MeanSquaredError

ラベルと予測の間の誤差の二乗平均を計算します。

loss = loss = square(labels - predictions)

スタンドアロン使用:

    Operand<TFloat32> labels =
        tf.constant(new float[][] { {0.f, 1.f}, {0.f, 0.f} });
    Operand<TFloat32> predictions =
        tf.constant(new float[][] { {1.f, 1.f}, {1.f, 0.f} });
    MeanSquaredError mse = new MeanSquaredError(tf);
    Operand<TFloat32> result = mse.call(labels, predictions);
    // produces 0.5f
 

サンプルの重みを指定して呼び出します:

    Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.7f, 0.3f});
    Operand<TFloat32> result = mse.call(labels, predictions, sampleWeight);
    // produces 0.25f
 

SUMリダクションタイプの使用:

    MeanSquaredError mse = new MeanSquaredError(tf, Reduction.SUM);
    Operand<TFloat32> result = mse.call(labels, predictions);
    // produces 1.0f
 

NONE削減タイプを使用する:

    MeanSquaredError mse = new MeanSquaredError(tf, Reduction.NONE);
    Operand<TFloat32> result = mse.call(labels, predictions);
    // produces [0.5f, 0.5f]