Book Image

The Deep Learning Workshop

By : Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So
Book Image

The Deep Learning Workshop

By: Mirza Rahim Baig, Thomas V. Joseph, Nipun Sadvilkar, Mohan Kumar Silaparasetty, Anthony So

Overview of this book

Are you fascinated by how deep learning powers intelligent applications such as self-driving cars, virtual assistants, facial recognition devices, and chatbots to process data and solve complex problems? Whether you are familiar with machine learning or are new to this domain, The Deep Learning Workshop will make it easy for you to understand deep learning with the help of interesting examples and exercises throughout. The book starts by highlighting the relationship between deep learning, machine learning, and artificial intelligence and helps you get comfortable with the TensorFlow 2.0 programming structure using hands-on exercises. You’ll understand neural networks, the structure of a perceptron, and how to use TensorFlow to create and train models. The book will then let you explore the fundamentals of computer vision by performing image recognition exercises with convolutional neural networks (CNNs) using Keras. As you advance, you’ll be able to make your model more powerful by implementing text embedding and sequencing the data using popular deep learning solutions. Finally, you’ll get to grips with bidirectional recurrent neural networks (RNNs) and build generative adversarial networks (GANs) for image synthesis. By the end of this deep learning book, you’ll have learned the skills essential for building deep learning models with TensorFlow and Keras.
Table of Contents (9 chapters)

Saving and Restoring Models

In the previous section, we learned how we can use data augmentation to generate different variants of an image. This will increase the size of the dataset but will also help the model train on a wider variety of images and help it generalize better.

Once you've trained your model, you will most likely want to deploy it in production and use it to make live predictions. To do so, you will need to save your model as a file. This file can then be loaded by your prediction service so that it can be used as an API or data science tool.

There are different components of a model that can be saved:

  • The model's architecture with all the network and layers used
  • The model's trained weights
  • The training configuration with the loss function, optimizer, and metrics

In TensorFlow, you can save the entire model or each of these components separately. Let's learn how to do this.

Saving the Entire Model

To save all the...