tensorflow keras 存儲模型錯誤 使用自定義層 報錯 TypeError: ('Not JSON Serializable:', ) 等

錯誤原因

原因在於使用了自定義的層
例如：定義損失函數 Loss（因爲這個函數不好，就不多做說明了，只是做個例子來說明）

def contrastive_loss_layer(top_different, deep_different, y_true):
         margin = 1000
         top_distance=tf.norm((top_different),ord=2)
         deep_distance=tf.norm((deep_different),ord=2)
         mul_distance=K.log(top_distance*deep_distance)
         loss=(1-y_true)*mul_distance+y_true*tf.square(tf.maximum(margin-mul_distance,0))
         loss=tf.reduce_mean(loss)
         return loss
model.add_loss(layers.Lambda(lambda x:self.contrastive_loss_layer(*x), name='loss')([left_inputs-right_inputs,left_output-right_output,label_inputs]))                                                                        

替換成層類就不會報錯了

class ContrastiveLoss(layers.Layer):
    def __init__(self, **kwargs):
        super(ContrastiveLoss, self).__init__(**kwargs)

    def call(self, inputs, **kwargs):
        """
        # inputs：Input tensor, or list/tuple of input tensors.
        如上，父類KL.Layer的call方法明確要求inputs爲一個tensor，或者包含多個tensor的列表/元組
        所以這裏不能直接接受多個入參，需要把多個入參封裝成列表/元組的形式然後在函數中自行解包，否則會報錯。
        """
        # 解包入參
        
        top_different,deep_different,y_true=inputs
        margin = 100
        top_distance = tf.norm((top_different), ord=2)
        deep_distance = tf.norm((deep_different), ord=2)
        mul_distance = K.log(top_distance * deep_distance)
        loss = (1 - y_true) * mul_distance + y_true * tf.square(tf.maximum(margin - mul_distance, 0))
        loss = tf.reduce_mean(loss)
        # 重點：把自定義的loss添加進層使其生效，同時加入metric方便在KERAS的進度條上實時追蹤
        
        self.add_loss(loss, inputs=True)
        self.add_metric(loss, aggregation="mean", name="C_loss")
        return loss