Issues
- 1
Can synthdog insert text for a specified bbox?
#299 opened by Supercarry-khr - 0
Where is the fine-tuned model?
#300 opened by sdip15fa - 0
not work this app.py
#298 opened by sssssshf - 4
How to handle multi page invoices
#279 opened by DNFSiF - 6
Problem with getting predictions
#287 opened by jdrzj - 0
Not getting prediction correctly using the model trained on the custom dataset (similar format as CORD-V2 dataset)
#297 opened by SiriusPoint - 0
donut inference시 sub task가 변경?
#296 opened by kittyLunar - 4
- 0
Update donut-python Python Package to be compatible with latest versions of transformers
#295 opened by agovin9812 - 0
Classification inference
#294 opened by SNavgale - 4
Input type (float) and bias type (struct c10::BFloat16) should be the same
#267 opened by Coder-Vishali - 2
The provided lr scheduler `LambdaLR` doesn't follow PyTorch's LRScheduler API. You should override the `LightningModule.lr_scheduler_step` hook with your own logic if you are using a custom LR scheduler.
#255 opened by goseesomething - 0
confidence 값의 공식적인 지원
#293 opened by HwangSeyoon - 3
How to extract complete text from the document?
#292 opened by vikasr111 - 3
Complete text
#253 opened by VagnerBelfort - 0
Multi GPU support for fine tuning
#291 opened by SNavgale - 5
details is not ideal
#258 opened by chopin1998 - 2
VisionEncoderDecoderModel convert
#284 opened by sjtu-cz - 2
custom json schema - ASAP
#290 opened by crazycoderF12 - 1
getting no module named lightning module when trying to run the fine tuning code in train.py file of donut model.
#280 opened by svocdfrockz - 1
Question about the special token map
#274 opened by RAY-RaY-R - 0
Error "A configuraton of type donut cannot be instantiated because not both `encoder` and `decoder` sub-configurations are passed" when run inference after finetuned docvqa without pushing to hugging face?
#289 opened by phuchm - 1
Does synthdog data has MiT or afl-3.0 license?
#288 opened by becxer - 5
Donut Return Output even With Blank Image
#272 opened by wdprsto - 4
- 3
DOCVQA data set format ?
#281 opened by tzktz - 0
- 1
fine-tuning on docvqa ,anls only 40%
#265 opened by ShuoZhang2003 - 1
Integrate a customized internal OCR engine to Donut
#285 opened by Altimis - 1
Two types of documents in one model?
#256 opened by henkish - 1
Bounding boxes required for pretraining?
#277 opened by mustaszewski - 1
Prediction and Answer differ by dataset-specific tag
#282 opened by ftkeys - 2
The latest update has the model weights twice the embedding dim size of the actual model installed through github or pip
#283 opened by Samartha27 - 0
Trying to run DOCVQA dataset
#278 opened by srgautam9 - 1
Could not find image processor class in the image processor config or the model config.
#276 opened by felixnguyen258 - 2
How to config synthdog for much more longer text, like total length about 1024-2048
#249 opened by CheungZeeCn - 0
Simple questions answering
#271 opened by shersoni610 - 1
dataset script missing error
#250 opened by segaranp - 0
Where can I find the dataset used for training Document Visual Question Answering model
#269 opened by Coder-Vishali - 1
json2token performance
#266 opened by benjaminfh - 0
- 2
Can donut support batch inference?
#262 opened by sjtu-cz - 1
Dataset Loader didn't work properly on Kaggle
#263 opened by wdprsto - 0
Documentation for Synthdog?
#261 opened by parthch11 - 0
- 0
How to annotate and train donut for extracting all dates (unknown number of dates)
#259 opened by Anas-Khayata - 0
Is UIPATH AI Center Document Understanding Process also OCR free like Donut
#257 opened by Sridhar-Ranganaboina - 1
- 1
Couldn't connect to 'https://huggingface.co'
#252 opened by mmhzlrj - 0