• Post Reply Bookmark Topic Watch Topic
  • New Topic
programming forums Java Mobile Certification Databases Caching Books Engineering Micro Controllers OS Languages Paradigms IDEs Build Tools Frameworks Application Servers Open Source This Site Careers Other all forums
this forum made possible by our volunteer staff, including ...
Marshals:
  • Campbell Ritchie
  • Paul Clapham
  • Ron McLeod
  • Liutauras Vilda
  • Bear Bibeault
Sheriffs:
  • Jeanne Boyarsky
  • Tim Cooke
  • Devaka Cooray
Saloon Keepers:
  • Tim Moores
  • Tim Holloway
  • Piet Souris
  • salvin francis
  • Stephan van Hulst
Bartenders:
  • Frits Walraven
  • Carey Brown
  • Jj Roberts

TensorFlow 2.0 in Action: Minimum Number of Examples For Training

 
Ranch Hand
Posts: 35
  • Mark post as helpful
  • send pies
  • Quote
  • Report post to moderator
Hi Thushan.

This is probably my last question...

In practice what is the lower limit for the number of times a label has been applied in the training set that makes it viable in a multi-label project?

For example in a situation where we are labelling pictures, if we have say 1 million training examples of animals, most will be labelled as dogs, cats, puppies and kittens. A few will be horses, cows and sheep. Even fewer will be elephants, tigers or rhinos. When we get down to camelopards, there may only be 5 out of the million pictures. Is there any way we could train TensorFlow with the camelopard label, or do we just have to ignore it?
What would a sensible threshold be? 10 examples? 100 examples? Should we think more as a percentage, so any label that has been applied to less than 1% of the pictures is not going to be trainable?


Thanks
Don.
 
If tomatoes are a fruit, then ketchup must be a jam. Taste this tiny ad:
Building a Better World in your Backyard by Paul Wheaton and Shawn Klassen-Koop
https://coderanch.com/wiki/718759/books/Building-World-Backyard-Paul-Wheaton
reply
    Bookmark Topic Watch Topic
  • New Topic