liucw2012 / hands-on-computer-vision-with-tensorflow

Hands On Computer Vision with TensorFlow

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

This repository contains the code for the book Hands On Computer Vision with TensorFlow 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 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 - Neural Networks from Scratch
• Chapter 2 - Introduction to TensorFLow
  • TBD
• Chapter 3 - Modern Neural Networks
  • 3.1 - Basic CNN Operations
  • 3.2 - First CNN with TensorFlow
  • 3.3 - Optimizers
  • 3.4 - Regularization
• Chapter 4 - Influential Classification Tools
  • 4.1 - Dataset Preparation
  • 4.2 - ResNet from Scratch
  • 4.3 - ResNet from Keras-App
  • 4.4 - TensorFlow Hub
  • 4.5 - Transfer Learning with Keras
• Chapter 5
  • TBD
• Chapter 6 - Enhancing and Segmenting Images
  • 6.1 - Introduction to Auto-Encoders
  • 6.2 - Denoising with Auto-Encoders
  • 6.3 - Super-Resolution with Deep Auto-Encoders
  • 6.4 - Data Preparation for Smart Car Applications
  • 6.5 - Semantic Segmentation for Smart Cars with FCN-8s
  • 6.6 - Object and Instance Segmentation for Smart Cars with U-Net