Book Image

Python Deep Learning Cookbook

By : Indra den Bakker
Book Image

Python Deep Learning Cookbook

By: Indra den Bakker

Overview of this book

Deep Learning is revolutionizing a wide range of industries. For many applications, deep learning has proven to outperform humans by making faster and more accurate predictions. This book provides a top-down and bottom-up approach to demonstrate deep learning solutions to real-world problems in different areas. These applications include Computer Vision, Natural Language Processing, Time Series, and Robotics. The Python Deep Learning Cookbook presents technical solutions to the issues presented, along with a detailed explanation of the solutions. Furthermore, a discussion on corresponding pros and cons of implementing the proposed solution using one of the popular frameworks like TensorFlow, PyTorch, Keras and CNTK is provided. The book includes recipes that are related to the basic concepts of neural networks. All techniques s, as well as classical networks topologies. The main purpose of this book is to provide Python programmers a detailed list of recipes to apply deep learning to common and not-so-common scenarios.
Table of Contents (21 chapters)
Title Page
About the Author
About the Reviewer
Customer Feedback

Visualizing training with TensorBoard

In the previous chapter, we how to set up TensorBoard with Keras. However, as mentioned, TensorBoard can also be used with TensorFlow (among others). In this recipe, we will show you how to use TensorBoard with TensorFlow when classifying Fashion-MNIST.

How to do it..

  1. Let's start by TensorFlow and a to load mnist datasets, as follows:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
  1. Next, we specify the Fashion MNIST dataset and load it:
mnist = input_data.read_data_sets('Data/fashion', one_hot=True)
  1. Let's create the placeholders for the input data:
n_classes = 10
input_size = 784

x = tf.placeholder(tf.float32, shape=[None, input_size])
y = tf.placeholder(tf.float32, shape=[None, n_classes])
  1. Before we specify our network architecture, we will define a couple of functions we will be using multiple times in our model. We start with a function that creates and initializes the weights:
def weight_variable(shape):