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

52 votes356 views2 answers
Python find index by value
Python
1 vote324 views2 answers
Left click pyautogui
Python
30 votes332 views3 answers
Django create superuser from script
Python
0 vote326 views1 answer
Replace transparent pixels python
Python
1 vote305 views1 answer
Subset a list python
Python
1 vote339 views1 answer
How to check if two columns match in pandas
Python
0 vote340 views1 answer
Herons rule python
Python
0 vote384 views1 answer
Flask - store object directly in a session [duplicate]
Python Flask
0 vote317 views1 answer
Pandas csv sum column
Python
0 vote315 views1 answer
Where to import kivy builder
Python