zkalson
zkalson
Hi all, PyMuPDF is licensed under the copyleft GNU AFFERO GPL 3.0. I noticed that it is used in: autogluon\multimodal\data\process_document.py (import fitz) It seems that having to install PyMuPDF could...
Hi all, Based on my understanding, Textract provides an axis-aligned BoundingBox object and a Polygon object which is composed of more specific points (https://docs.aws.amazon.com/textract/latest/dg/text-location.html). It seems that Textractor only provides...
I understand that Document AI performs preprocessing to correct for issues like skew in documents sent to the API, and that any transformations applied are provided in the response under...
## Description PDFs can be classified using Autogluon multimodal, but there doesn't seem to be an Autogluon implementation for recognizing layout/structure (like headings, paragraphs, tables, etc) from documents. Of course,...
## Description In Autogluon multimodal, you can specify a text model on Huggingface (say for the sake of the example roberta-base). If I fine-tuned roberta-base using the Transformers library but...
Referencing issue #52
Using torch==2.6.0, an error occurs on BertClassifierWithPooling.load(): _pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if...
Hi, I have a large diskcache (~600 GB). I used rsync to sync from my local Windows machine to a Linux VM, and I am getting unusual issues on the...