Python 在tensorflow 2中，以50%的真正速率计算分布的Jensen-Shannon散度的自定义度量

我不熟悉TensorFlow，也不熟悉一般的编码。我试图使用一个自定义指标：输入变量之一的概率分布的Jensen-Shannon散度，真实正率（回忆）为50%。我正在努力使它工作。我还使用了一个自定义的loss函数，我设法使它工作（但为了简单起见，我在下面的代码中保留了一个标准loss）

在运行上述行时，我遇到以下错误：

ValueError: in user code:

    <ipython-input-79-2185a89bc166>:39 jsd  *
        js = (tf.keras.losses.KLDivergence(prob_a,m) + tf.keras.losses.KLDivergence(prob_b,m))/2
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1091 __init__  **
        kl_divergence, name=name, reduction=reduction)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:235 __init__
        super(LossFunctionWrapper, self).__init__(reduction=reduction, name=name)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:99 __init__
        losses_utils.ReductionV2.validate(reduction)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/losses/loss_reduction.py:68 validate
        raise ValueError('Invalid Reduction Key %s.' % key)

    ValueError: Invalid Reduction Key Tensor("metrics_2/jsd/truediv:0", shape=(50,), dtype=float64).

ValueError:在用户代码中：
：39 jsd*
js=（tf.keras.loss.kldisference（prob_a，m）+tf.keras.loss.kldisference（prob_b，m））/2
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/loss.py:1091**
kl_分歧，名称=名称，缩减=缩减）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/loss.py:235__init__
super（LossFunctionWrapper，self）。\uuuuu init\uuuuu（reduce=reduce，name=name）
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/loss.py:99\u init__
损失_utils.ReductionV2.validate（减少）
/usr/local/lib/python3.6/dist包/tensorflow/python/ops/loss/loss_reduction.py:68
raise VALUERROR（'无效的缩减键%s.%Key）
ValueError:还原键张量无效（“metrics_2/jsd/truediv:0”，shape=（50，），dtype=float64）。

tf.compat.v1.disable_eager_execution()

initializer = keras.initializers.Orthogonal()
l2_layer1 = 0.0
l2_layer2 = 0.0
l2_layer3 = 0.0
l2_layer4 = 0.0


def neural_network():
        # create model
        i = Input(shape=(n_cols,))
       

        x1 = Dense(32, activation='relu',kernel_regularizer=l2(l2_layer1),kernel_initializer=initializer)(i)
       

        x2 = Dense(32, activation='relu',kernel_regularizer=l2(l2_layer2),kernel_initializer=initializer)(x1)
      

        x3 = Dense(32, activation='relu',kernel_regularizer=l2(l2_layer3),kernel_initializer=initializer)(x2)      

        x4 = Dense(32, activation='relu',kernel_regularizer=l2(l2_layer3),kernel_initializer=initializer)(x3)
      

        o = Dense(2, activation='softmax',kernel_regularizer=l2(l2_layer4),kernel_initializer=initializer)(x4)

        model = Model(i,o)

        opt = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999)
        model.compile(loss=custom_loss(i,10), optimizer=opt,metrics=['accuracy',custom_metric(i)])
        return model

model = neural_network()
history = History()
# fit the model
#history = model.fit(trainX, trainY, epochs=5, verbose=1,batch_size=2048,shuffle = True)
history = model.fit(trainX, trainY, validation_data=(valX, valY), epochs=50, verbose=0 ,batch_size=2048,shuffle = True)

ValueError: in user code:

    <ipython-input-79-2185a89bc166>:39 jsd  *
        js = (tf.keras.losses.KLDivergence(prob_a,m) + tf.keras.losses.KLDivergence(prob_b,m))/2
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1091 __init__  **
        kl_divergence, name=name, reduction=reduction)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:235 __init__
        super(LossFunctionWrapper, self).__init__(reduction=reduction, name=name)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:99 __init__
        losses_utils.ReductionV2.validate(reduction)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/losses/loss_reduction.py:68 validate
        raise ValueError('Invalid Reduction Key %s.' % key)

    ValueError: Invalid Reduction Key Tensor("metrics_2/jsd/truediv:0", shape=(50,), dtype=float64).