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

Analyzing network weights and more

In the previous recipe, we focused on the loss and metric. However, with TensorBoard, you can also keep track of the weights. Taking a closer look at the weights can help in understanding how your model works and learns. 

How to do it...

  1. We start by TensorFlow, as follows:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
  1. Now, we will be able to load the Fashion-MNIST dataset with just one line of code:
mnist = input_data.read_data_sets('Data/fashion', one_hot=True)
  1. Before proceeding, we need to set the placeholders for our model:
n_classes = 10
input_size = 784

x = tf.placeholder(tf.float32, shape=[None, input_size])
y = tf.placeholder(tf.float32, shape=[None, n_classes])
keep_prob = tf.placeholder(tf.float32)
  1. We define four functions that will help us build our network architecture:
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):