Python – tensorflow.IndexedSlices.dense_shape Attribute

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks. 

dense_shape returns a 1-D tensor containing the shape of the corresponding dense tensor. 

Syntax: tensorflow.IndexedSlices.dense_shape

Returns: It returns a 1-D Tensor.

Example 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)

Output:

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

Example 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)

Output:

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