AttributeError:图层没有入站节点，或者AttributeError:图层从未被调用 [英] AttributeError: Layer has no inbound nodes, or AttributeError: The layer has never been called

问题描述

我需要一种方法来获取TensorFlow中任何类型的层(即Dense，Conv2D等)的输出张量的形状.根据文档，有output_shape属性可以解决此问题.但是，每次访问它都会得到AttributedError.

I need a way to get the shape of output tensor for any type of layer (i.e. Dense, Conv2D, etc) in TensorFlow. According to documentation, there is output_shape property which solves the problem. However every time I access it I get AttributedError.

以下是显示问题的代码示例:

Here is code sample showing the problem:

import numpy as np
import tensorflow as tf


x = np.arange(0, 8, dtype=np.float32).reshape((1, 8))
x = tf.constant(value=x, dtype=tf.float32, verify_shape=True)

dense = tf.layers.Dense(units=2)

out = dense(x)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    res = sess.run(fetches=out)
    print(res)
    print(dense.output_shape)

print(dense.output_shape)语句将产生错误消息:

The print(dense.output_shape) statement will produce error message:

AttributeError: The layer has never been called and thus has no defined output shape.

或print(dense.output)将产生:

AttributeError('Layer ' + self.name + ' has no inbound nodes.')
AttributeError: Layer dense_1 has no inbound nodes.

有什么办法可以解决该错误?

Is there any way to fix the error?

PS: 我知道在上面的示例中，我可以通过out.get_shape()获得输出张量的形状.但是我想知道为什么output_shape属性不起作用以及如何解决?

P.S.: I know that in example above I can get shape of output tensor via out.get_shape(). However I want to know why output_shape property doesn't work and how I can fix it?

推荐答案

TL; DR

如何解决?定义输入层:

x = tf.keras.layers.Input(tensor=tf.ones(shape=(1, 8)))
dense = tf.layers.Dense(units=2)

out = dense(x)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    res = sess.run(fetches=out)
    print(dense.output_shape) # shape = (1, 2)

---

对Keras的同意文档(如果层只有一个节点，您可以通过以下方式获取其输入张量，输出张量，输入形状和输出形状:

---

Accordint to Keras documentation, if a layer has a single node, you can get its input tensor, output tensor, input shape and output shape via:

• layer.input
• layer.output
• layer.input_shape
• layer.output_shape

但是在上面的示例中，当我们调用layer.output_shape或其他属性时，它将引发看起来有些奇怪的异常.

But in the above example, when we call layer.output_shape or other attributes, it throws exceptions that seem a bit strange.

如果我们深入研究来源代码，由入站节点引起的错误.

If we go deep in the source code, the error caused by inbound nodes.

if not self._inbound_nodes:
  raise AttributeError('The layer has never been called '
                       'and thus has no defined output shape.')

这些入站节点

What these inbound nodes are?

节点描述了两层之间的连通性.每次将图层连接到一些新输入时， 将一个节点添加到 layer._inbound_nodes . 每当一个层的输出被另一个层使用时， 将节点添加到 layer._outbound_nodes .

A Node describes the connectivity between two layers. Each time a layer is connected to some new input, a node is added to layer._inbound_nodes. Each time the output of a layer is used by another layer, a node is added to layer._outbound_nodes.

如上所示，当self._inbounds_nodes为None时，它将引发异常.这意味着，当一个层未连接到输入层或更普遍时，先前的所有层都未连接到输入层，self._inbounds_nodes为空，这引起了问题.

As you can see in the above, when self._inbounds_nodes is None it throws an exception. This means when a layer is not connected to the input layer or more generally, none of the previous layers are connected to an input layer, self._inbounds_nodes is empty which caused the problem.

请注意，示例中的x是张量而不是输入层.参见另一个示例以了解更多信息:

Notice that x in your example, is a tensor and not an input layer. See another example for more clarification:

x = tf.keras.layers.Input(shape=(8,))
dense = tf.layers.Dense(units=2)

out = dense(x)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    res = sess.run(fetches=out, feed_dict={x: np.ones(shape=(1, 8))})
    print(res)
    print(res.shape)  # shape = (1,2)
    print(dense.output_shape)  # shape = (None,2)

这很好，因为定义了输入层.

It is perfectly fine because the input layer is defined.

请注意，在您的示例中，out是张量. tf.shape()函数和.shape =(get_shape())之间的区别是:

Note that, in your example, out is a tensor. The difference between the tf.shape() function and the .shape =(get_shape()) is:

tf.shape(x)返回表示动态的一维整数张量 x的形状.动态形状只有在图形执行时才能知道.

tf.shape(x) returns a 1-D integer tensor representing the dynamic shape of x. A dynamic shape will be known only at graph execution time.

x.shape返回代表静态的Python元组 x的形状.在图形定义时已知的静态形状.

x.shape returns a Python tuple representing the static shape of x. A static shape, known at graph definition time.

有关更多张量形状的信息，请访问: https://pgaleone.eu/tensorflow/2018/07/28/understanding-tensorflow-tensors-shape-static-dynamic/

Read more about tensor shape at: https://pgaleone.eu/tensorflow/2018/07/28/understanding-tensorflow-tensors-shape-static-dynamic/

这篇关于AttributeError:图层没有入站节点，或者AttributeError:图层从未被调用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！