I have created an algorithm similar to FaceNet (not as completely same as FaceNet because of the GPU limitations) , optimized it and used it. This algorithm is tested for only one person but if you want, you can use more than one positive and anchor values to train the network. Furthermore, this algorithm is sensitive to light and position of face.
This project is tested with GTX 1050
This algorithm is sensitive to light and position of the video camera
This algorithm is tested for only one people, you can test it with more positive and anchor values if you want
I haven't tested this algorithm with similar faces
Github displays only 1000 photos of humans
-
Notifications
You must be signed in to change notification settings - Fork 0
I have created an algorithm similar to FaceNet (not as completely same as FaceNet because of the GPU limitations) , optimized it and used it. This algorithm is tested for only one person but if you want, you can use more than one positive and anchor values to train the network. Dataset: https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
logicdeveloperTR/Manually-Created-Face-Recognition-Model
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
I have created an algorithm similar to FaceNet (not as completely same as FaceNet because of the GPU limitations) , optimized it and used it. This algorithm is tested for only one person but if you want, you can use more than one positive and anchor values to train the network. Dataset: https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published