RE-Train Invoice ML Model with Validation Station data

Help AI Center
,
1

Hello,
I have created a workflow which uses train extractor ml Activity and Out of the box invoice model. I am trying to retrain the model using the data generated by the validation station in Action Center for more accuracy.
I have not used any data manager feature since I don’t want to customize anything.
The Invoice Trainer activity is automatically uploading it from Studio to a DataSet.(inside of a fine-tune folder)
But I am not able to train ml model using that fine-tune folder dataset as it doesn’t contain split.csv all those files. Can anyone help what I am doing wrong.

My problem is same as this post. Post Link

2

Hello @RpaNoobMax!

It seems that you have trouble getting an answer to your question in the first 24 hours.
Let us give you a few hints and helpful links.

First, make sure you browsed through our Forum FAQ Beginner’s Guide. It will teach you what should be included in your topic.

You can check out some of our resources directly, see below:

  1. Always search first. It is the best way to quickly find your answer. Check out the image icon for that.
    Clicking the options button will let you set more specific topic search filters, i.e. only the ones with a solution.

  2. Topic that contains most common solutions with example project files can be found here.

  3. Read our official documentation where you can find a lot of information and instructions about each of our products:

  4. Watch the videos on our official YouTube channel for more visual tutorials.

  5. Meet us and our users on our Community Slack and ask your question there.

Hopefully this will let you easily find the solution/information you need. Once you have it, we would be happy if you could share your findings here and mark it as a solution. This will help other users find it in the future.

Thank you for helping us build our UiPath Community!

Cheers from your friendly
Forum_Staff

3

Hi @RpaNoobMax ,

Maybe even though you do not want to customize the data, the Data Manager’s Scheduled Export does the following :

image
image857×81 10.3 KB

Hence, we may not be able to avoid the Data Labelling for Auto Retraining the ML Model.

Perhaps, you could try importing some documents (15-20) into the Data Manager, Use Pre-Labelling option by providing the necessary endpoints and API (No need for correction as you do not want to customize) and then Perform the Export /Schedule the Export.

For Combining the datasets into the Export Folder, it seems Data Manager’s Export feature is required for now. Maybe in later releases they may introduce it separately or Perhaps because the Model needs a minimum number of Trained documents they keep the functionality this way.

Let us know if you were able to figure out a solution or provide us with some feedback if you were able to try the above approaches.

Source of the Post :