How to Train Document Understanding Model in AI Center

How to train Document Understanding Model in AI Center?

Below are steps that needs to be followed/ taken-care for training the Document Understanding Out Of Box package in AI Center.

Note: Document Understanding Package must be trained before deployment to ensure that ML - Skill creation will not fail.

  1. Create a ML package using the OOB Document understanding model in AI Center. Refer Out Of Box Packages .
  2. Then dataset needs to be created in the AI Center under the "Data sets" tab. Refer Creating Data Sets .
Below are the steps to be followed/taken-care while preparing dataset for DU model:
a) Data labelling needs to be performed on all the documents using "Data Manager". Steps for Installation needs to be followed.

b) At least 25 documents needs to be labelled in order to train the model and each regular field should be labelled on at at least 10 documents. Read Pipelines .

c) Below export requirements should be met. Refer Data Manager Export Documents

d) Now while uploading dataset, files should be uploaded in exact format mentioned in the Dataset Format
  1. Once the data set is uploaded, pipeline needs to created and correct dataset needs to be tagged in pipeline.Refer below link to know more about Pipeline Creation .
  2. After successful training , new package version will get generated and this needs to be used for creating the ML-Skill. Refer this Managing ML Skills .