如何在 TensorFlow 中将张量转换为 ndarray? [英] How can I convert a tensor into a ndarray in TensorFlow?

问题描述

我的目标是将张量转换为没有 'run' 或 'eval' 的 ndarray.我想执行与示例相同的操作.

My goal is to convert a tensor into a ndarray without 'run' or 'eval'. I wanted to perform the same operation as the example.

A = tf.constant(5)
B = tf.constant([[A, 1], [0,0]])

然而，ndarray 可以在 tf.constant 中，但 tensor 不能.因此，我尝试使用以下示例执行操作，但 tf.make_ndarray 不起作用.

However, ndarray can be inside tf.constant but tensor cannot. Therefore, I tried to perform the operation using the following example, but tf.make_ndarray does not work.

A = tf.constant(5)
C = tf.make_ndarray(A)
B = tf.constant([[C, 1], [0,0]])

https://github.com/tensorflow/tensorflow/issues/28840#issuecomment-509551333

如上面的 github 链接所述，tf.make_ndarray 不起作用.准确地说，发生错误是因为 tensorflow 需要一个不存在的 'tensor_shape'，而不是一个存在的 'shape'.

As mentioned in the github link above, tf.make_ndarray does not work. To be precise, an error occurs because tensorflow requires a 'tensor_shape' that does not exist, instead of a 'shape' that exists.

在这种情况下如何运行代码?

How can I run the code in this situation?

推荐答案

tf.make_ndarray 用于转换TensorProto 值转换为 NumPy 数组.这些值通常是图形中使用的常量.例如，当您使用 tf.constant 时，您创建一个 Const 操作，其属性 value 保存操作将产生的常量值.该属性存储为 TensorProto.因此，您可以像这样将 Const 操作的值提取"为 NumPy 数组:

tf.make_ndarray is used to convert TensorProto values into NumPy arrays. These values are generally the constants used in a graph. For example, when you use tf.constant, you create a Const operation with an attribute value holding the constant value that the operation will produce. That attribute is stored as a TensorProto. Hence, you can "extract" the value of a Const operation as a NumPy array like this:

import tensorflow as tf

A = tf.constant(5)
C = tf.make_ndarray(A.op.get_attr('value'))
print(C, type(C))
# 5 <class 'numpy.ndarray'>

但是，一般来说，您不能将任意张量转换为 NumPy 数组，因为它们的值将取决于变量的值和特定会话中的馈送输入.

In general, though, you cannot convert arbitrary tensors into NumPy arrays, as their values will depend on the values of the variables and the fed inputs within a particular session.

这篇关于如何在 TensorFlow 中将张量转换为 ndarray?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！