By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post

managing more than 250 unique labels in a dataset

0

As per the documentation only 250 unique labels are supported in a manifest https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/limits.html. I have a use case to train more than 3000 unique labels using AWS Rekognition.

Question: Should I have to create many training models(in my case 14 models) and search the input image with 14 training models to get the matching custom labels?

Topics
ComputeMachine Learning & AI
Tags
High Performance ComputeMachine Learning & AIAmazon Rekognition
Language
English
sun
asked 20 days ago93 views
1 Answer
0

Hi, Yes your approach is right. You will need to train multiple models to cover the use case of all 3000 labels. 250 unique labels is a hard limit and cannot be increased.

AWS
AWS-user-PoojaR
answered 7 days ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions

Relevant content