【Tensorflow】tf.reshape 函数

来源：互联网发布：2015网络热门词汇编辑：程序博客网时间：2024/05/22 04:31

tf.reshape(tensor, shape, name=None) 数据重定形状函数

参数：

tensor：输入数据
shape：目标形状
name：名称

返回：Tensor

例：

# tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9]# tensor 't' 的形状就是 [9]reshape(t, [3, 3]) ==> [[1, 2, 3],                        [4, 5, 6],                        [7, 8, 9]]# tensor 't' is [[[1, 1], [2, 2]],#                [[3, 3], [4, 4]]]# tensor 't' 当前形状是 [2, 2, 2]reshape(t, [2, 4]) ==> [[1, 1, 2, 2],                        [3, 3, 4, 4]]# tensor 't' is [[[1, 1, 1],#                 [2, 2, 2]],#                [[3, 3, 3],#                 [4, 4, 4]],#                [[5, 5, 5],#                 [6, 6, 6]]]# tensor 't' 形状是 [3, 2, 3]# pass '[-1]' 扁平化 't'reshape(t, [-1]) ==> [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6]# -1 也可以被用于shape中# -1 被推断结果是 9：reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3], [4, 4, 4, 5, 5, 5, 6, 6, 6]]# -1 被推断结果是 2:reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3], [4, 4, 4, 5, 5, 5, 6, 6, 6]]# -1 被推断结果是 3:reshape(t, [ 2, -1, 3]) ==> [[[1, 1, 1], [2, 2, 2], [3, 3, 3]], [[4, 4, 4], [5, 5, 5], [6, 6, 6]]]# tensor 't' is [7]# shape `[]` 重塑为标量，用[]的时候，t只是有一个元素，不然会报错reshape(t, []) ==> 7测试代码import tensorflow as tft = [7]k = tf.reshape(t,[])sess = tf.Session()kk = sess.run(k)print(kk)

0 0