Python – tensorflow.IndexedSlices.shape 属性

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。

shape用于获取 tensorflow.TensorShape 表示密集张量的形状。

Syntax:  tensorflow.IndexedSlices.shape

Returns:  It returns tensorflow.TensorShape representing the shape of the dense tensor.

示例 1：

Python3

# 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], tf.constant([1, 2]))
  
# Finding Shape
shape = res.shape
  
# Printing the result
print('Shape: ', shape)

输出：

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

示例 2：

Python3

# 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], tf.constant([1]))
  
# Finding Shape
shape = res.shape
  
# Printing the result
print('Shape: ', shape)

输出：

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