Question

假设我有一个张量：

tensor = tf.constant(
  [[[0.05340263, 0.27248233, 0.49127685, 0.07926575, 0.96054204],
    [0.50013988, 0.05903472, 0.43025479, 0.41379231, 0.86508251],
    [0.02033722, 0.11996034, 0.57675261, 0.12049974, 0.65760677],
    [0.71859089, 0.22825203, 0.64064407, 0.47443116, 0.64108334]],

   [[0.18813498, 0.29462021, 0.09433628, 0.97393446, 0.33451445],
    [0.01657461, 0.28126666, 0.64016929, 0.48365073, 0.26672697],
    [0.9379696 , 0.44648103, 0.39463243, 0.51797975, 0.4173626 ],
    [0.89788558, 0.31063058, 0.05492096, 0.86904097, 0.21696292]],

   [[0.07279436, 0.94773635, 0.34173115, 0.7228713 , 0.46553334],
    [0.61199848, 0.88508141, 0.97019517, 0.61465985, 0.48971128],
    [0.53037002, 0.70782324, 0.32158754, 0.2793538 , 0.62661128],
    [0.52787814, 0.17085317, 0.83711126, 0.40567032, 0.71386498]]])

形状为（3，4，5）

我想对其进行切片以返回形状为（3,5）的新张量，其中具有给定的1D张量，其值指示要检索的位置，例如：

index_tensor = tf.constant([2,1,3])

这将导致一个新的张量，如下所示：

[[0.02033722, 0.11996034, 0.57675261, 0.12049974, 0.65760677],        
 [0.01657461, 0.28126666, 0.64016929, 0.48365073, 0.26672697],     
 [0.52787814, 0.17085317, 0.83711126, 0.40567032, 0.71386498]]

，即沿着第二维，从索引2、1，和3中取得项目。类似于：

tensor[:,x,:]

除了这只会给我沿维度在索引“ x”处的项目，我希望它具有灵活性。

可以做到吗？

Answer 1

您可以使用tf.one_hot()来掩盖index_tensor。

index = tf.one_hot(index_tensor,tensor.shape[1])

[[0. 0. 1. 0.]
 [0. 1. 0. 0.]
 [0. 0. 0. 1.]]

然后通过tf.boolean_mask()得到结果。

result = tf.boolean_mask(tensor,index)

[[0.02033722 0.11996034 0.57675261 0.12049974 0.65760677]
 [0.01657461 0.28126666 0.64016929 0.48365073 0.26672697]
 [0.52787814 0.17085317 0.83711126 0.40567032 0.71386498]]

Answer 2

tensor = tf.constant(
  [[[0.05340263, 0.27248233, 0.49127685, 0.07926575, 0.96054204],
    [0.50013988, 0.05903472, 0.43025479, 0.41379231, 0.86508251],
    [0.02033722, 0.11996034, 0.57675261, 0.12049974, 0.65760677],
    [0.71859089, 0.22825203, 0.64064407, 0.47443116, 0.64108334]],

   [[0.18813498, 0.29462021, 0.09433628, 0.97393446, 0.33451445],
    [0.01657461, 0.28126666, 0.64016929, 0.48365073, 0.26672697],
    [0.9379696 , 0.44648103, 0.39463243, 0.51797975, 0.4173626 ],
    [0.89788558, 0.31063058, 0.05492096, 0.86904097, 0.21696292]],

   [[0.07279436, 0.94773635, 0.34173115, 0.7228713 , 0.46553334],
    [0.61199848, 0.88508141, 0.97019517, 0.61465985, 0.48971128],
    [0.53037002, 0.70782324, 0.32158754, 0.2793538 , 0.62661128],
    [0.52787814, 0.17085317, 0.83711126, 0.40567032, 0.71386498]]])


with tf.Session() as sess :
  sess.run( tf.global_variables_initializer() )
  print(sess.run( tf.concat( [ tensor[0:1,2:3], tensor[1:2,1:2], tensor[2:3,3:4] ] , 1 ) ))

这将打印出这样的值。

[[[0.02033722 0.11996034 0.5767526  0.12049974 0.6576068 ]
  [0.01657461 0.28126666 0.64016926 0.48365074 0.26672697]
  [0.52787817 0.17085317 0.83711123 0.40567032 0.713865  ]]]

沿具有给定索引的维切片张量

2 个答案: