Chapter 1, TensorFlow 101, recaps the basics of TensorFlow, such as how to create tensors, constants, variables, placeholders, and operations. We learn about computation graphs and how to place computation graph nodes on various devices such as GPU. We also learn how to use TensorBoard to visualize various intermediate and final output values.
Chapter 2, High-Level Libraries for TensorFLow, covers several high-level libraries such as TF Contrib Learn, TF Slim, TFLearn, Sonnet, and Pretty Tensor.
Chapter 3, Keras 101, gives a detailed overview of the high-level library Keras, which is now part of the TensorFlow core.
Chapter 4, Classical Machine Learning with TensorFlow, teaches us to use TensorFlow to implement classical machine learning algorithms, such as linear regression and classification with logistic regression.
Chapter 5, Neural Networks and MLP with TensorFlow and Keras, introduces the concept of neural networks and shows how to build simple neural network models. We also cover how to build deep neural network models known as MultiLayer Perceptrons.
Chapter 6, RNNs with TensorFlow and Keras, covers how to build Recurrent Neural Networks with TensorFlow and Keras. We cover the internal architecture of RNN, Long Short-Term Networks (LSTM), and Gated Recurrent Units (GRU). We provide a brief overview of the API functions and classes provided by TensorFlow and Keras to implement RNN models.
Chapter 7, RNN for Time Series Data with TensorFlow and Keras, shows how to build and train RNN models for time series data and provide examples in TensorFlow and Keras libraries.
Chapter 8, RNN for Text Data with TensorFlow and Keras, teaches us how to build and train RNN models for text data and provides examples in TensorFlow and Keras libraries. We learn to build word vectors and embeddings with TensorFlow and Keras, followed by LSTM models for using embeddings to generate text from sample text data.
Chapter 9, CNN with TensorFlow and Keras, covers CNN models for image data and provides examples in TensorFlow and Keras libraries. We implement the LeNet architecture pattern for our example.
Chapter 10, Autoencoder with TensorFlow and Keras, illustrates the Autoencoder models for image data and again provides examples in TensorFlow and Keras libraries. We show the implementation of Simple Autoencoder, Denoising Autoencoder, and Variational Autoencoders.
Chapter 11, TensorFlow Models in Production with TF Serving, teaches us to deploy the models with TensorFlow Serving. We learn how to deploy using TF Serving in Docker containers and Kubernetes clusters.
Chapter 12, Transfer Learning and Pre-Trained Models, shows the use of pretrained models for predictions. We learn how to retrain the models on a different dataset. We provide examples to apply the VGG16 and Inception V3 models, pretrained on the ImageNet dataset, to predict images in the COCO dataset. We also show examples of retraining only the last layer of the models with the COCO dataset to improve the predictions.
Chapter 13, Deep Reinforcement Learning, covers reinforcement learning and the OpenAI gym. We build and train several models using various reinforcement learning strategies, including deep Q networks.
Chapter 14, Generative Adversarial Networks, shows how to build and train generative adversarial models in TensorFLow and Keras. We provide examples of SimpleGAN and DCGAN.
Chapter 15, Distributed Models with TensorFlow Clusters, covers distributed training for TensorFLow models using TensorFLow clusters. We provide examples of asynchronous and synchronous update methods for training models in data-parallel fashion.
Chapter 16, TensorFlow Models on Mobile and Embedded Platforms, shows how to deploy TensorFlow models on mobile devices running on iOS and Android platforms. We cover both TF Mobile and TF Lite APIs of the TensorFlow Library.
Chapter 17, TensorFlow and Keras in R, covers how to build and train TensorFlow models in R statistical software. We learn about the three packages provided by R Studio that implement the TF Core, TF Estimators, and Keras API in R.
Chapter 18, Debugging TensorFlow Models, tells us strategies and techniques to find problem hotspots when the models do not work as expected. We cover TensorFlow debugger, along with other methods.
Appendix, Tensor Processing Units, gives a brief overview of Tensor Processing Units. TPUs are futuristic platforms optimized to train and run TensorFlow models. Although not widely available yet, they are available on the Google Cloud Platform and slated to be available soon outside the GCP.
