Python – tensorflow.IndexedSlices.dense_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。

dense_shape返回一个包含相应密集张量形状的一维张量。

Syntax: tensorflow.IndexedSlices.dense_shape

Returns: It returns a 1-D Tensor.

示例 1：

Python3

# 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], 2)
  
# Finding dense shape
dense = res.dense_shape
  
# Printing the result
print('dense shape: ', dense)

输出：

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

示例 2：

Python3

# 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 dense shape
dense = res.dense_shape
  
# Printing the result
print('dense shape: ', dense)

输出：

data:  tf.Tensor([1 2 3], shape=(3, ), dtype=int32)
dense shape:  None