tf.transpose(input, [dimension_1, dimenaion_2,…,dimension_n]):这个函数主要适用于交换输入张量的不同维度用的,如果输入张量是二维,就相当是转置。dimension_n是整数,如果张量是三维,就是用0,1,2来表示。这个列表里的每个数对应相应的维度。如果是[2,1,0],就把输入张量的第三维度和第一维度交换。
tf.transpose的第二个参数perm=[0,1,2],0代表三维数组的高(即为二维数组的个数),1代表二维数组的行,2代表二维数组的列。 tf.transpose(x, perm=[1,0,2])代表将三位数组的高和行进行转置。
tf.transpose(
a,
perm=None,
name='transpose',
conjugate=False
)
函数参数:
返回:
置换 a,根据 perm 重新排列尺寸. 返回的张量的维度 i 将对应于输入维度 perm[i].如果 perm 没有给出,它被设置为(n-1 … 0),其中 n 是输入张量的秩.因此,默认情况下,此操作在二维输入张量上执行常规矩阵转置.如果共轭为 True,并且 a.dtype 是 complex64 或 complex128,那么 a 的值是共轭转置和.
x = tf.constant([[1, 2, 3], [4, 5, 6]])
tf.transpose(x) # [[1, 4]
# [2, 5]
# [3, 6]]
# Equivalently
tf.transpose(x, perm=[1, 0]) # [[1, 4]
# [2, 5]
# [3, 6]]
# If x is complex, setting conjugate=True gives the conjugate transpose
x = tf.constant([[1 + 1j, 2 + 2j, 3 + 3j],
[4 + 4j, 5 + 5j, 6 + 6j]])
tf.transpose(x, conjugate=True) # [[1 - 1j, 4 - 4j],
# [2 - 2j, 5 - 5j],
# [3 - 3j, 6 - 6j]]
# 'perm' is more useful for n-dimensional tensors, for n > 2
x = tf.constant([[[ 1, 2, 3],
[ 4, 5, 6]],
[[ 7, 8, 9],
[10, 11, 12]]])
# Take the transpose of the matrices in dimension-0
# (this common operation has a shorthand `matrix_transpose`)
tf.transpose(x, perm=[0, 2, 1]) # [[[1, 4],
# [2, 5],
# [3, 6]],
# [[7, 10],
# [8, 11],
# [9, 12]]]
test
import tensorflow as tf
#x = tf.constant([[1, 2 ,3],[4, 5, 6]])
x = [[[1,2,3,4],[5,6,7,8],[9,10,11,12]],[[21,22,23,24],[25,26,27,28],[29,30,31,32]]]
#a=tf.constant(x)
a=tf.transpose(x, [0, 1, 2])
b=tf.transpose(x, [0, 2, 1])
c=tf.transpose(x, [1, 0, 2])
d=tf.transpose(x, [1, 2, 0])
e=tf.transpose(x, [2, 1, 0])
f=tf.transpose(x, [2, 0, 1])
# 'perm' is more useful for n-dimensional tensors, for n > 2
# 'x' is [[[1 2 3]
# [4 5 6]]
# [[7 8 9]
# [10 11 12]]]
# Take the transpose of the matrices in dimension-0
#tf.transpose(b, perm=[0, 2, 1])
with tf.Session() as sess:
print ('---------------')
print (sess.run(a))
print ('---------------')
print (sess.run(b))
print ('---------------')
print (sess.run(c))
print ('---------------')
print (sess.run(d))
print ('---------------')
print (sess.run(e))
print ('---------------')
print (sess.run(f))
print ('---------------')
我们期待的结果是得到如下矩阵:
a: 2 x 3*4 b: 2 x 4*3 c: 3 x 2*4 d: 3 x 4*2 e: 4 x 3*2 f: 4 x 2*3
运行脚本,结果一致,如下:
---------------
[[[ 1 2 3 4]
[ 5 6 7 8]
[ 9 10 11 12]]
[[21 22 23 24]
[25 26 27 28]
[29 30 31 32]]]
---------------
[[[ 1 5 9]
[ 2 6 10]
[ 3 7 11]
[ 4 8 12]]
[[21 25 29]
[22 26 30]
[23 27 31]
[24 28 32]]]
---------------
[[[ 1 2 3 4]
[21 22 23 24]]
[[ 5 6 7 8]
[25 26 27 28]]
[[ 9 10 11 12]
[29 30 31 32]]]
---------------
[[[ 1 21]
[ 2 22]
[ 3 23]
[ 4 24]]
[[ 5 25]
[ 6 26]
[ 7 27]
[ 8 28]]
[[ 9 29]
[10 30]
[11 31]
[12 32]]]
---------------
[[[ 1 21]
[ 5 25]
[ 9 29]]
[[ 2 22]
[ 6 26]
[10 30]]
[[ 3 23]
[ 7 27]
[11 31]]
[[ 4 24]
[ 8 28]
[12 32]]]
---------------
[[[ 1 5 9]
[21 25 29]]
[[ 2 6 10]
[22 26 30]]
[[ 3 7 11]
[23 27 31]]
[[ 4 8 12]
[24 28 32]]]
---------------
参考:https://www.w3cschool.cn/tensorflow_python/tensorflow_python-z61d2no5.html https://blog.csdn.net/uestc_c2_403/article/details/73350498 https://blog.csdn.net/cc1949/article/details/78422704