SquaredHinge

Menghitung kerugian engsel kuadrat antara label dan prediksi.

loss = square(maximum(1 - labels * predictions, 0))

nilai labels diharapkan -1 atau 1. Jika label biner (0 atau 1) diberikan, label tersebut akan dikonversi ke -1 atau 1.

Penggunaan mandiri:

    Operand<TFloat32> labels =
        tf.constant(new float[][] { {0., 1.}, {0., 0.} });
    Operand<TFloat32> predictions =
        tf.constant(new float[][] { {0.6f, 0.4f}, {0.4f, 0.6f} });
    SquaredHinge squaredHinge = new SquaredHinge(tf);
    Operand<TFloat32> result = squaredHinge.call(labels, predictions);
    // produces 1.86f
 

Memanggil dengan berat sampel:

    Operand<TFloat32> sampleWeight = tf.constant(new float[] {1.f, 0.f});
    Operand<TFloat32> result = squaredHinge.call(labels, predictions,
                                                  sampleWeight);
    // produces 0.73f
 

Menggunakan tipe pengurangan SUM :

    SquaredHinge squaredHinge = new SquaredHinge(tf, Reduction.SUM);
    Operand<TFloat32> result = squaredHinge.call(labels, predictions);
    // produces 3.72f
 

Menggunakan tipe reduksi NONE :

    SquaredHinge squaredHinge = new SquaredHinge(tf, Reduction.NONE);
    Operand<TFloat32> result = squaredHinge.call(labels, predictions);
    // produces [1.46f, 2.26f]