book

TensorFlow 2.0 Computer Vision Cookbook

Name: TensorFlow 2.0 Computer Vision Cookbook
Author: Jesús Martínez
ISBN: 9781838829131

by Jesús Martínez

February 2021

Intermediate to advanced

542 pages

9h 13m

English

Packt Publishing

Read now

Unlock full access

TensorFlow 2.0 Computer Vision Cookbook
Why subscribe?ContributorsAbout the authorAbout the reviewersPackt is searching for authors like you
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesCode in ActionDownload the color imagesConventions usedSectionsHow to do it…How it works…There’s more…See alsoGet in touchReviews
Chapter 1: Getting Started with TensorFlow 2.x for Computer Vision
Technical requirementsWorking with the basic building blocks of the Keras APIGetting readyHow to do it…How it works…See alsoLoading images using the Keras APIGetting readyHow to do it…How it works…See alsoLoading images using the tf.data.Dataset APIHow to do it…How it works…See alsoSaving and loading a modelHow to do it…How it works…There's more…Visualizing a model's architectureGetting readyHow to do it…How it works…Creating a basic image classifierGetting readyHow to do it…How it works…See also
Chapter 2: Performing Image Classification
Technical requirementsCreating a binary classifier to detect smilesGetting readyHow to do it…How it works…See alsoCreating a multi-class classifier to play rock paper scissorsGetting readyHow to do it…How it works…Creating a multi-label classifier to label watchesGetting readyHow to do it…How it works…See alsoImplementing ResNet from scratchGetting readyHow to do it…How it works…See alsoClassifying images with a pre-trained network using the Keras APIGetting readyHow to do it…How it works…See alsoClassifying images with a pre-trained network using TensorFlow HubGetting readyHow to do it…How it works…See alsoUsing data augmentation to improve performance with the Keras APIGetting readyHow to do it…How it works…See alsoUsing data augmentation to improve performance with the tf.data and tf.image APIsGetting readyHow to do it…How it works…See also
Chapter 3: Harnessing the Power of Pre-Trained Networks with Transfer Learning
Technical requirementsImplementing a feature extractor using a pre-trained networkGetting readyHow to do it…How it works…See alsoTraining a simple classifier on extracted featuresGetting readyHow to do it…How it works…See alsoSpot-checking extractors and classifiers Getting readyHow to do it…How it works…Using incremental learning to train a classifierGetting readyHow to do it…How it works…Fine-tuning a network using the Keras APIGetting readyHow to do it…How it works…See alsoFine-tuning a network using TFHubGetting readyHow to do it…How it works…See also
Chapter 4: Enhancing and Styling Images with DeepDream, Neural Style Transfer, and Image Super-Resolution
Technical requirementsImplementing DeepDreamGetting readyHow to do it…How it works…See alsoGenerating your own dreamy imagesGetting readyHow to do it…How it works…Implementing Neural Style TransferGetting readyHow to do it…How it works…See alsoApplying style transfer to custom imagesGetting readyHow to do it…How it works…See alsoApplying style transfer with TFHubGetting readyHow to do it…How it works…See alsoImproving image resolution with deep learningGetting readyHow to do it…How it works…See also
Chapter 5: Reducing Noise with Autoencoders
Technical requirementsCreating a simple fully connected autoencoderGetting readyHow to do it…How it works…See alsoCreating a convolutional autoencoderGetting readyHow to do it…How it works…See alsoDenoising images with autoencodersGetting readyHow to do it…How it works…Spotting outliers using autoencodersGetting readyHow to do it…How it works…Creating an inverse image search index with deep learningGetting readyHow to do it…How it works…See alsoImplementing a variational autoencoderGetting readyHow to do it…How it works…See also
Chapter 6: Generative Models and Adversarial Attacks
Technical requirementsImplementing a deep convolutional GANGetting readyHow to do it…How it works…See alsoUsing a DCGAN for semi-supervised learningGetting readyHow to do it…How it works…See alsoTranslating images with Pix2PixGetting readyHow to do it…How it works…See alsoTranslating unpaired images with CycleGANGetting readyHow to do it…How it works…See alsoImplementing an adversarial attack using the Fast Gradient Signed MethodGetting readyHow to do itHow it works…See also
Chapter 7: Captioning Images with CNNs and RNNs
Technical requirementsImplementing a reusable image caption feature extractorGetting readyHow to do it…How it works…See alsoImplementing an image captioning networkGetting readyHow to do it…How it works…See alsoGenerating captions for your own photosGetting readyHow to do it…How it works…Implementing an image captioning network on COCO with attentionGetting readyHow to do it…
Chapter 8: Fine-Grained Understanding of Images through Segmentation
Technical requirementsCreating a fully convolutional network for image segmentationGetting readyHow to do it…How it works…See alsoImplementing a U-Net from scratchGetting readyHow to do it…How it works…See alsoImplementing a U-Net with transfer learningGetting readyHow to do it…How it works…See alsoSegmenting images using Mask-RCNN and TensorFlow HubGetting readyHow to do it…How it works…See also

