best practice for document AI

[binary420]

while defining label locations, 

is it better to strictly select the desired data, or is it more beneficial to the AI if you select the desired data, as well as its surrounding data, and then delete the surrounding data in the selection text box?

to be clear i only want the name field,

but wondering whether selecting the entire address and prior headline text and then removing it from in the left text box field is better for learning?

see pics for clarification 

 

[Aris_O]

Welcome back to Google Cloud Community.

I understand that you are getting lot of error for your application. 

I would like to have some more information so that I can investigate further for your issue.

1.) Can you provide me the configuration files (app.yaml, queue.yaml and snippet of the code which causing the error)
2.) What is your application doing ?
3.) Did the same code was working fine before or not ? If yes then did you made any changes in your code ?

Once I have above information in hand. I will be in a better position to help you further. Let me know if you have any other question or concern.

[Aris_O]

Hi @binary420,

Welcome back to Google Cloud Community.

If your documents all have a similar format (for example, a fixed form with very low variation), then fewer documents are required to achieve accuracy. The higher the variation, the more documents are required.

• Here are some reference that might help you.
  
  https://cloud.google.com/document-ai/docs/workbench/training-overview
  
  https://cloud.google.com/document-ai/docs/workbench/train-processor?_ga=2.208094802.-1362987118.1680...
  
  https://cloud.google.com/document-ai/docs/workbench/label-documents?_ga=2.212100308.-1362987118.1680...