Sarthak Mittal

I'm not completely sure which fields you're referring to. Do you have a sample image you can display in this ticket? In general however, it should be possible to train...

Can you give an example of what different types of forms you plan to try InvoiceNet on? In general, yes that should be possible but I feel InvoiceNet is an...

This would install python2 versions of pip and virtualenv if I'm correct. Should be changed to python3-pip and python3-virtualenv right?

Could you pull in the latest commits and check if those issues are resolved?

I have been working on trying to integrate EasyOCR into InvoiceNet and basically provide an option to choose between tesseract and easyocr. However, it looks like EasyOCR doesn't return bounding...

> I managed to edit the code to use Azure instead too. I'd definitely merge it if you open a PR :eyes:

@wbtan7 added support for AWS Textract as an alternate OCR option in #56. Install [boto3](https://pypi.org/project/boto3/) and setup your AWS credentials according to the documentation to use Textract!

This is a limitation of the architecture I'm currently using. Increasing the n-gram size (which is currently 4) increases the model size exponentially and unless you have massive GPU resources...

There are two places you'd have to change the n-gram length: - https://github.com/naiveHobo/InvoiceNet/blob/9c94bb59cc7a3e4116c5f7a6ab7dfe4aec3bcbd2/invoicenet/common/util.py#L116 - https://github.com/naiveHobo/InvoiceNet/blob/9c94bb59cc7a3e4116c5f7a6ab7dfe4aec3bcbd2/invoicenet/acp/data.py#L65

Firstly, can you pull in the latest commit? It fixes a couple of bugs I missed when n-gram length is different. Secondly, you need to prepare your data again after...