Python - tensorflow.math.segment_mean()

Python – tensorflow.math.segment_sum()

Last Updated : 12 Jun, 2020

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

segment_sum() is used to find the sum of elements in segments of a tensor.

Syntax: tensorflow.math.segment_sum( data, segment_ids, name )

Parameter:

data: It is a tensor. Allowed dtypes are float32, float64, int32, uint8, int16, int8, int64, bfloat16, uint16, half, uint32, uint64.

segment_ids: It’s 1-D tensor with sorted values. It’s size should be equal to size of first dimension of data. Allowed dtypes are int32 and int64.

name(optional): It defines the name for the operation.

Return: It returns a tensor of dtype as x.

Example 1:

Python3

# importing the library 
import tensorflow as tf 
  
# Initializing the input tensor 
data = tf.constant([1, 2, 3]) 
segment_ids = tf.constant([2, 2, 2]) 
  
# Printing the input tensor 
print('data: ', data) 
print('segment_ids: ', segment_ids) 
  
# Calculating result 
res = tf.math.segment_sum(data, segment_ids) 
  
# Printing the result 
print('Result: ', res) 

Output:

data:  tf.Tensor([1 2 3], shape=(3, ), dtype=int32)
segment_ids:  tf.Tensor([2 2 2], shape=(3, ), dtype=int32)
Result:  tf.Tensor([0 0 6], shape=(3, ), dtype=int32)

Example 2:

Python3

# importing the library 
import tensorflow as tf 
  
# Initializing the input tensor 
data = tf.constant([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype = float64) 
segment_ids = tf.constant([0, 0, 2]) 
  
# Printing the input tensor 
print('data: ', data) 
print('segment_ids: ', segment_ids) 
  
# Calculating result 
res = tf.math.segment_sum(data, segment_ids) 
  
# Printing the result 
print('Result: ', res) 

Output:

data:  tf.Tensor(
[[1. 2. 3.]
 [4. 5. 6.]
 [7. 8. 9.]], shape=(3, 3), dtype=float64)
segment_ids:  tf.Tensor([0 0 2], shape=(3, ), dtype=int32)
Result:  tf.Tensor(
[[5. 7. 9.]
 [0. 0. 0.]
 [7. 8. 9.]], shape=(3, 3), dtype=float64)

Python - tensorflow.math.segment_mean()

aman neekhara

Improve

Article Tags :

Similar Reads

Python - tensorflow.math.unsorted_segment_sum()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. unsorted_segment_sum() is used to find the sum of segments. Syntax: tensorflow.math.unsorted_segment_sum( data, segment_ids, num_segments, name ) Parameter: data: It is a

Python - tensorflow.math.segment_min()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. segment_min() is used to find the minimum element in segments of a tensor. Syntax: tensorflow.math.segment_min( data, segment_ids, name ) Parameter: data: It is a tensor.

Python - tensorflow.math.segment_max()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. segment_max() is used to find the maximum element in segments of a tensor. Syntax: tensorflow.math.segment_max( data, segment_ids, name ) Parameter: data: It is a tensor.

Python - tensorflow.math.segment_mean()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. segment_mean() is used to find the mean of elements in segments of a tensor. Syntax: tensorflow.math.segment_mean( data, segment_ids, name ) Parameter: data: It is a tens

Python - tensorflow.math.segment_prod()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. segment_prod() is used to find the product of elements in segments of a tensor. Syntax: tensorflow.math.segment_prod( data, segment_ids, name ) Parameter: data: It is a t

Python - tensorflow.math.reduce_sum()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. reduce_sum() is used to find sum of elements across dimensions of a tensor. Syntax: tensorflow.math.reduce_sum( input_tensor, axis, keepdims, name) Parameters: input_tens

Python - tensorflow.math.rint()

TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning neural networks. rint() is used to find element-wise integer closest to x. Syntax: tf.math.rint(x, name) Parameter: x: It's the input tensor. Allowed dtype for this tensor are bfloat16, h

Python - tensorflow.math.sigmoid()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. sigmoid() is used to find element wise sigmoid of x. Syntax: tensorflow.math.sigmoid(x, name) Parameters: x: It's a tensor. Allowed dtypes are float16, float32, float64,

Python - tensorflow.math.reduce_std()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. reduce_std() is used to find standard deviation of elements across dimensions of a tensor. Syntax: tensorflow.math.reduce_std( input_tensor, axis, keepdims, name) Paramet

Python - tensorflow.math.unsorted_segment_sqrt_n()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks. unsorted_segment_sqrt_n() is used to find the sum of segments divided by sqrt(N). Syntax: tensorflow.math.unsorted_segment_sqrt_n( data, segment_ids, num_segments, name )