fast-facenet-at-oneshot

This repository is an implemantation of siamese network using one shot learning which can be found at Deeplearning.ai on coursera
The implementation is inspired by two path breaking papers on facial recognition using deep convoluted neural network, namely FaceNet and DeepFace.
I have used pre trained model Keras-OpenFace which is an open source Keras implementation of the OpenFace (Originally Torch implemented)

For beginners

• Know about a to z about deep learning here here
• Watch the Convolutional Networks Specialization on Coursera, found here.
• Read all 3 lecture notes under Module 2 for Karpathy CNN course found here
• Watch SirajRaval’s video on CNNs here and here
• Write out a simple CNN yourself (using no ML libraries)

Tools

• Watch CS20 (Tensorflow for DL research). Slides are here. Playlist is here
• Watch Siraj Raval’s intro to tensorflow playlist here
• Read Keras Example code to quickly understand its structure here

For experienced programmers

• Read about one shot learning here and here

Getting started

• capture your facial data from data capture file and after the data has been sucssesfully captured run the facial recognition file.

please do note that this is not the true implementation of inception network,This model has been designed keeping in mind the network architechture of Inception Network

Reaserch papers

• Facebook Deep face

ps: this is a part of a project from Deepleaning.ai Specialization on Convolutional Neural Networks