How to make training prediction on one's own data set

codeniko / shape_predictor_81_face_landmarks

Custom shape predictor model trained to find 81 facial feature landmarks given any image

BSD 3-Clause "New" or "Revised" License

465 stars 126 forks source link

How to make training prediction on one's own data set #8

Closed zhouhao-learning closed 5 years ago

zhouhao-learning commented 5 years ago

Hello, I have a face data with 194 face key points. I want to use your network to train my data so that I can predict 194 face key points, but there is no explanation in your explanation. Please tell me how should I start?

codeniko commented 5 years ago

Hi, the purpose of this project was to share the model that I have trained which enables detecting of 81 facial landmarks on images with faces. Although I have provided a quick summary of how my model came to life, it's not intended to be an in-depth tutorial on how to train your own models.

Please look into dlib tutorials and documentation for how to train your model since they will be more in-depth than I can ever make it.