故障定義numpy的數組作爲tensorflow變量

Question

我有斧numpy的數組：

[0, 6, 3513, 7, 155, 794, 25, 223, 8, 32, 20, 202, 5025, 350, 91, 6, 66, 207, 5, 2] 

我想將它定義爲一個tensorflow變量如下：

tf.Variable(x) 

而且我得到以下錯誤：

TypeError: Expected binary or unicode string, got [0, 6, 3513, 7, 155, 794, 25, 223, 8, 32, 20, 202, 5025, 350, 91, 6, 66, 207, 5, 2]

到底是什麼？

Answer 1

你可以分享你想做什麼，因爲tensorflow只是定義了一個變量，你只能在執行該會話時使用該變量。希望下面的代碼可以幫助你。

import tensorflow as tf 
    import numpy as np 
    x =[0, 6, 3513, 7, 155, 794, 25, 223, 8, 32, 20, 202, 5025, 350, 91, 6, 
     66, 207, 5, 2] 

    # convert it into numpy array 
    w = np.array(x) 

    # this create a tensor variable 
    q = tf.Variable(x) 

    # create an interactive session 
    sess = tf.InteractiveSession() 


    # now you can perform operation on that tensor variable 

    tf.add(q,q) 

Answer 2

x = np.array(...) 

v = tf.Variable(tf.constant(x))