#DevFest
Organized By
GDG Beja
Introduction to tensorflow
Hello!
I am Rebai Ahmed
I am here because I love to give presentations && I love Tensorflow
Check out my portfolio rebai.ahmed.github.io
2
Plan
3
➢ Introduction
➢ What is Tensorflow ?
➢ Why Tensorflow ?
➢ Cool Projects with Tensorflow ?
Quick Questions
➢ How many people have heard about tensorflow ?
➢ How many people know about tensorflow ?
➢ How many people are using tensorflow ?
4
1. Introduction
Artificial Intelligence, deep learning, machine learning — 
whatever you’re doing if you don’t understand it — learn it.
Because otherwise you’re going to be a dinosaur within 3 years.
Mark Cuban
Introduction : What is Machine learning ?
★ Subfield of Artificial Intelligence (AI) gives "computers the ability to
learn without being explicitly programmed"
★ Machine learning is preferred approach to :
➢ Weather prediction
➢ Recommendation systems
➢ Spam Filtering
7
Introduction : What is Machine learning (2) ?
8
Introduction : What is Deep Learning ?
Deep Learning is a subfield of Machine
learning concerned with algorithms inspired by
the structure and the function of the brain called
artificial neural network.
9
Introduction : What is Deep Learning ?
➢ Our brain has lots of neurons connected
together and the strength of
the connections between neurons
represents long term knowledge.
Neurons in the brain
10
Introduction : What is Deep Learning ?
Neural Network (Deep Learning)
11
Introduction : Deep learning Why Now ?
12
Introduction : Deep learning Why Now ?
➢ Big DATA
➢ big processing power
➢ GPU
➢ The Cloud
➢ robust neural networks
13
Tools
2. What is TensorFlow ?
● TensorFlow is an open-source library for Deep Learning and Machine learning
● Developed by the Google Brain team and released in November 2015
● TensorFlow is mainly used for: Classification, Perception, Understanding,
Discovering, Prediction and Creation
14
More in Tensorflow:
Machine learning in Javascript
15
More in Tensorflow:
➢ It possible to add machine learning capabilities to any web application
➢ You can use the APIs to build and train models right in the browser or in
your Node.js server application
➢ You can use TensorFlow.js to run existing models in your JavaScript
environment.
16
Why Tensorflow ?
3. Why Tensorflow ?
18
3. Why Tensorflow ?
19
➢ PyTorch
➢ Caffe
➢ Theano (Keras, Lasagne)
➢ DL4J
➢ Apache Mxnet
There are other alternatives
20
Why TensorFlow : Runs Everywhere
Runs on desktop and mobile devices such as
● Linux
● macOS
● iOS
● Android
● Raspberry pi
● And Windows
21
Why TensorFlow: Parallel Computation
TensorFlow supports distributed computing
22
Why TensorFlow :Google products
● It powers many of Google’s large-scale services, such as
○ Google Cloud Speech
○ Google Photos and
○ Google Search
23
Why TensorFlow : Large community
● One the the most popular open source projects
on GitHub
● It has a dedicated team of passionate and
helpful developers
● Growing community contributing to improve it
24
Why TensorFlow : Big Companies using
Tensorflow
● Google
● OpenAI
● DeepMind
● Uber
● eBay
● DropBox
● A bunch of startups
Cool Projects with
Tensorflow
Cool Projects with Tensorflow
Project1 : Image Classification
26
Cool Projects with Tensorflow
Project 2: Object Detection
27
Cool Projects with Tensorflow
Project 3: Speech recognition
28
Cool Projects with Tensorflow
Project 4: Deep learning driven jazz generation
29
Cool Projects with Tensorflow
Project 5: Restore colors in B&W photos and videos
30
Cool Projects with Tensorflow
Project 6: Transferring style from famous paintings
31
Ressources
32
➢ TensorFlow tutorials
➢ quora.com/topic/TensorFlow-software-library
➢ Machine learning crash course
➢ Your first TensorFlow programming with Jupyter
➢ TensorFlow Dev-Summit 2018
33
Thanks!
Any questions?
👍👉👍😉
You can find me at rebai.ahmed@outlook.com

Dev fest GDG beja tensorflow presenatation

  • 1.
  • 2.
    Hello! I am RebaiAhmed I am here because I love to give presentations && I love Tensorflow Check out my portfolio rebai.ahmed.github.io 2
  • 3.
