Stack Overflow
Stack Overflow

Questions tagged [donut]

9 questions
0
votes
0 answers

Make sure _init_weights is implemented for

I am facing an issue with the donut repo. I am trying to load the pretrained model naver-clova-ix/donut-base-finetuned-cord-v2 but getting the same error every time: Make sure _init_weights is implemented for P.s: I…
Asfan Sajid
  • 1
  • 1
0
votes
0 answers

Purpose of using special tokken in DONUT

text in this code they have used special tokken as New special tokens: ['', '', '', '', '', '', '', '', '', ''] and adding via…
shubham bhardwaj
  • 1
  • 2
0
votes
0 answers

Extracting text in a structured way not working with Transformer DONUT

I am currently working on fine tuning DONUT transformer (https://huggingface.co/docs/transformers/model_doc/donut) on this task : I want it to extract only the paragraphs of my text document like this : <> Text of the paragraph <>" . For this, I…
Anais Despres
  • 1
  • 1
0
votes
0 answers

Donut Chart in Salesforce

Hi guys I need your help/advice. I need to create a donut chart where I will be able to show the amount of 5 different fields (all currency fields in the opportunity object), so that in the donut chart will appear the percentage of amount of each of…
tifiamolaroma
  • 1
0
votes
0 answers

Breaking apart encoder-decoder steps in transformer model

I've been experimenting with the DONUT DocVQA model made available by Hugging Face to extract data points from documents. It uses a visual transformer for encoding the image, and a language model decoder that takes the encoded image and tokenized…
user3897315
  • 487
  • 2
  • 5
  • 14
0
votes
0 answers

Using Label Studio to create a dataset like CORD v2

I am using Label Studio to create a dataset for an OCR task to recognize items in a bunch of receipts. I am trying to use a pre-traiened model in Hugging Face named Donut which has been trained using CORD v2 dataset. Here is the link of the CORD…
Mohammad Ali Taefi Garmeh
  • 1
0
votes
0 answers

I'm getting an error when using the Donut Model: Input Type and Bias type should be the same

I'm trying to extract text from image using the Donut Model which is an Image Parser. It seems that the input image is not in the proper format. I'm getting an error that says: RuntimeError: Input type (float) and bias type (c10::BFloat16) should be…
Rithwik Babu
  • 1
  • 1
0
votes
0 answers

RuntimeError: It looks like your LightningModule has parameters that were not used in producing the loss returned by training_step

I'm trying to use donut, which is a transformer model with a huggingface implementation, and pre-train it on a language it hasn't been yet on my desktop. Unfortunately the version of the stack provided on the original repo doesn't support my GPU, so…
lte__
  • 7,175
  • 25
  • 74
  • 131
-1
votes
0 answers

How do i annotate an image to train it for a DocQuery Donut Model

I have to train a DocQuery model on a custom dataset of documents(balance sheets,profit loss documents, etc, example shown below) and i have to annotate it to be able to train a DocQuery donut model and be able to ask it questions about the…
Tejas M A
  • 11
  • 2