TensorFlow IndexedSlices 中的 indices 属性的用法与实例


发布日期 : 2024-06-05 22:54:10 UTC

访问量: 10 次浏览

Python – tensorflow.IndexedSlices.indices 属性

TensorFlow是谷歌设计的开源Python库,用于开发机器学习模型和深度学习神经网络。

indices用于查找分片的索引。

语法

tensorflow.IndexedSlices.indices

返回:它返回一个包含分片索引的一维张量。

示例

示例 1:

# Importing the library
import tensorflow as tf

# Initializing the input
data = tf.constant([1, 2, 3])

# Printing the input
print('data: ', data)

# Calculating result
res = tf.IndexedSlices(data, [0])

# Finding Graph 
indices = res.indices

# Printing the result
print('Indices: ', indices)

输出:

data: tf.Tensor([1 2 3], shape=(3, ), dtype=int32)
Indices: [0]

示例 2:

# Importing the library
import tensorflow as tf

# Initializing the input
data = tf.constant([[1, 2, 3], [4, 5, 6]])

# Printing the input
print('data: ', data)

# Calculating result
res = tf.IndexedSlices(data, [0, 1])

# Finding Graph 
indices = res.indices

# Printing the result
print('Indices: ', indices)

输出:

data: tf.Tensor(
[[1 2 3]
[4 5 6]], shape=(2, 3), dtype=int32)
Indices: [0, 1]