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. 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
import tensorflow as tf
data = tf.constant([ 1 , 2 , 3 ])
segment_ids = tf.constant([ 2 , 2 , 2 ])
print ( 'data: ' , data)
print ( 'segment_ids: ' , segment_ids)
res = tf.math.segment_min(data, segment_ids)
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 1], shape=(3, ), dtype=int32)
Example 2:
Python3
import tensorflow as tf
data = tf.constant([[ 1 , 2 , 3 ], [ 4 , 5 , 6 ], [ 7 , 8 , 9 ]], dtype = float64)
segment_ids = tf.constant([ 0 , 0 , 2 ])
print ( 'data: ' , data)
print ( 'segment_ids: ' , segment_ids)
res = tf.math.segment_min(data, segment_ids)
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(
[[1. 2. 3. ]
[0. 0. 0. ]
[7. 8. 9. ]], shape=(3, 3), dtype=float64)
Last Updated :
12 Jun, 2020
Like Article
Save Article
Share your thoughts in the comments
Please Login to comment...