tf.concat:
函数原型:
tf.concat(values,axis,name='concat')
作用:
- 按指定轴(axis)进行张量连接操作(Concatenates Tensors)
合并方式:
- 将axis指定维度上的元素进行合并即增加axis维度元素
例子:
import tensorflow as tf
t1 = [[1, 2, 3], [4, 5, 6]]
t2 = [[7, 8, 9], [10, 11, 12]]
con1 = tf.concat(t1, 0)
con2 = tf.concat([t1, t2], 0)
con3 = tf.concat([t1, t2], 1)
con4 = tf.concat([t1, t2], -1)
shape1 = tf.shape(con1)
shape2 = tf.shape(con2)
shape3 = tf.shape(con3)
shape4 = tf.shape(con4)
with tf.Session() as sess:
print(sess.run(con1))
print(sess.run(shape1))
print(sess.run(con2))
print(sess.run(shape2))
print(sess.run(con3))
print(sess.run(shape3))
print(sess.run(con4))
print(sess.run(shape4))
"""
[1 2 3 4 5 6]
[6]
[[ 1 2 3]
[ 4 5 6]
[ 7 8 9]
[10 11 12]]
[4 3]
[[ 1 2 3 7 8 9]
[ 4 5 6 10 11 12]]
[2 6]
[[ 1 2 3 7 8 9]
[ 4 5 6 10 11 12]]
[2 6]
"""