Chapter 9: Localizing Elements in Images with Object Detection
Technical requirementsCreating an object detector with image pyramids and sliding windowsGetting readyHow to do it…How it works…See alsoDetecting objects with YOLOv3Getting readyHow it works…See alsoTraining your own object detector with TensorFlow's Object Detection APIGetting readyHow to do it…How it works…See alsoDetecting objects using TFHubGetting readyHow to do it…How it works…See also
Chapter 10: Applying the Power of Deep Learning to Videos
Technical requirementsDetecting emotions in real timeGetting readyHow to do it…How it works…See alsoRecognizing actions with TensorFlow HubGetting readyHow to do it…How it works…See alsoGenerating the middle frames of a video with TensorFlow HubGetting readyHow to do it…How it works…See alsoPerforming text-to-video retrieval with TensorFlow HubGetting readyHow to do it…How it works…See also
Chapter 11: Streamlining Network Implementation with AutoML
Technical requirementsCreating a simple image classifier with AutoKerasHow to do it…How it works…See alsoCreating a simple image regressor with AutoKerasGetting readyHow to do it…How it works…See alsoExporting and importing a model in AutoKerasHow to do it…How it works…See alsoControlling architecture generation with AutoKeras' AutoModelHow to do it…How it works…See alsoPredicting age and gender with AutoKerasGetting readyHow to do it…How it works…See also
Chapter 12: Boosting Performance
Technical requirementsUsing convolutional neural network ensembles to improve accuracyGetting readyHow to do it…How it works…See alsoUsing test time augmentation to improve accuracyGetting readyHow to do it…How it works…Using rank-N accuracy to evaluate performanceGetting readyHow to do it…How it works…See alsoUsing label smoothing to increase performanceGetting readyHow to do it…How it works…Checkpointing modelHow to do it…Customizing the training process using tf.GradientTapeHow to do it…How it works…Getting readyHow to do it…How it works…See also
Other Books You May Enjoy
Leave a review - let other readers know what you think

Content preview from TensorFlow 2.0 Computer Vision Cookbook

Chapter 3: Harnessing the Power of Pre-Trained Networks with Transfer Learning

Despite the undeniable power deep neural networks bring to computer vision, they are very complex to tune, train, and make performant. This difficulty comes from three main sources:

Deep neural networks start to pay off when we have sufficient data, but more often than not, this is not the case. Furthermore, data is expensive and, sometimes, impossible to expand.
Deep neural networks contain a wide range of parameters that need tuning and can affect the overall performance of the model.
Deep learning is very resource-intensive in terms of time, hardware, and effort.

Do not be dismayed! With transfer learning, we can save ourselves loads of time and effort by leveraging ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Hands-On Computer Vision with TensorFlow 2

Publisher Resources

ISBN: 9781838829131Purchase Link

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

TensorFlow 2.0 Computer Vision Cookbook

by Jesús Martínez

Chapter 3: Harnessing the Power of Pre-Trained Networks with Transfer Learning

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.