如何从 Tensorflow 中的其他张量中找到张量中的值

Question

我在从其他张量中查找值时遇到问题。

这个问题的描述如下。 例如，

Input Tensor
s_idx = ( 1, 3, 5, 7)
e_idx = ( 3, 4, 5, 8)


label_s_idx = (2, 2, 3, 6)
label_e_idx = (2, 3, 4, 8)

上图中，s_idx[1]的值等于label_s_idx[2]和e_idx[1]的值> 等于 label_e_idx[2]。

换句话说，问题是如果条件 s_idx[i] == label_s_idx[i] 给 output[i] 值 1并且 e_idx[i] == label_s_idx[j] 满足 label_s_idx 长度（== label_e_idx 长度）范围内的一些 j。

因此，在上面的例子中，输出张量是

output = ( 0, 1, 0, 0)

如何在 Python 中的 Tensorflow 上进行这样的编码？

Answer 1

我找不到为此操作设计的函数。您可以使用下面的矩阵运算来实现它。

import tensorflow as tf

s_idx = [1, 3, 5, 7]
e_idx = [3, 4, 5, 8]
label_s_idx = [2, 2, 3, 6]
label_e_idx = [2, 3, 4, 8]

# convert the variables to one-hot encoding
# s_oh[i,j] = 1 if and only if s_idx[i] == j
# analogous for e_oh
s_depth = tf.reduce_max([s_idx, label_s_idx])
s_oh = tf.one_hot(s_idx, s_depth)
label_s_oh = tf.one_hot(label_s_idx, s_depth)

e_depth = tf.reduce_max([e_idx, label_e_idx])
e_oh = tf.one_hot(e_idx, e_depth)
label_e_oh = tf.one_hot(label_e_idx, e_depth)

# s_mult[i,j] == 1 if and only if s_idx[i] == label_s_idx[j]
# analogous for e_mult
s_mult = tf.matmul(s_oh, label_s_oh, transpose_b=True)
e_mult = tf.matmul(e_oh, label_e_oh, transpose_b=True)

# s_included[i] == 1 if and only if s_idx[i] is included in label_s_idx
# analogous for e_included
s_included = tf.reduce_max(s_mult, axis=1)
e_included = tf.reduce_max(e_mult, axis=1)

# output[i] == 1 if and only if s_idx[i] is included in label_s_idx
# and e_idx[i] is included in label_e_idx
output = tf.multiply(s_included, e_included)

with tf.Session() as sess:
    print(sess.run(output))
# [0. 1. 0. 0.]