Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Data Science  with Python

You're reading from   Data Science with Python Combine Python with machine learning principles to discover hidden patterns in raw data

Arrow left icon
Product type Paperback
Published in Jul 2019
Publisher Packt
ISBN-13 9781838552862
Length 426 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (3):
Arrow left icon
Rohan Chopra Rohan Chopra
Author Profile Icon Rohan Chopra
Rohan Chopra
Mohamed Noordeen Alaudeen Mohamed Noordeen Alaudeen
Author Profile Icon Mohamed Noordeen Alaudeen
Mohamed Noordeen Alaudeen
Aaron England Aaron England
Author Profile Icon Aaron England
Aaron England
Arrow right icon
View More author details
Toc

Table of Contents (10) Chapters Close

About the Book 1. Introduction to Data Science and Data Pre-Processing FREE CHAPTER 2. Data Visualization 3. Introduction to Machine Learning via Scikit-Learn 4. Dimensionality Reduction and Unsupervised Learning 5. Mastering Structured Data 6. Decoding Images 7. Processing Human Language 8. Tips and Tricks of the Trade 1. Appendix

Images

The digital cameras that we have today store images as a big matrix of numbers. These are what we call digital images. A single number on this matrix refers to a single pixel in the image. Individual numbers refer to the intensity of the color at that pixel. For a grayscale image, these values vary from 0 to 255, where 0 is black and 255 is white. For a colored image, this matrix is three-dimensional, where each dimension has values for red, green, and blue. The values in the matrices refer to the intensities of the respective colors. We use these values as input to our computer vision programs or data science models to perform predictions and recognitions.

Now, there are two ways for us to create machine learning models using these pixels:

  • Input individual pixels as different input variables to the neural network
  • Use a convolutional neural network

Creating a fully connected neural network that takes individual pixel values as input variables is the easiest and the most...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image