Chapter
The hyperbolic tangent function
The Rectified Linear Unit (ReLU)
Artificial neural network (ANN)
Stochastic gradient descent
Playing with TensorFlow playground
Convolutional neural network
Recurrent neural networks (RNN)
Long short-term memory (LSTM)
Deep learning for computer vision
Detection or localization and segmentation
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
Open Computer Vision - OpenCV
TensorFlow example to print Hello, TensorFlow
TensorFlow example for adding two numbers
The TensorFlow Serving tool
Chapter 2: Image Classification
Training the MNIST model in TensorFlow
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
Other popular image testing datasets
The Fashion-MNIST dataset
The ImageNet dataset and competition
The bigger deep learning models
The Google Inception-V3 model
The Microsoft ResNet-50 model
Spatial transformer networks
Training a model for cats versus dogs
Benchmarking with simple CNN
Transfer learning or fine-tuning of a model
Training on bottleneck features
Fine-tuning several layers in deep learning
Developing real-world applications
Tackling the underfitting and overfitting scenarios
Gender and age detection from face
Fine-tuning apparel models
Chapter 3: Image Retrieval
Understanding visual features
Visualizing activation of deep learning models
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
Matching faster using approximate nearest neighbour
Autoencoders of raw images
Denoising using autoencoders
Chapter 4: Object Detection
Detecting objects in an image
COCO object detection challenge
Evaluating datasets using metrics
The mean average precision
Localizing objects using sliding windows
Training a fully connected layer as a convolution layer
Convolution implementation of sliding window
Thinking about localization as a regression problem
Applying regression to other problems
Combining regression with the sliding window
Regions of the convolutional neural network (R-CNN)
Single shot multi-box detector
Re-training object detection models
Data preparation for the Pet dataset
Object detection training pipeline
Monitoring loss and accuracy using TensorBoard
Training a pedestrian detection for a self-driving car
The YOLO object detection algorithm
Chapter 5: Semantic Segmentation
Diagnosing medical images
Understanding the earth from satellite imagery
Algorithms for semantic segmentation
The Fully Convolutional Network
Upsampling the layers by pooling
Sampling the layers by convolution
Skipping connections for better training
Segmenting satellite images
Modeling FCN for segmentation
Chapter 6: Similarity Learning
Algorithms for similarity learning
Visual recommendation systems
Face landmarks and attributes
The Multi-Task Facial Landmark (MTFL) dataset
The Kaggle keypoint dataset
The Multi-Attribute Facial Landmark (MAFL) dataset
Learning the facial key points
The labeled faces in the wild (LFW) dataset
The YouTube faces dataset
The CelebFaces Attributes dataset (CelebA)
Computing the similarity between faces
Finding the optimum threshold
Chapter 7: Image Captioning
Understanding the problem and datasets
Understanding natural language processing for image captioning
Expressing words in vector form
Converting words to vectors
Approaches for image captioning and related problems
Using a condition random field for linking image and text
Using RNN on CNN features to generate captions
Creating captions using image ranking
Retrieving captions from images and images from captions
Using multimodal metric space
Using attention network for captioning
Implementing attention-based image captioning
Chapter 8: Generative Models
Applications of generative models
Predicting the next frame in a video
Super-resolution of images
Interactive image generation
Image to image translation
Creating new animation characters
Neural artistic style transfer
Style loss using the Gram matrix
Generative Adversarial Networks
Chapter 9: Video Classification
Understanding and classifying videos
Exploring video classification datasets
Splitting videos into frames
Approaches for classifying videos
Fusing parallel CNN for video classification
Classifying videos over long periods
Streaming two CNN's for action recognition
Using 3D convolution for temporal learning
Using trajectory for classification
Attending regions for classification
Extending image-based approaches to videos
Regressing the human pose
Tracking facial landmarks
Deployment of models in devices
Other Books You May Enjoy