    Plan 3 ➢ Introduction ➢ Whatis Tensorflow ? ➢ Why Tensorflow ? ➢ Cool Projects with Tensorflow ?
  • 4.
    Quick Questions ➢ Howmany people have heard about tensorflow ? ➢ How many people know about tensorflow ? ➢ How many people are using tensorflow ? 4
  • 5.
    1. Introduction Artificial Intelligence,deep learning, machine learning —  whatever you’re doing if you don’t understand it — learn it. Because otherwise you’re going to be a dinosaur within 3 years. Mark Cuban
  • 6.
    Introduction : Whatis Machine learning ?
  • 7.
    ★ Subfield ofArtificial Intelligence (AI) gives "computers the ability to learn without being explicitly programmed" ★ Machine learning is preferred approach to : ➢ Weather prediction ➢ Recommendation systems ➢ Spam Filtering 7 Introduction : What is Machine learning (2) ?
  • 8.
    8 Introduction : Whatis Deep Learning ? Deep Learning is a subfield of Machine learning concerned with algorithms inspired by the structure and the function of the brain called artificial neural network.
  • 9.
    9 Introduction : Whatis Deep Learning ? ➢ Our brain has lots of neurons connected together and the strength of the connections between neurons represents long term knowledge. Neurons in the brain
  • 10.
    10 Introduction : Whatis Deep Learning ? Neural Network (Deep Learning)
  • 11.
    11 Introduction : Deeplearning Why Now ?
  • 12.
    12 Introduction : Deeplearning Why Now ? ➢ Big DATA ➢ big processing power ➢ GPU ➢ The Cloud ➢ robust neural networks
  • 13.
  • 14.
    2. What isTensorFlow ? ● TensorFlow is an open-source library for Deep Learning and Machine learning ● Developed by the Google Brain team and released in November 2015 ● TensorFlow is mainly used for: Classification, Perception, Understanding, Discovering, Prediction and Creation 14
  • 15.
    More in Tensorflow: Machinelearning in Javascript 15
  • 16.
    More in Tensorflow: ➢It possible to add machine learning capabilities to any web application ➢ You can use the APIs to build and train models right in the browser or in your Node.js server application ➢ You can use TensorFlow.js to run existing models in your JavaScript environment. 16
  • 17.
  • 18.
  • 19.
    3. Why Tensorflow? 19 ➢ PyTorch ➢ Caffe ➢ Theano (Keras, Lasagne) ➢ DL4J ➢ Apache Mxnet There are other alternatives
  • 20.
    20 Why TensorFlow :Runs Everywhere Runs on desktop and mobile devices such as ● Linux ● macOS ● iOS ● Android ● Raspberry pi ● And Windows
  • 21.
    21 Why TensorFlow: ParallelComputation TensorFlow supports distributed computing
  • 22.
    22 Why TensorFlow :Googleproducts ● It powers many of Google’s large-scale services, such as ○ Google Cloud Speech ○ Google Photos and ○ Google Search
  • 23.
    23 Why TensorFlow :Large community ● One the the most popular open source projects on GitHub ● It has a dedicated team of passionate and helpful developers ● Growing community contributing to improve it
  • 24.
    24 Why TensorFlow :Big Companies using Tensorflow ● Google ● OpenAI ● DeepMind ● Uber ● eBay ● DropBox ● A bunch of startups
  • 25.
  • 26.
    Cool Projects withTensorflow Project1 : Image Classification 26
  • 27.
    Cool Projects withTensorflow Project 2: Object Detection 27
  • 28.
    Cool Projects withTensorflow Project 3: Speech recognition 28
  • 29.
    Cool Projects withTensorflow Project 4: Deep learning driven jazz generation 29
  • 30.
    Cool Projects withTensorflow Project 5: Restore colors in B&W photos and videos 30
  • 31.
    Cool Projects withTensorflow Project 6: Transferring style from famous paintings 31
  • 32.
    Ressources 32 ➢ TensorFlow tutorials ➢quora.com/topic/TensorFlow-software-library ➢ Machine learning crash course ➢ Your first TensorFlow programming with Jupyter ➢ TensorFlow Dev-Summit 2018
  • 33.
    33 Thanks! Any questions? 👍👉👍😉 You canfind me at rebai.ahmed@outlook.com