Keras中损失函数的导数 [英] Derivative in loss function in Keras

问题描述

我想在喀拉拉邦做以下损失函数:

I want to make following loss function in keras:

Loss = mse + double_derivative(y_pred,x_train)

我无法合并派生词.我已经尝试过K.gradients(K.gradients(y_pred,x_train),x_train)，但是它没有帮助.

I am not able to incorporate the derivative term. I have tried K.gradients(K.gradients(y_pred,x_train),x_train) but it does not help.

我收到错误消息:

AttributeError:'NoneType'对象没有属性'op'

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

推荐答案

问题是x_train始终为None，而keras无法使用派生wrt None.发生这种情况是因为model_neural.add(...)不返回任何内容.

The problem is that x_train is always None and keras can't take a derivative wrt None. And this is happening because model_neural.add(...) does not return anything.

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

I assume that x_train is the input that is passed to the network. In this case x_train should probably be another argument of create_model_neural or alternatively you can try model_neural.input tensor.

这篇关于Keras中损失函数的导数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！