Repository files navigation

I have worked all my life in Machine Learning, andI've never seen one algorithm knock over its benchmarks like Deep Learning - Andrew Ng

This repository includes deep learning based project implementations I've done from scratch. You can find both the source code and documentation as a step by step tutorial. Model structrues and pre-trained weights are shared as well.

Facial Expression RecognitionCode,Tutorial

This is a custom CNN model. KaggleFER 2013 data set is fed to the model. This model runs fast and produces satisfactory results. It can be also run real time as well.

We can run emotion analysis in real time as wellReal Time Code,Video

Face RecognitionCode,Tutorial

Face recognition is mainly based on convolutional neural networks. We feed two face images to a CNN model and it returns a multi-dimensional vector representations. We then compare these representations to determine these two face images are same person or not.

You can find the most popular face recognition models below.

All of those state-of-the-art face recognition models are wrapped indeepface library for python. You can build and run them with a few lines of code. To have more information, please visit therepo of the library.

Real Time Deep Face Recognition ImplementationCode,Video

These are the real time implementations of the common face recognition models we've mentioned in the previous section. VGG-Face has the highest face recognition score but it comes with the high complexity among models. On the other hand, OpenFace is a pretty model and it has a close accuracy to VGG-Face but its simplicity offers high speed than others.

Large Scale Face Recognition

Face recognition requires to apply face verification several times. It has a O(n) time complexity and it would be problematic for very large scale data sets (millions or billions level data). Herein, if you have a really strong database, then you use relational databases and regular SQL. Besides, you can store facial embeddings in nosql databases. In this way, you can have the power of the map reduce technology. Besides, approximate nearest neighbor (a-nn) algorithm reduces time complexity dramatically. Spotify Annoy, Facebook Faiss and NMSLIB are amazing a-nn libraries. Besides, Elasticsearch wraps NMSLIB and it also offers highly scalablity. You should build and run face recognition models within those a-nn libraries if you have really large scale data sets.

Apparent Age and Gender PredictionTutorial,Code for age,Code for gender

We've used VGG-Face model for apparent age prediction this time. We actually applied transfer learning. Locking the early layers' weights enables to have outcomes fast.

We can run age and gender prediction in real time as wellReal Time Code,Video

Celebrity You Look-Alike Face RecognitionCode,Tutorial

Applying VGG-Face recognition technology forimdb data set will find your celebrity look-alike if you discard the threshold in similarity score.

This can be run in real time as wellReal Time Code,Video

Race and Ethnicity PredictionTutorial,Code,Real Time Code,Video

Ethnicity is a facial attribute as well and we can predict it from facial photos. We customize VGG-Face and we also applied transfer learning to classify 6 different ethnicity groups.

Beauty Score PredictionTutorial,Code

South China University of Technology published a research paper about facial beauty prediction. They alsoopen-sourced the data set. 60 labelers scored the beauty of 5500 people. We will build a regressor to find facial beauty score. We will also test the built regressor on a huge imdb data set to find the most beautiful ones.

Attractiveness Score PredictionTutorial,Code

The University of Chicago open-sourced the Chicago Face Database. The database consists of 1200 facial photos of 600 people. Facial photos are also labeled with attractiveness and babyface scores by hundreds of volunteer markers. So, we've built a machine learning model to generalize attractiveness score based on a facial photo.

Making Arts with Deep Learning: Artistic Style TransferCode,Tutorial,Video

What if Vincent van Gogh had painted Istanbul Bosporus? Today we can answer this question. A deep learning technique namedartistic style transfer enables to transform ordinary images to masterpieces.

Autoencoder and clusteringCode,Tutorial

We can use neural networks to represent data. If you design a neural networks model symmetric about the centroid and you can restore a base data with an acceptable loss, then output of the centroid layer can represent the base data. Representations can contribute any field of deep learning such as face recognition, style transfer or just clustering.

Convolutional Autoencoder and clusteringCode,Tutorial

We can adapt same representation approach to convolutional neural networks, too.

Transfer Learning: Consuming InceptionV3 to Classify Cat and Dog Images in KerasCode,Tutorial

We can have the outcomes of the other researchers effortlessly. Google researchers compete on Kaggle Imagenet competition. They got 97% accuracy. We will adapt Google's Inception V3 model to classify objects.

Handwritten Digit Classification Using Neural NetworksCode,Tutorial

We had to apply feature extraction on data sets to use neural networks. Deep learning enables to skip this step. We just feed the data, and deep neural networks can extract features on the data set. Here, we will feed handwritten digit data (MNIST) to deep neural networks, and expect to learn digits.

Handwritten Digit Recognition Using Convolutional Neural Networks with KerasCode,Tutorial

Convolutional neural networks are close to human brain. People look for some patterns in classifying objects. For example, mouth, nose and ear shape of a cat is enough to classify a cat. We don't look at all pixels, just focus on some area. Herein, CNN applies some filters to detect these kind of shapes. They perform better than conventional neural networks. Herein, we got almost 2% accuracy than fully connected neural networks.

Automated Machine Learning and Auto-Keras for Image DataCode,Model,Tutorial

AutoML concept aims to find the best network structure and hyper-parameters. Here, I've applied AutoML to facial expression recognition data set. My custom design got 57% accuracy whereas AutoML found a better model and got 66% accuracy. This means almost 10% improvement in the accuracy.

Explaining Deep Learning Models with SHAPCode,Tutorial

SHAP explains black box machine learning models and makes them transparent, explainable and provable.

Gradient Vanishing ProblemCodeTutorial

Why legacy activation functions such as sigmoid and tanh disappear on the pages of the history?

How single layer perceptron worksCode

This is the 1957 model implementation of the perceptron.

Face Alignment for Face RecognitionCode,Tutorial

Google declared that face alignment increase its face recognition model accuracy from 98.87% to 99.63%. This is almost 1% accuracy improvement which means a lot for engineering studies.

I have tested this repository on the following environments. To avoid environmental issues, confirm your environment is same as below.

C:\>python --versionPython 3.6.4 :: Anaconda, Inc.C:\>activate tensorflow(tensorflow) C:\>pythonPython 3.5.5 |Anaconda, Inc.| (default, Apr  7 2018, 04:52:34) [MSC v.1900 64 bit (AMD64)] on win32Type "help", "copyright", "credits" or "license" for more information.>>> import tensorflow as tf>>> print(tf.__version__)1.9.0>>>>>> import kerasUsing TensorFlow backend.>>> print(keras.__version__)2.2.0>>>>>> import cv2>>> print(cv2.__version__)3.4.4

To get your environment up from zero, you can follow the instructions in the following videos.

Installing TensorFlow and PrerequisitesVideo

Installing KerasVideo

This repo might use some external sources. Notice that related tutorial links and comments in the code blocks cite references already.

There are many ways to support a project - starring⭐️ the GitHub repos is one 🙏

You can also support this work onPatreon,GitHub Sponsors orBuy Me a Coffee.

Please cite tensorflow-101 in your publications if it helps your research. Here is an example BibTeX entry:

@misc{serengil2021tensorflow,abstract     ={TensorFlow 101: Introduction to Deep Learning for Python Within TensorFlow},author       ={Serengil, Sefik Ilkin},title        ={tensorflow-101},howpublished ={https://github.com/serengil/tensorflow-101},year         ={2021}}

This repository is licensed under MIT license - seeLICENSE for more details