CODEWITHSUNDEEP
azureazure-form-recognizer
Madhukar Hiriadka
Madhukar Hiriadka

Reputation: 279

Form Recognizer Labeling - Traning model

I am trying to use Azure Form Recognizer with Labeling tool to train and extract text out of images. As per the documentation:

First, make sure all the training documents are of the same format. If you have forms in multiple formats, organize them into subfolders based on common format. When you train, you'll need to direct the API to a subfolder. (https://learn.microsoft.com/en-us/azure/cognitive-services/form-recognizer/quickstarts/label-tool#set-up-input-data)

In my case I have different formatted images. I can create different projects, label images, train them and get expected output. Challenge in my case is, if I follow this approach I need to create different projects, train it separately and maintain several model ids.

So I just wanted to know is there any way where we can train different formats together as a single training model? Basically I want to know if we can use single model Id to extract key-value pair out of different formatted images?

Upvotes: 1

Views: 1097

Answers (2)

DinF
DinF

Reputation: 1

If these are only a few different types (e.g., 2-4), and they are easily distinguishable, you can also try training them all together. For that to work, though, you'll need to label more files, and results are still likely not going to be as good as separate models.

For trying that, put approximately the same number of images for each type all in same folder, and label altogether.

If there are many different types, this is not likely to work.

Upvotes: 0

ChaZ
ChaZ

Reputation: 179

This is a feature that has been asked for by a few customers. We are working on a solution for this, expecting it to arrive in a few months. For now, we suggest you to train models separately and maintain multiple model IDs.

Upvotes: 1

Related Questions