x
Table of Contents
Question
Given the following scenario: You have a trained version of the Document Understanding Model with 1000 pages called v22.10.0.1. You have an evaluation dataset of 100 pages that gave a score of 0.72 for v22.10.0.1. The business team labeled 800 pages and they ask for an increment of the Model that would contain all 1000+800 pages.
What is the first recommended pipeline run configuration to create the new version?
A. Run a Pipeline on the Package with the following settings:
Pipeline type: Full –
Package Major Version: 22.10.0 –
Package Minor Version: 1 –
Input Dataset: 800 pages –
Evaluation Dataset: 100 pages
B. Run a Pipeline on the Package with the following settings:
Pipeline type: Training –
Package Major Version: 22.10.0 –
Package Minor Version: 1 –
Input Dataset: 1000+800 pages –
Evaluation Dataset: N/A
C. Run a Pipeline on the Package with the following settings:
Pipeline type: Full –
Package Major Version: 22.10.0 –
Package Minor Version: 0 –
Input Dataset: 1000+800 pages –
Evaluation Dataset: 100 pages
D. Run a Pipeline on the Package with the following settings:
Pipeline type: Evaluate –
Package Major Version: 22.10.0 –
Package Minor Version: 0 –
Input Dataset: 1000+800 pages –
Evaluation Dataset: 100 pages
Answer
The correct answer is B. When creating a new version of a trained Document Understanding Model that incorporates additional labeled pages, the recommended pipeline run configuration is as follows:
B. Run a Pipeline on the Package with the following settings:
Pipeline type: Training –
Package Major Version: 22.10.0 –
Package Minor Version: 1 –
Input Dataset: 1000+800 pages –
Evaluation Dataset: N/A
Explanation
When updating a trained Document Understanding Model with new labeled pages, it is essential to run a Training pipeline. This pipeline type focuses on retraining the model using the combined dataset, which includes both the original pages (1000) and the newly labeled pages (800).
The Package Major Version should remain the same (22.10.0) to indicate that this new version is still part of the same major release. However, the Package Minor Version should be incremented (from 0 to 1) to reflect that this is an updated version of the model within the same major release.
The Input Dataset should consist of all available labeled pages, including the original 1000 pages and the newly labeled 800 pages, totaling 1800 pages. This ensures that the model is trained on the most comprehensive dataset possible.
Since this is a Training pipeline, an Evaluation Dataset is not required at this stage. The model’s performance will be assessed later using the existing evaluation dataset of 100 pages.
By following this recommended pipeline run configuration, you can create a new version of your trained Document Understanding Model that incorporates the newly labeled pages, improving its performance and accuracy.
UiPath UiSAIv1 certification exam assessment practice question and answer (Q&A) dump including multiple choice questions (MCQ) and objective type questions, with detail explanation and reference available free, helpful to pass the UiPath UiSAIv1 exam and earn UiPath UiSAIv1 certification.