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

Support training MTCNN #1

Open
justinpinkney opened this issue Jan 16, 2020 · 4 comments
Open

Support training MTCNN #1

justinpinkney opened this issue Jan 16, 2020 · 4 comments
Labels
enhancement New feature or request

Comments

@justinpinkney
Copy link
Member

justinpinkney commented Jan 16, 2020

We currently do not support training a MTCNN model from scratch, only inference using pre-trained weights.

If you'd be interested in being able to train a custom model, please like or comment on this issue.

@justinpinkney justinpinkney added the enhancement New feature or request label Jan 16, 2020
@Omripaz1
Copy link

Omripaz1 commented Mar 10, 2020

Hey Justin,
Training a custom MTCNN model would be lovely.
Also, I would like to know if there is an option to use transfer learning on the current model in order to use it on modified facial images.

Thanks ahead

@justinpinkney
Copy link
Member Author

justinpinkney commented Mar 10, 2020

Thanks for the input Omripaz1. If we implement training then transfer learning would also be possible.

@cuixing158
Copy link

cuixing158 commented Mar 20, 2020

Hope to support custom training in the future and increase flexibility!

@Mostafa77es
Copy link

Mostafa77es commented Apr 23, 2022

Hi Justin,
Training a custom MTCNN model would be useful to train the model in other datasets. There are many challenging datasets for face and landmarks detection such as occluded faces. So, please support the training model of MTCNN.
I appreciate your efforts.
Thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants