[BUG]: How can I avoid loading the model every time

[OKC13]

Before You Report a Bug, Please Confirm You Have Done The Following...

• I have updated to the latest version of the packages.
• I have searched for both existing issues and closed issues and found none that matched my issue.

DeepFace's version

newest

Python version

3.8.5

Operating System

centos

Dependencies

How can I avoid loading the model every time? I believe the way you wrote it, the model is loaded each time a prediction is made, which consumes a lot of time. Is there a way to initialize the model into memory first, and then use something like model.predict()?

Reproducible example

embedding = DeepFace.represent(img_path=img_path, model_name=model_name,
                                               detector_backend=backends[4])

Relevant Log Output

No response

Expected Result

No response

What happened instead?

No response

Additional Info

No response

[serengil]

This thread was initiated for bug purposes, but it is unrelated to any bug reporting. Please direct your questions to Stack Overflow, as indicated in the issue templates.