Book Image

TensorFlow 2.0 Computer Vision Cookbook

By : Jesús Martínez
Book Image

TensorFlow 2.0 Computer Vision Cookbook

By: Jesús Martínez

Overview of this book

Computer vision is a scientific field that enables machines to identify and process digital images and videos. This book focuses on independent recipes to help you perform various computer vision tasks using TensorFlow. The book begins by taking you through the basics of deep learning for computer vision, along with covering TensorFlow 2.x’s key features, such as the Keras and tf.data.Dataset APIs. You’ll then learn about the ins and outs of common computer vision tasks, such as image classification, transfer learning, image enhancing and styling, and object detection. The book also covers autoencoders in domains such as inverse image search indexes and image denoising, while offering insights into various architectures used in the recipes, such as convolutional neural networks (CNNs), region-based CNNs (R-CNNs), VGGNet, and You Only Look Once (YOLO). Moving on, you’ll discover tips and tricks to solve any problems faced while building various computer vision applications. Finally, you’ll delve into more advanced topics such as Generative Adversarial Networks (GANs), video processing, and AutoML, concluding with a section focused on techniques to help you boost the performance of your networks. By the end of this TensorFlow book, you’ll be able to confidently tackle a wide range of computer vision problems using TensorFlow 2.x.

Related Content you might be interested in

Current Title:

Small book image
TensorFlow 2.0 Computer Vision Cookbook
Jesús Martínez
Feb, 2021 | 542 pages
Small book image
Python Deep Learning Cookbook
Indra den Bakker
Oct, 2017 | 330 pages
Small book image
TensorFlow 2.0 Quick Start Guide
Tony Holdroyd
Mar, 2019 | 196 pages
Small book image
The TensorFlow Workshop
Matthew Moocarme | Abhranshu Bagchi | Anthony So | Anthony Maddalone
Dec, 2021 | 600 pages
Table of Contents (14 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Code in Action
Download the color images
Conventions used
Sections
Get in touch
Reviews
1
Chapter 1: Getting Started with TensorFlow 2.x for Computer Vision
Chapter 1: Getting Started with TensorFlow 2.x for Computer Vision
Technical requirements
Working with the basic building blocks of the Keras API
Loading images using the Keras API
Loading images using the tf.data.Dataset API
Saving and loading a model
Visualizing a model's architecture
Creating a basic image classifier
Free Chapter
2
Chapter 2: Performing Image Classification
Chapter 2: Performing Image Classification
Technical requirements
Creating a binary classifier to detect smiles
Creating a multi-class classifier to play rock paper scissors
Creating a multi-label classifier to label watches
Implementing ResNet from scratch
Classifying images with a pre-trained network using the Keras API
Classifying images with a pre-trained network using TensorFlow Hub
Using data augmentation to improve performance with the Keras API
Using data augmentation to improve performance with the tf.data and tf.image APIs
3
Chapter 3: Harnessing the Power of Pre-Trained Networks with Transfer Learning
Chapter 3: Harnessing the Power of Pre-Trained Networks with Transfer Learning
Technical requirements
Implementing a feature extractor using a pre-trained network
Training a simple classifier on extracted features
Spot-checking extractors and classifiers
Using incremental learning to train a classifier
Fine-tuning a network using the Keras API
Fine-tuning a network using TFHub
4
Chapter 4: Enhancing and Styling Images with DeepDream, Neural Style Transfer, and Image Super-Resolution
Chapter 4: Enhancing and Styling Images with DeepDream, Neural Style Transfer, and Image Super-Resolution
Technical requirements
Implementing DeepDream
Generating your own dreamy images
Implementing Neural Style Transfer
Applying style transfer to custom images
Applying style transfer with TFHub
Improving image resolution with deep learning
5
Chapter 5: Reducing Noise with Autoencoders
Chapter 5: Reducing Noise with Autoencoders
Technical requirements
Creating a simple fully connected autoencoder
Creating a convolutional autoencoder
Denoising images with autoencoders
Spotting outliers using autoencoders
Creating an inverse image search index with deep learning
Implementing a variational autoencoder
6
Chapter 6: Generative Models and Adversarial Attacks
Chapter 6: Generative Models and Adversarial Attacks
Technical requirements
Implementing a deep convolutional GAN
Using a DCGAN for semi-supervised learning
Translating images with Pix2Pix
Translating unpaired images with CycleGAN
Implementing an adversarial attack using the Fast Gradient Signed Method
7
Chapter 7: Captioning Images with CNNs and RNNs
Chapter 7: Captioning Images with CNNs and RNNs
Technical requirements
Implementing a reusable image caption feature extractor
Implementing an image captioning network
Generating captions for your own photos
Implementing an image captioning network on COCO with attention
8
Chapter 8: Fine-Grained Understanding of Images through Segmentation
Chapter 8: Fine-Grained Understanding of Images through Segmentation
Technical requirements
Creating a fully convolutional network for image segmentation
Implementing a U-Net from scratch
Implementing a U-Net with transfer learning
Segmenting images using Mask-RCNN and TensorFlow Hub
9
Chapter 9: Localizing Elements in Images with Object Detection
Chapter 9: Localizing Elements in Images with Object Detection
Technical requirements
Creating an object detector with image pyramids and sliding windows
Detecting objects with YOLOv3
Training your own object detector with TensorFlow's Object Detection API
Detecting objects using TFHub
10
Chapter 10: Applying the Power of Deep Learning to Videos
Chapter 10: Applying the Power of Deep Learning to Videos
Technical requirements
Detecting emotions in real time
Recognizing actions with TensorFlow Hub
Generating the middle frames of a video with TensorFlow Hub
Performing text-to-video retrieval with TensorFlow Hub
11
Chapter 11: Streamlining Network Implementation with AutoML
Chapter 11: Streamlining Network Implementation with AutoML
Technical requirements
Creating a simple image classifier with AutoKeras
Creating a simple image regressor with AutoKeras
Exporting and importing a model in AutoKeras
Controlling architecture generation with AutoKeras' AutoModel
Predicting age and gender with AutoKeras
12
Chapter 12: Boosting Performance
Chapter 12: Boosting Performance
Technical requirements
Using convolutional neural network ensembles to improve accuracy
Using test time augmentation to improve accuracy
Using rank-N accuracy to evaluate performance
Using label smoothing to increase performance
Checkpointing model
Customizing the training process using tf.GradientTape
13
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Loading images using the Keras API

In this recipe, we will learn how to load images using the Keras API, a very important task considering that, in computer vision, we'll always work with visual data. In particular, we'll learn how to open, explore, and visualize a single image, as well as a batch of them. Additionally, we will learn how to programmatically download a dataset.

Getting ready

Keras relies on the Pillow library to manipulate images. You can install it easily using pip:

$> pip install Pillow

Let's get started!

How to do it…

Now, let's begin this recipe:

  1. Import the necessary packages:
    import glob
import os
import tarfile
import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing.image 
import load_img, img_to_array
from tensorflow.keras.utils import get_file
  2. Define the URL and destination of the CINIC-10 dataset, an alternative to the famous...
Previous Section
End of Section 4
Next Section