Comments (2)
Hey,
Did you pretrain the model? If not I would suspect that to be an issue. The paper mentions some form of pre-training for basic OCR recognition
from nougat.
Hey, Did you pretrain the model? If not I would suspect that to be an issue. The paper mentions some form of pre-training for basic OCR recognition
Is the model just using the general pretrained weights of swin transformer and mBart, and directly trained end-to-end on the arxiv data (and PMC+IDL data, which I didn't use for now)?
from nougat.
Related Issues (20)
- Will Nougat support Turkish and German utf-8 characters? HOT 3
- Support code blocks in paper?
- Don't look for GPU when --help is present
- pdf to .tex and not .mmd HOT 2
- the output(multimarkdown) unable to display and convert well HOT 3
- Dataset creation: Do we expect the .tex files to be just a single file for each corresponding PDF? HOT 2
- Why the page header is often ignored in model's output? HOT 3
- Doesn't support checkboxes
- Huggingface output
- Creating my own dataset and training it using Trainer from transformers HOT 1
- get type error from running sklearn.externals.joblib.externals import cloudpickle HOT 1
- some package in docker image building file seems outdated HOT 2
- nougat misses the double column pdfs
- Pretraining Objectives? HOT 6
- token by token generation with probability?
- Extract Table failed.... HOT 2
- Why does metadata exist?
- can not run this app with warning torch.meshgrid HOT 2
- TypeError: BARTDecoder.prepare_inputs_for_inference() got an unexpected keyword argument 'cache_position' HOT 7
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 nougat.