Question

我想切片张量以通过索引列表获得特定张量，例如：

word_weight   = tf.get_variable("word_weight", [20])
a= word_weight[ [1,6,5] ]

（我想得到word_weight[1], word_weight[6], word_weight[5]）

但是当我运行代码时出现以下错误：

ValueError: Shape (16491,) must have rank 3

Answer 1

首先，首先评估张量。然后，您可以将它们编入索引：

var sys = require('util')
var exec = require('child_process').exec;

function puts(error, stdout, stderr) { 
   console.log(stdout) 
}

// this is where you should get your path/filename
var filename = "login";
// execute unix command 'file'
exec("file " + filename, puts);

输出：

import tensorflow as tf

word_weight = tf.get_variable("word_weight", [20])

with tf.Session() as sess:   
    tf.initialize_all_variables().run()
    x = sess.run(word_weight)
    print(x[[1,6,5]])
    # Or evaluete like this
    print(sess.run([word_weight[1],word_weight[6],word_weight[5]]))

TensorFlow - 切片张量导致：ValueError：Shape（16491，）必须具有等级3

1 个答案: