Tf.squeeze()

Removes dimensions of size 1 from the shape of a tensor.

tf.squeeze(
    input, axis=None, name=None
)

Given a tensor input, this operation returns a tensor of the same 
type with all dimensions of size 1 removed. If you don't want to 
remove all size 1 dimensions, you can remove specific size 1 
dimensions by specifying axis.

Example:
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t))  # [2, 3]
# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
tf.shape(tf.squeeze(t, [2, 4]))  # [1, 2, 3, 1]

Source: tensorflow.org

Similar codes

0 vote186 views1 answer
How to order randomly in django orm
Python Django
0 vote184 views1 answer
Python if index not out of range
Python
0 vote139 views1 answer
UTC to ISO 8601 with Local TimeZone information without microsecond (Python 3):
Python
-2 votes151 views1 answer
Numpy find index of matching values
Python
9 votes191 views1 answer
Create models in django
Python Django
0 vote134 views1 answer
Python resample time series
Python
0 vote161 views1 answer
Python pandas return column name of a specific column
Python
0 vote161 views1 answer
Multi hot encode pandas column
Python
0 vote148 views1 answer
Send serial commands in python
Python
1 vote157 views1 answer
Swapping of two numbers in python
Python