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

问题描述

在将Tensorflow与Python绑定一起使用时如何将张量转换为numpy数组?

How to convert a tensor into a numpy array when using Tensorflow with Python bindings?

推荐答案

Session.run或eval返回的任何张量都是NumPy数组.

Any tensor returned by Session.run or eval is a NumPy array.

>>> print(type(tf.Session().run(tf.constant([1,2,3]))))
<class 'numpy.ndarray'>

或者:

>>> sess = tf.InteractiveSession()
>>> print(type(tf.constant([1,2,3]).eval()))
<class 'numpy.ndarray'>

或者，等效地:

>>> sess = tf.Session()
>>> with sess.as_default():
>>>    print(type(tf.constant([1,2,3]).eval()))
<class 'numpy.ndarray'>

编辑:由Session.run或eval()返回的任何张量不是NumPy数组.例如，稀疏张量返回为SparseTensorValue:

Not any tensor returned by Session.run or eval() is a NumPy array. Sparse Tensors for example are returned as SparseTensorValue:

>>> print(type(tf.Session().run(tf.SparseTensor([[0, 0]],[1],[1,2]))))
<class 'tensorflow.python.framework.sparse_tensor.SparseTensorValue'>

这篇关于如何在TensorFlow中将张量转换为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！