Python – tensorflow.expand_dims()

TensorFlow 是由 Google 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。

expand_dims()用于在输入张量中插入一个附加维度。

Syntax: tensorflow.expand_dims( input, axis, name)

Parameters:

• input: It is the input Tensor.
• axis: It defines the index at which dimension should be inserted. If input has D dimensions then axis must have value in range  [-(D+1), D].
• name(optional): It defines the name for the operation.

Returns: It returns a Tensor with expanded dimension.

示例 1：

Python3

# Importing the library
import tensorflow as tf
 
# Initializing the input
x = tf.constant([[2, 3, 6], [4, 8, 15]])
 
# Printing the input
print('x:', x)
 
# Calculating result
res = tf.expand_dims(x, 1)
 
# Printing the result
print('res: ', res)

输出：

x: tf.Tensor(
[[ 2  3  6]
 [ 4  8 15]], shape=(2, 3), dtype=int32)
res:  tf.Tensor(
[[[ 2  3  6]]

 [[ 4  8 15]]], shape=(2, 1, 3), dtype=int32)

# shape has changed from (2, 3) to (2, 1, 3)

示例 2：

Python3

# Importing the library
import tensorflow as tf
 
# Initializing the input
x = tf.constant([[2, 3, 6], [4, 8, 15]])
 
# Printing the input
print('x:', x)
 
# Calculating result
res = tf.expand_dims(x, 0)
 
# Printing the result
print('res: ', res)

输出：

x: tf.Tensor(
[[ 2  3  6]
 [ 4  8 15]], shape=(2, 3), dtype=int32)
res:  tf.Tensor(
[[[ 2  3  6]
  [ 4  8 15]]], shape=(1, 2, 3), dtype=int32)
  
# shape has changed from (2, 3) to (1, 2, 3)