Skip to Content
Hands-On Transfer Learning with Python
book

Hands-On Transfer Learning with Python

by Dipanjan Sarkar, Raghav Bali, Tamoghna Ghosh
August 2018
Intermediate to advanced
438 pages
12h 3m
English
Packt Publishing
Content preview from Hands-On Transfer Learning with Python

Future scope for improvement

There are various ways to improve this model based on the approach we took in this chapter. Here are some of the specific aspects that could be improved upon:

  • Using a better image feature extraction model, such as Google's Inception model
  • Higher-resolution and better-quality training images (needs for GPU power!)
  • More training data based on datasets such as Flickr30K or even image augmentation
  • Introducing attention in models

If you have the necessary data and infrastructure, these are some ideas worth exploring!

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Hands-On Transfer Learning with TensorFlow 2.0

Hands-On Transfer Learning with TensorFlow 2.0

Margaret Maynard-Reid

Publisher Resources

ISBN: 9781788831307Supplemental Content