各位看客，本博客的代码均为实际运行结果，但还是希望您可以自己运行一遍，实践出真知。
实例：
from keras import backend as K
import tensorflow as tf
import numpy as np
a = K.variable(np.array([[[1,2],[3,4],[5,6],[7,8]]]))
b = K.variable(np.array([[[11,12],[13,14],[15,16],[17,18]]]))
c1 = K.concatenate([a,b],axis=0)
c2 = K.concatenate([a,b],axis=1)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
print(sess.run(a))
print(a.shape)
print("-----------------------------")
print(c1.shape)
print(sess.run(c1))
print("-----------------------------")
print(c2.shape)
print(sess.run(c2))
print("-----------------------------")
输出结果：
[[[1. 2.]
[3. 4.]
[5. 6.]
[7. 8.]]]
(1, 4, 2)
-----------------------------
(2, 4, 2)
[[[ 1. 2.]
[ 3. 4.]
[ 5. 6.]
[ 7. 8.]]
[[11. 12.]
[13. 14.]
[15. 16.]
[17. 18.]]]
-----------------------------
(1, 8, 2)
[[[ 1. 2.]
[ 3. 4.]
[ 5. 6.]
[ 7. 8.]
[11. 12.]
[13. 14.]
[15. 16.]
[17. 18.]]]
-----------------------------
axis = m，意思为，在第m个维度相融合，进行矩阵拼接；
