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

9 votes262 views5 answers
Threading python
Python
23 votes245 views2 answers
How to replace zero value in python dataframe
Python
0 vote258 views1 answer
Save model with best validation loss keras
Python
0 vote254 views1 answer
Num=operator.index(num) name 'num' is not defined
Python
1 vote288 views4 answers
Pandas count zeros in column
Python
3 votes284 views1 answer
How to know all methods in a module in python
Python
5 votes269 views2 answers
Python string replace by index
Python
17 votes257 views2 answers
WARNING: You are using pip version 19.2.3, however version 21.2.4 is available.
Python
4 votes288 views2 answers
Create an array from 1 to n python
Python
0 vote263 views1 answer
Numpy remove rows containing nan
Python