Form Recognizer
-
How can we improve the accuracy of the form-recognizer model?
I am using Microsoft form-recognizer service. My forms are bit complex and I tried training a model for them. The performance I achieved is not really good. Is there anyway I can improve this accuracy? Is there anyway to tune this model? I have trained the model using 5 different populated forms of the same type.
3 votesForm Recognizer v2.0 (preview) enables you to label from to extract the values of interest.
Train a Form Recognizer model with labels using the sample labeling tool – https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/quickstarts/label-tool -
Can we train a single model for multiple type of forms?
I am using Microsoft form-recognizer cognitive service to train a model for forms. My question is that can we train a single model for multiple type of forms? Is it recommended? I have many multiple types of forms and I choose to train a single model for four different types, it get trained but is it a recommended approach?
3 votesForm Recognizer supports training a single model for different types of forms. The model quality should be the same for a single type model and a multi type model per type.
-
Response status code: 408
Iam using Microsoft form-recognizer service and was able to train a model with 5 forms of the same type and it was successful. I was able to analyze that model on test forms as well, But when I tried training the same forms again, I faced the following error:
Response status code: 408 Response body: {'error': {'code': '1011', 'innerError': {'requestId': 'fb75e36b-b704-49fe-a9bf-2fecaa71ca44'}, 'message': 'The operation exceeded allowed time limit and was canceled. The common reasons are that the data source is too large or contains unsupported content. Please check that your request conforms to service limits and retry with redacted data…
1 vote -
Explain how 'empty' document templates need to be created & help the model trainer
only reference that can be found relates to this article (https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/quickstarts/curl-train-extract) - nothing explained in the API section of how to add these to the training model; if >1 helps the model etc.
1 voteYou can train a model with five filled-in forms or an empty form (include the word “empty” in the file name) plus two filled-in forms. Even if you have enough filled-in forms to train with, adding an empty form to your training data set can improve the accuracy of the model.
For more information about building a training data set see “How to build a training data set for a custom model” document – https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer/build-training-data-set
-
Improve the documentation about the SAS URL usage and requirements
I'm finding unclear what/how to gnerate the SAS URL (what permissions are required, at what level).
1 voteTo retrieve the SAS URL, open the Microsoft Azure Storage Explorer, right-click your container, and select Get shared access signature. Click the next dialog and copy the value in the URL section. It should have the form: https://.blob.core.windows.net/?.
Please see the Form Recognizer quick-starts guides located here: https://aka.ms/form-recognizer/docs
-
Cannot create the resource in portal
I cannot select any region or pricing while creating the service.
3 votes -
Taken to request access page even though already accepted to the preview
Clicking on the Form Recognizer container link in the quick start section I get taken to the request access page. I am already accepted to the preview.
1 votePlease use the link in the Form Recognizer Welcome to the public preview e-mail to access the Form Recognizer create resource option in the Azure Portal.
-
2 votes
Form Recognizer v2.0 (preview) supports Tiff format.
- Don't see your idea?