Deep Learning for Computer Vision : Expert techniques to train advanced neural networks using TensorFlow and Keras.

Deep Learning for Computer Vision : Expert techniques to train advanced neural networks using TensorFlow and Keras.

Deep learning has shown its power in several application areas of Artificial Intelligence, especially in Computer Vision, the science of manipulating and processing images. In this book, you will learn different techniques in deep learning to accomplish tasks related to object classification, object...

Full description

Saved in:
Bibliographic Details
Main Author: Shanmugamani, rajalingappaa
Other Authors: Abdul Rahman, Abdul Ghani, Moore, Stephen Maurice, Koganti, Nishanth
Format: eBook
Language:English
Published: Birmingham : Packt Publishing, 2018.
Subjects:
TensorFlow.
Artificial intelligence.
Neural networks (Computer science)
artificial intelligence.
Data capture & analysis.
Pattern recognition.
Computer vision.
Computers > Computer Vision & Pattern Recognition.
Computers > Data Processing.
Computers > Intelligence (AI) & Semantics.
Artificial intelligence
handbooks.
Handbooks and manuals
Handbooks and manuals.
Guides et manuels.
Online Access:Click for online access
Table of Contents:
  • Cover; Copyright and Credits; Packt Upsell; Foreword; Contributors; Table of Contents; Preface; Chapter 1: Getting Started; Understanding deep learning; Perceptron; Activation functions; Sigmoid; The hyperbolic tangent function; The Rectified Linear Unit (ReLU); Artificial neural network (ANN); One-hot encoding; Softmax; Cross-entropy; Dropout; Batch normalization; L1 and L2 regularization; Training neural networks; Backpropagation; Gradient descent; Stochastic gradient descent; Playing with TensorFlow playground; Convolutional neural network; Kernel; Max pooling.
  • Recurrent neural networks (RNN)Long short-term memory (LSTM); Deep learning for computer vision; Classification; Detection or localization and segmentation; Similarity learning; Image captioning; Generative models; Video analysis; Development environment setup; Hardware and Operating Systems
  • OS; General Purpose
  • Graphics Processing Unit (GP-GPU); Computer Unified Device Architecture
  • CUDA; CUDA Deep Neural Network
  • CUDNN; Installing software packages; Python; Open Computer Vision
  • OpenCV; The TensorFlow library; Installing TensorFlow; TensorFlow example to print Hello, TensorFlow.
  • TensorFlow example for adding two numbersTensorBoard; The TensorFlow Serving tool; The Keras library; Summary; Chapter 2: Image Classification; Training the MNIST model in TensorFlow; The MNIST datasets; Loading the MNIST data; Building a perceptron; Defining placeholders for input data and targets; Defining the variables for a fully connected layer; Training the model with data; Building a multilayer convolutional network; Utilizing TensorBoard in deep learning; Training the MNIST model in Keras; Preparing the dataset; Building the model; Other popular image testing datasetsÂ
  • The CIFAR datasetThe Fashion-MNIST dataset; The ImageNet dataset and competition; The bigger deep learning models; The AlexNet model; The VGG-16 model; The Google Inception-V3 model; The Microsoft ResNet-50 model; The SqueezeNet model; Spatial transformer networks; The DenseNet model; Training a model for cats versus dogs; Preparing the data; Benchmarking with simple CNN; Augmenting the dataset; Augmentation techniques ; Transfer learning or fine-tuning of a model; Training on bottleneck features; Fine-tuning several layers in deep learning; Developing real-world applications.
  • Choosing the right modelTackling the underfitting and overfitting scenarios; Gender and age detection from face; Fine-tuning apparel models ; Brand safety; Summary; Chapter 3: Image Retrieval; Understanding visual features; Visualizing activation of deep learning models; Embedding visualization; Guided backpropagation; The DeepDream; Adversarial examples; Model inference; Exporting a model; Serving the trained model ; Content-based image retrieval; Building the retrieval pipeline; Extracting bottleneck features for an image; Computing similarity between query image and target database.

Similar Items