Comments (1)
gwkrsrch
commented on May 18, 2024
1
Hi, thank you for the issue :)
1, Local custom dataset.
We use huggingface/datasets for loading & processing the dataset.
As explained in the README, if you set metadata.jsonl and image_paths properly, there would be no problem.
This link would be helpful to you. If you still have an error, please share the details, e.g., error messages, so that I can help you.
2, pretrained_path in test.py.
Thanks for pointing it out. There is no critical issue with the argument name. Still, I think it would be better to change the name to reduce any miss understanding. I will update the name.
-> Fixed the typo. Thanks again :)
Hope this helps :) Please let me know if you are still confused.
from donut.
Related Issues (20)
- Model Consistently Mispredicting Specific Character in Invoice Number
- Documentation for Synthdog?
- Can donut support batch inference? HOT 2
- Dataset Loader didn't work properly on Kaggle HOT 1
- Are there any acceleration solutions for donut deployment?
- fine-tuning on docvqa ,anls only 40%
- json2token performance HOT 1
- Input type (float) and bias type (struct c10::BFloat16) should be the same HOT 3
- Where can I find the dataset used for training Document Visual Question Answering model
- Random prediction and wrong prediction in repeated characters HOT 4
- Simple questions answering
- Donut Return Output even With Blank Image HOT 5
- Question about the special token map HOT 1
- Idea: Freezing SwinEncoder and fine-tuning BARTdecoder only on custom data HOT 4
- Could not find image processor class in the image processor config or the model config. HOT 1
- Bounding boxes required for pretraining? HOT 1
- Trying to run DOCVQA dataset
- How to handle multi page invoices HOT 4
- getting no module named lightning module when trying to run the fine tuning code in train.py file of donut model. HOT 1
- DOCVQA data set format ? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from donut.