keras 预测的时候加载自定义loss

用deepctr搭建网络时，自定义focal loss，再用普通load_model会报错如下：

ValueError: Unknown loss function:binary_focal_loss_fixed

ValueError: Unknown loss function:binary_focal_loss_fixed

参考文章如下，要load_model的时候指定custom_objects

https://blog.csdn.net/liushuijingying2/article/details/87695593

代码如下：

model = load_model(save_path, custom_objects={'binary_focal_loss_fixed': binary_focal_loss})

''' focal loss '''
def binary_focal_loss(gamma=2, alpha=0.25):
    alpha = tf.constant(alpha, dtype=tf.float32)
    gamma = tf.constant(gamma, dtype=tf.float32)

    def binary_focal_loss_fixed(y_true, y_pred):
        """
        y_true shape need be (None,1)
        y_pred need be compute after sigmoid
        """
        y_true = tf.cast(y_true, tf.float32)
        alpha_t = y_true * alpha + (K.ones_like(y_true) - y_true) * (1 - alpha)

        p_t = y_true * y_pred + (K.ones_like(y_true) - y_true) * (K.ones_like(y_true) - y_pred) + K.epsilon()
        focal_loss = - alpha_t * K.pow((K.ones_like(y_true) - p_t), gamma) * K.log(p_t)
        return K.mean(focal_loss)

    return binary_focal_loss_fixed

但是又出现了：

ValueError: Unknown layer: NoMask

ValueError: Unknown layer: NoMask

报错说我们没有NoMask层，解决办法如下：

from deepctr.layers import custom_objects

custom = custom_objects
custom.update({'binary_focal_loss_fixed': binary_focal_loss})
model = load_model(save_path, custom_objects=custom)

点进custom_objects去看，这个字典里确实有NoMask