TensorFlow-无法使用get_shape命令获取矩阵的形状 [英] TensorFlow - Cannot get the shape of matrix with the get_shape command

问题描述

当我这样做时，我似乎无法获得张量的形状

I can't seem to get the shape of the tensor when I do

get_shape().as_list()

这是我编写的代码:

matrix1 = tf.placeholder(tf.int32) 
matrix2 = tf.placeholder(tf.int32)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    a = sess.run(matrix1, {matrix1: [[1,2,3],[4,5,6],[7,8,9]]})
    b = sess.run(matrix2, {matrix2: [[10,11,12],[13,14,15], [16,17,18]]})
    print(a.get_shape().as_list()) #ERROR

我收到以下错误:

AttributeError: 'numpy.ndarray' object has no attribute 'get_shape'

我想知道矩阵的形状，以便可以采用任意矩阵并遍历其行和列.

I want to know the shape of the matrix so that I can take in an arbitrary matrix and loop through its rows and columns.

推荐答案

^{只需在注释中总结讨论内容，而无需多加注释}

matrix1和a都是多维数组，但是有一个区别:

Both matrix1 and a are multidimensional arrays, but there is a difference:

• matrix1是 tf.Tensor 的实例，它支持两种访问形状的方法:matrix1.shape属性和matrix1.get_shape()方法.

tf.Tensor评估结果a是一个numpy

The result of tf.Tensor evaluation, a, is a numpy ndarray, which has just a.shape attribute.

从历史上看，tf.Tensor仅具有get_shape()方法，后来又添加了shape以使其类似于numpy.还有一点需要注意:在tensorflow中，张量形状可以是动态的(例如您的示例)，在这种情况下，get_shape()和shape都不会返回数字.在这种情况下，可以使用 tf.shape 函数在运行时进行访问(下面的示例可能有用).

Historically, tf.Tensor had only get_shape() method, shape was added later to make it similar to numpy. And one more note: in tensorflow, tensor shape can be dynamic (like in your example), in which case neither get_shape() nor shape will return a number. In this case, one can use tf.shape function to access it in runtime (here's an example when it might be useful).

这篇关于TensorFlow-无法使用get_shape命令获取矩阵的形状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！