Название: Deep Learning with TensorFlow and Keras Автор: Derrick Mwiti Издательство: Leanpub Год: 2022-10-03 Страниц: 354 Язык: английский Формат: pdf (true), epub Размер: 39.9 MB
Build Deep Learning applications with Keras and TensorFlow.
Topics covered include Convolutional Neural networks, Recurrent Neural Networks, TensorBoard, Transfer learning, custom training loops, and Keras Functional API.
Deep Learning (DL) is a branch of Machine Learning (ML) that involves building networks that try to mimic the working of the human brain. The dendrite in the human brain represents the input to the network, while the axion terminals represent the output. The cell is where computation would take place before we get the output.
TensorFlow is an open-source Deep Learning framework that enables us to design and train Deep Learning networks. TensorFlow can be installed from the Python Index via the pip command. TensorFlow is already installed on Google Colab. You will, therefore, not install it when working in this environment.
Why TensorFlow? There are a couple of reasons why you would choose TensorFlow: - Has a high-level API that makes it easy to build networks. - Large ecosystem of tools and libraries. - Large community that makes it easy to find solutions to common problems. - Well documented. - Supports deployment of models on the browser, mobile devices, edge devices, and the cloud. - Simple and flexible architecture to make research work faster.
As of TensorFlow 2, Keras is the high-level API for TensorFlow. Keras makes it simple to design and train Deep Learning networks.
What is CNN? A Convolutional Neural Network (CNN) is a special artificial neural network that processes image data and detects complex features from data. CNNs are primarily used in image tasks and in other problems such as natural language processing tasks.