NotImplementedError:无法将符号张量(2nd_target:0)转换为numpy数组 [英] NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array

问题描述

我尝试将2个损失函数传递给模型，因为 Keras允许这样做.

I try to pass 2 loss functions to a model as Keras allows that.

loss:字符串(目标函数的名称)或目标函数或损失实例.见损失.如果模型有多个输出，则可以通过传递字典或列表对每个输出使用不同的损失损失.模型将使损失值最小化然后是所有个人损失的总和.

loss: String (name of objective function) or objective function or Loss instance. See losses. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of losses. The loss value that will be minimized by the model will then be the sum of all individual losses.

两个损失函数:

def l_2nd(beta):
    def loss_2nd(y_true, y_pred):
        ...
        return K.mean(t)

    return loss_2nd

和

def l_1st(alpha):
    def loss_1st(y_true, y_pred):
        ...
        return alpha * 2 * tf.linalg.trace(tf.matmul(tf.matmul(Y, L, transpose_a=True), Y)) / batch_size

    return loss_1st

然后我建立模型:

l2 = K.eval(l_2nd(self.beta))
l1 = K.eval(l_1st(self.alpha))
self.model.compile(opt, [l2, l1])

我训练时会产生错误:

1.15.0-rc3警告:tensorflow:来自/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630:调用BaseResourceVariable.初始化(来自带有约束的tensorflow.python.ops.resource_variable_ops)是不推荐使用，将在以后的版本中删除.有关说明

1.15.0-rc3 WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.init (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for

NotImplementedError错误回溯(最近的呼叫最后)在()47 create_using = nx.DiGraph()，nodetype = None，data = [('weight'，int)])48---> 49模型= SDNE(G，hidden_​​size = [256，128]，)50 model.train(batch_size = 100，epochs = 40，verbose = 2)51个嵌入= model.get_embeddings()

NotImplementedError Traceback (most recent call last) in () 47 create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)]) 48 ---> 49 model = SDNE(G, hidden_size=[256, 128],) 50 model.train(batch_size=100, epochs=40, verbose=2) 51 embeddings = model.get_embeddings()

在 init (自身，图形，hidden_​​size，alpha，beta，nu1和nu2)72 self.A，self.L = self._create_A_L(73 self.graph，self.node2idx)#调整矩阵，L矩阵---> 74 self.reset_model()75 self.inputs = [self.A，self.L]76 self._embeddings = {}

10 frames in init(self, graph, hidden_size, alpha, beta, nu1, nu2) 72 self.A, self.L = self._create_A_L( 73 self.graph, self.node2idx) # Adj Matrix,L Matrix ---> 74 self.reset_model() 75 self.inputs = [self.A, self.L] 76 self._embeddings = {}

在reset_model(自我，选择)中

in reset_model(self, opt)

---> 84 self.model.compile(opt，loss = [l2，l1])85 self.get_embeddings()86

---> 84 self.model.compile(opt, loss=[l2, l1]) 85 self.get_embeddings() 86

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/tracking/base.py在_method_wrapper(self，* args，** kwargs)中455 self._self_setattr_tracking = False#pylint:disable =受保护的访问456尝试:-> 457 result = method(self，* args，** kwargs)458最后:459 self._self_setattr_tracking = previous_value#pylint:disable =受保护的访问

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs) 455 self._self_setattr_tracking = False # pylint: disable=protected-access 456 try: --> 457 result = method(self, *args, **kwargs) 458 finally: 459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access

NotImplementedError:无法转换符号张量(2nd_target:0)到一个numpy数组.

请帮助，谢谢！

推荐答案

我找到了解决此问题的方法:

I found the solution to this problem:

这是因为我将符号张量与非符号类型(例如numpy)混合使用.例如.不建议有这样的东西:

It was because I mixed symbolic tensor with a non-symbolic type, such as a numpy. For example. It is NOT recommended to have something like this:

def my_mse_loss_b(b):
     def mseb(y_true, y_pred):
         ...
         a = np.ones_like(y_true) #numpy array here is not recommended
         return K.mean(K.square(y_pred - y_true)) + a
     return mseb

相反，您应该将所有像这样转换为符号张量:

Instead, you should convert all to symbolic tensors like this:

def my_mse_loss_b(b):
     def mseb(y_true, y_pred):
         ...
         a = K.ones_like(y_true) #use Keras instead so they are all symbolic
         return K.mean(K.square(y_pred - y_true)) + a
     return mseb

希望获得帮助！

这篇关于NotImplementedError:无法将符号张量(2nd_target:0)转换为numpy数组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！