Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Training time #44

Closed
JS0926 opened this issue Jul 17, 2018 · 9 comments
Closed

Training time #44

JS0926 opened this issue Jul 17, 2018 · 9 comments

Comments

@JS0926
Copy link

JS0926 commented Jul 17, 2018

I am new in python. I training the data from UTFFace, but it too very long time. Any method that can train the data in short time? Thank you.

@yu4u
Copy link
Owner

yu4u commented Jul 17, 2018

There is not many options.
Use smaller training images, buy a good GPU machine, or try Google Colaboratory with GPU.

@JS0926
Copy link
Author

JS0926 commented Jul 23, 2018 via email

@yu4u
Copy link
Owner

yu4u commented Jul 23, 2018

Depth of the model can be set in train.py by depth argument.
Default value is 16.

@JS0926
Copy link
Author

JS0926 commented Jul 23, 2018 via email

@yu4u
Copy link
Owner

yu4u commented Jul 23, 2018

Did you train the model using CPU?

@JS0926
Copy link
Author

JS0926 commented Jul 24, 2018 via email

@yu4u
Copy link
Owner

yu4u commented Jul 24, 2018

Please train network using a machine with GPU as the first my comment.

@JS0926
Copy link
Author

JS0926 commented Jul 27, 2018

I have another question which is how can I get the age (value) and gender from the person who testing in front the webcam? I am doing Final year project, which I want get the data(age and gender) from them for doing some recommendation purpose based on their age and gender .

@yu4u
Copy link
Owner

yu4u commented Jul 27, 2018

Please carefully read demo.py; the answer is there.

@JS0926 JS0926 closed this as completed Dec 16, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants