book

TensorFlow 2.0 Computer Vision Cookbook

by Jesús Martínez

February 2021

Intermediate to advanced

542 pages

9h 13m

English

Packt Publishing

Read now

Unlock full access

Why subscribe?ContributorsAbout the authorAbout the reviewersPackt is searching for authors like you
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
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
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
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
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
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
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
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…
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

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
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
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
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
Leave a review - let other readers know what you think

Overview

Unlock the full potential of computer vision with TensorFlow 2.0 in "TensorFlow 2.0 Computer Vision Cookbook." This comprehensive guide offers practical recipes for tackling various computer vision challenges. Covering everything from basic image classification to advanced generative adversarial networks, you'll master techniques to transform your digital vision tasks.

What this Book will help me do

Learn to train and fine-tune object detection models like YOLOv3 for precise identification.
Use TensorFlow features to analyze digital images for tasks such as age and gender prediction through AutoML.
Implement image segmentation and classification using state-of-the-art deep learning approaches.
Explore generative adversarial networks (GANs) for creating and enhancing image content.
Gain advanced skills in video analysis and real-time processing of digital visual data.

Author(s)

The book, authored by None Martínez, brings valuable insights from an expert well-versed in both TensorFlow and computer vision. With a dedication to teaching and hands-on practices, None shares their expertise through a rich collection of practical recipes. The author's commitment to a structured learning approach ensures users can easily follow and implement the presented solutions.

Who is it for?

This book is aimed at computer vision engineers, deep learning enthusiasts, and professional developers working with digital visual content. It caters to readers familiar with Python who seek to deepen their understanding of TensorFlow for visual processing tasks. Whether you're streamlining existing workflows or stepping into advanced concepts, this book caters to your needs.