logicdeveloperTR/Manually-Created-Face-Recognition-Model

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

Jupyter Notebook