TensorFlow基础笔记(4) Tensor Transformation
https://segmentfault.com/a/1190000008793389
抽取
-
tf.slice(input_, begin, size, name=None)
:按照指定的下标范围抽取连续区域的子集 -
tf.gather(params, indices, validate_indices=None, name=None)
:按照指定的下标集合从axis=0
中抽取子集,适合抽取不连续区域的子集
input = [[[1, 1, 1], [2, 2, 2]],
[[3, 3, 3], [4, 4, 4]],
[[5, 5, 5], [6, 6, 6]]]
tf.slice(input, [1, 0, 0], [1, 1, 3]) ==> [[[3, 3, 3]]]
tf.slice(input, [1, 0, 0], [1, 2, 3]) ==> [[[3, 3, 3],
[4, 4, 4]]]
tf.slice(input, [1, 0, 0], [2, 1, 3]) ==> [[[3, 3, 3]],
[[5, 5, 5]]]
tf.gather(input, [0, 2]) ==> [[[1, 1, 1], [2, 2, 2]],
[[5, 5, 5], [6, 6, 6]]]
下面通过图片实例来说明求解过程:
import tensorflow as tf
import numpy as np
input = np.array([[[1, 1, 1], [2, 2, 2]],
[[3, 3, 3], [4, 4, 4]],
[[5, 5, 5], [6, 6, 6]]])
print(input.shape)
print(input)
sess = tf.Session()
out = tf.slice(input, [1, 0, 0], [1, 2, 3])
print ('out:\n',sess.run(out))
输出:
(3, 2, 3)
[[[1 1 1]
[2 2 2]]
[[3 3 3]
[4 4 4]]
[[5 5 5]
[6 6 6]]]
out:
[[[3 3 3]
[4 4 4]]]
维度为 3 * 2 * 3
第0方向维度,竖直方向,维度为3
第1方向维度,竖直方向,维度为2
第2方向维度,水平方向,维度为3
begin = [1, 0, 0]
size = [1, 2, 3]
定位到 input[1,1,2] = 3