Keras 中损失函数的导数

Question

我想在keras中制作以下损失函数：

Loss = mse + double_derivative(y_pred,x_train)

我无法合并导数项。我试过 K.gradients(K.gradients(y_pred,x_train),x_train) 但没有用。

我收到错误消息：

AttributeError: 'NoneType' object has no attribute 'op'

def _loss_tensor(y_true, y_pred,x_train):
    l1 = K.mean(K.square(y_true - y_pred), axis=-1)
    sigma = 0.01
    lamda = 3
    term = K.square(sigma)*K.gradients(K.gradients(y_pred,x_train),x_train)
    l2 = K.mean(lamda*K.square(term),axis=-1)
    return l1+l2

def loss_func(x_train):
        def loss(y_true,y_pred):
            return _loss_tensor(y_true,y_pred,x_train)
        return loss

def create_model_neural(learning_rate, num_layers,
                 num_nodes, activation):

    model_neural = Sequential()

    x_train = model_neural.add(Dense(num_nod, input_dim=num_input, activation=activation))

    for i in range(num_layers-1):
        model_neural.add(Dense(num_nodes,activation=activation,name=name))

    model_neural.add(Dense(1, activation=activation))

    optimizer = SGD(lr=learning_rate)
    model_loss = loss_func(x_train=x_train)

    model_neural.compile(loss=model_loss,optimizer=optimizer)

    return model_neural

Answer 1

问题是 x_train 总是 None 并且 keras 不能对 None 求导数。这是因为 model_neural.add(...) 没有 return 任何东西。

我假设 x_train 是传递给网络的输入。在这种情况下，x_train 可能应该是 create_model_neural 的另一个参数，或者您可以尝试 model_neural.input 张量。

Keras 中损失函数的导数

Derivative in loss function in Keras

python

machine-learning

neural-network

keras

loss-function