naemazam / real-time-face-recognition-using-facenet

Real time face recognition Using Facenet , pytorch, Tensorflow

Real time face recognition Using Facenet 🧔 🤖 🔍

Description 📰

A facial recognition system is a technology capable of identifying or verifying a person from a digital image or a video frame from a video source. There are multiples methods in which facial recognition systems work, but in general, they work by comparing selected facial features from given image with faces within a database.

Functionalities added 🕵️‍♂️

1. Using face align functionality from dlib to predict effectively while live streaming.

Python Implementation 👨‍🔬

1. Network Used- Inception Network
2. Original Paper - Facenet by Google
3. Constant Face Location and Acknowledgment - Naem Azam

If you face any problem, kindly raise an issue

File Organization 🗄️

├── Real-time-face-recognition-Using-Facenet (Current Directory)
    ├── encodings
    ├── architecture.py
    ├── detect.py
    ├── facenet_keras_weights.h5
    ├── train_v2.py
    ├── requirements.txt
    ├── Faces
        ├── Azam
        └── winnie
        └── JackieChan
    └── readme.md

Dependencies 💾

This code was working properly on tensroflow 2.3.0.

• Tensorflow 2.X
• numpy
• opencv-python
• mtcnn
• scikit-learn
• scipy

Code Requirements 🦄

You can install Conda for python which resolves all the dependencies for machine learning.

pip install requirements.txt

Menual dependencies install with pip 👨‍🔬

Install python 3.x and Conda

Installing virtualenv

pip install virtualenv

Install TensorFlow in windows

conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0

python3 -m pip install tensorflow

Verify install:

python3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

Install TensorFlow in Linux

conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0

export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/

python3 -m pip install tensorflow

Verify install:

python3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

install opencv-python 4.5.5.64

pip install opencv-python

install scikit-learn

python -m venv sklearn-venv

sklearn-venv\Scripts\activate

pip install -U scikit-learn

install mtcnn 0.1.1

pip install mtcnn

scipy

python -m pip install --user numpy scipy matplotlib ipython jupyter pandas sympy nose

SetUp 🖥️

0. Download facenet_keras_weights.h5 and put it accoding to our file Organization

1. Make a directory of your name inside the Faces folder and upload your 2-3 pictures of you.

2. Train Your System

python train_v2.py

Real time face recognition 🧔 🤖 🔍

Run this for real time Face recognition, it will open your camera and start detection

python detect.py

Results 📊

Thesis 📰

Constant Face Location and Acknowledgment By Naem Azam DOI:10.13140/RG.2.2.35497.2672

References 🔱

• Florian Schroff, Dmitry Kalenichenko, James Philbin (2015). FaceNet: A Unified Embedding for Face Recognition and Clustering
• Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf (2014). DeepFace: Closing the gap to human-level performance in face verification
• The pretrained model we use is inspired by Victor Sy Wang's implementation and was loaded using his code: https://github.com/iwantooxxoox/Keras-OpenFace.
• Our implementation also took a lot of inspiration from the official FaceNet github repository: https://github.com/davidsandberg/facenet

real-time-face-recognition-using-facenet's Issues

Where is file Organization location?

Hi Naem Azam,

In the SetUp on intruction 0:
0. Download facenet_keras_weights.h5 and put it accoding to our file Organization

Where the file organization location actually?, in which location should we put the facenet_keras_weights.h5?

Thanks,
Tri

Where is the requirements.txt file?

Hi Naem Azam, this is one of the best project.

But, I'm looking all of your commit and browse files, but ca't finding the requirements.txt file.
So where do you put that?, have you push the file to this repository?

Thanks,
Tri Nanda

Is it fit for the real world?

Because, When I run this codes it takes 30-40 seconds to start.
And the warning is
WARNING:tensorflow:5 out of the last 118 calls to <function Model.make_predict_function..predict_function at 0x0000017B38050940> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/tutorials/customization/performance#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.

suggest me better way to run this code. Thanks in advance