Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Python Deep Learning for the Web

You're reading from   Hands-On Python Deep Learning for the Web Integrating neural network architectures to build smart web apps with Flask, Django, and TensorFlow

Arrow left icon
Product type Paperback
Published in May 2020
Publisher Packt
ISBN-13 9781789956085
Length 404 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (2):
Arrow left icon
Sayak Paul Sayak Paul
Author Profile Icon Sayak Paul
Sayak Paul
Anubhav Singh Anubhav Singh
Author Profile Icon Anubhav Singh
Anubhav Singh
Arrow right icon
View More author details
Toc

Table of Contents (19) Chapters Close

Preface Artificial Intelligence on the Web
Demystifying Artificial Intelligence and Fundamentals of Machine Learning FREE CHAPTER Using Deep Learning for Web Development
Getting Started with Deep Learning Using Python Creating Your First Deep Learning Web Application Getting Started with TensorFlow.js Getting Started with Different Deep Learning APIs for Web Development
Deep Learning through APIs Deep Learning on Google Cloud Platform Using Python DL on AWS Using Python: Object Detection and Home Automation Deep Learning on Microsoft Azure Using Python Deep Learning in Production (Intelligent Web Apps)
A General Production Framework for Deep Learning-Enabled Websites Securing Web Apps with Deep Learning DIY - A Web DL Production Environment Creating an E2E Web App Using DL APIs and Customer Support Chatbot Other Books You May Enjoy Appendix: Success Stories and Emerging Areas in Deep Learning on the Web

Improving the deep learning backend

The simple model we have trained here is hardly one that we can claim is close to a perfect model. There are several methods that we can use to extend this model to make it better. For instance, some of the most basic steps that we can take to improve our deep learning model are as follows:

  • Increase training epochs: We have only trained our model for 10 epochs, which is usually a very small value for any deep learning model. Increasing the number of training epochs can improve the accuracy of the model. However, it can also lead to overfitting and so the number of epochs must be experimented with.
  • More training samples: Our web client currently doesn't do much more than show the predicted value. However, we could extend it to get feedback from the user on whether the prediction we made was correct. We can then add the user's input...
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 R$50/month. Cancel anytime