tensorflow中tf.concat()用法

   concat()是将tensor沿着指定维度连接起来。其中tensorflow1.3版中是这样定义的&＃xff1a;

concat(values,axis,name&＃61;&＃39;concat&＃39;)

   一、对于2维来说&＃xff0c;0表示行&＃xff0c;1表示列

t1 &＃61; [[1, 2, 3], [4, 5, 6]]
t2 &＃61; [[7, 8, 9], [10, 11, 12]]with tf.Session() as sess:print(sess.run(tf.concat([t1, t2], 0) ))

结果为&＃xff1a;[[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]

t1 &＃61; [[1, 2, 3], [4, 5, 6]]
t2 &＃61; [[7, 8, 9], [10, 11, 12]]with tf.Session() as sess:print(sess.run(tf.concat([t1, t2], 1) ))

结果为&＃xff1a;[[1, 2, 3, 7, 8, 9], [4, 5, 6, 10, 11, 12]]

二、 对于3维来说  0表示纵向&＃xff0c;1表示行&＃xff0c;2表示列

t1 &＃61; [[[1, 1, 1],[2, 2, 2]],[[3, 3, 3],[4, 4, 4]]]t2 &＃61; [[[5, 5, 5],[6, 6, 6]],[[7, 7, 7],[8, 8, 8]]]with tf.Session() as sess:print(sess.run(tf.concat([t1, t2], 0) ))

结果&＃xff1a;[[[1 1 1],[2 2 2]] , [[3 3 3],[4 4 4]] , [[5 5 5],[6 6 6]] ,  [[7 7 7],[8 8 8]]]

Tensor("concat_30:0", shape&＃61;(4, 2, 3), dtype&＃61;int32)

axis&＃61;1的结果如下&＃xff1a;

Tensor("concat_31:0", shape&＃61;(2, 4, 3), dtype&＃61;int32)
[[[1 1 1]&＃xff0c; [2 2 2]&＃xff0c;[5 5 5]&＃xff0c;[6 6 6]]&＃xff0c; [[3 3 3]&＃xff0c; [4 4 4]&＃xff0c;[7 7 7]&＃xff0c; [8 8 8]]]

axis&＃61;2的结果如下&＃xff1a;

Tensor("concat_32:0", shape&＃61;(2, 2, 6), dtype&＃61;int32)
[[[1 1 1 5 5 5]&＃xff0c;[2 2 2 6 6 6]]&＃xff0c; [[3 3 3 7 7 7]&＃xff0c; [4 4 4 8 8 8]]]