Advanced Applied Deep Learning

Book Description:

Develop and optimize profound learning versions with advanced architectures. This book teaches you the complex details and subtleties of those algorithms that are at the core of convolutional neural networks.

Along the way, you may look at the basic operations in CNN, such as convolution and pooling, and then look at more innovative architectures like inception networks, resnets, and a lot more. While the book discusses theoretical topics, you will learn how to operate efficiently with Keras with several tricks and tips, such as how to customize logging in Keras with custom callback courses, what’s keen execution, and also how to use it in your models. Finally, you may study how thing detection works, and build a comprehensive implementation of this YOLO (you just look once) algorithm in Keras and TensorFlow. By the end of the book, you will have implemented various models in Keras and learned many innovative tricks that will bring your skills to the next level.

What You Will Learn

• Notice how convolutional neural networks and object detection operate
• Save weights and versions on disc
• Pause training and restart it in a later stage
• Utilize hardware acceleration (GPUs) on your code
• Work with the Dataset TensorFlow abstraction and use pre-trained versions and transfer learning
• Remove and add layers to pre-trained networks to adapt them to your particular project
• Employ pre-trained models like Alexnet and VGG16 to new datasets

Who This Book Is For

Additionally, intermediate knowledge of Keras and TensorFlow is expected.

Download PDF    Buy Hardcopy