result = huberLoss.call(labels, predictions, sampleWeight);
    // produces 0.09f
 

Menggunakan tipe pengurangan SUM :

    Huber huberLoss = new Huber(tf, Reduction.SUM);
    Operand<TFloat32> result = huberLoss.call(labels, predictions);
    // produces 0.32f
 

Menggunakan tipe reduksi NONE :

    Huber huberLoss = new Huber(tf, Reduction.NONE);
    Operand<TFloat32> result = huberLoss.call(labels, predictions);
    // produces [0.18f, 0.13f]