BinaryCrossentropy

Computes the cross-entropy loss between true labels and predicted labels.

Use this cross-entropy loss when there are only two label classes (assumed to be 0 and 1). For each example, there should be a single floating-point value per prediction.

Standalone usage:

    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} });
    BinaryCrossentropy bce = new BinaryCrossentropy(tf);
    Operand<TFloat32> result = bce.call(labels, predictions);
    // produces 0.815
 

Calling with sample weight:

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

Using SUM reduction type:

    BinaryCrossentropy bce = new BinaryCrossentropy(tf, Reduction.SUM);
    Operand<TFloat32> result = bce.call(labels, predictions);
    // produces 1.630f
 

Using NONE reduction type:

    BinaryCrossentropy bce = new BinaryCrossentropy(tf, Reduction.NONE);
    Operand<TFloat32> result = bce.call(labels, predictions);
    // produces [0.916f, 0.714f]