Hands On Computer Vision with TensorFlow 2

Leverage deep learning to create powerful computer vision apps with TensorFlow 2 and Keras.

This repository contains the code for the book Hands On Computer Vision with TensorFlow 2 by Eliot Andres and Benjamin Planche, published by Packt.

More precisely, this repository offers several notebooks to illustrate each of the chapters and their notions, as well as the complete sources for the advanced projects used as examples along the book. Note that this repository is meant to complement the book. Therefore, we suggest to check out its content for more detailed explanations and advanced tips.

🔎 About the Book

Computer vision is achieving a new frontier of capabilities in artificial intelligence including medical screening, self-driving cars and expression detection. TensorFlow is one of the most widely used AI frameworks that leverages deep convolutional neural networks to process complex data. This book explores Google's open source TensorFlow 2 framework along its Keras API, and teaches how to apply them to solving advanced computer vision tasks. It will help you acquire the skills and understand vital concepts to be a part of the extraordinary advances in this domain.

🔧 Technical Requirements

The code is in the form of Jupyter notebooks. Unless specified otherwise, it is running using Python 3.5 (or higher) and TensorFlow 1.10. Installation instructions are presented in the book (we recommend Anaconda to manage the dependencies like numpy, matplotlib, etc.).

📚 Table of Content

• Chapter 1 - Computer Vision and Neural Networks
  • 1.1 - Building and Training a Neural Network from Scratch
• Chapter 2 - Introduction to TensorFlow
  • TBD
• Chapter 3 - Modern Neural Networks
  • 3.1 - Discovering CNNs' Basic Operations
  • 3.2 - Building and Training our First CNN with TensorFlow 2 and Keras
  • 3.3 - Experimenting with Advanced Optimizers
  • 3.4 - Applying Regularization Methods to CNNs
• Chapter 4 - Influential Classification Tools
  • 4.1 - Implementing ResNet from Scratch
  • 4.2 - Reusing Models from Keras Applications
  • 4.3 - Fetching Models from TensorFlow Hub
  • 4.4 - Applying Transfer Learning
  • 4.5 - (Appendix) Exploring ImageNet and Tiny-ImageNet
• Chapter 5
  • TBD
• Chapter 6 - Enhancing and Segmenting Images
  • 6.1 - Discovering Auto-Encoders
  • 6.2 - Denoising with Auto-Encoders
  • 6.3 - Improving Image Quality with Deep Auto-Encoders (Super-Resolution)
  • 6.4 - Preparing Data for Smart Car Applications
  • 6.5 - Building and Training a FCN-8s Model for Semantic Segmentation
  • 6.6 - Building and Training a U-Net Model for Object and Instance Segmentation
  • 6.6 - Object and Instance Segmentation for Smart Cars with U-Net
• Chapter 7 - Training on Complex and Scarce Datasets
  • 7.1 - Setting up Efficient Input Pipelines with tf.data
  • 7.2 - Generating and Parsing TFRecords
  • 7.3 - (TBD) Rendering Images from 3D Models
  • 7.4 - (TBD) Apply Domain Adaptation Methods to Bridge the Realism Gap
  • 7.5 - (TBD) Create Images with Variational Auto-Encoders (VAEs)
  • 7.6 - (TBD) Create Images with Generative-Adversarial Networks (GANs)

📜 Citing

If you use the code samples in your study/work or want to cite the book, please use:

@book{Andres_Planche_HandsOnCVWithTF2,
 author = {Andres, Eliot and Planche, Benjamin},
 title = {Hands-On Computer Vision with TensorFlow 2},
 year = {2019},
 isbn = {TBD},
 publisher = {Packt Publishing},
}

Other Formats: (Click to View)

MLA	Andres, Eliot and Planche Benjamin. Hands-On Computer Vision with TensorFlow 2. Packt Publishing Ltd, 2019.
APA	Andres, E., & Planche B. (2019). Hands-On Computer Vision with TensorFlow 2. Packt Publishing Ltd.
Chicago	Andres, Eliot, and Planche, Benjamin. Hands-On Computer Vision with TensorFlow 2. Packt Publishing Ltd, 2019.
Harvard	Andres, E. and Planche B., 2019. Hands-On Computer Vision with TensorFlow 2. Packt Publishing Ltd.
Vancouver	Andres E, Planche B. Hands-On Computer Vision with TensorFlow 2. Packt Publishing Ltd; 2019.

EndNote RefMan RefWorks