Comments (4)
Hi, thank you for your interest in the project.
I've had the same problem and I think it is because of the learning rate scheduler. I've created a discussion post here: #11
Restarting the training is not an optimal solution but it seems to work. As stated, maybe another scheduler is a better fit. Any ideas?
Also, I'm using config.yaml
right now.
from latex-ocr.
Thanks for your reply. I have also been looking for possible reasons for this problem. I think both the optimizer and the lr scheduler may be the cause. So I will try to use different configs for the optimizer and the lr scheduler to find the optimal result.
And, are you currently using the method which manually stops and retrains with the previous model as a starting point?
from latex-ocr.
I'm interrupting the training after some time (I keep looking at the progress in wandb and if the loss stagnates I'm interrupting) and resume from the last saved checkpoint (It saves on Keyboardinterrupt after the first epoch).
python train.py --config path-to-checkpoints/model-name/config.yaml --resume
something like that.
from latex-ocr.
With the StepLR scheduler this does not happen anymore
from latex-ocr.
Related Issues (20)
- fails on very simple image HOT 2
- docker image HOT 1
- Request: How can I use this package with PyCall or PythonCall in Julia.
- Package this project to MacOS application
- [Windows GUI] latexocr: Hide Command Window and close to task bar
- Cant run with conda HOT 2
- Equation in many lines
- Problem with union and intersection
- How to join the contribution?
- How to join the contribution?
- How to join the contribution?
- uninstalling does not uninstall the nvidia packages HOT 1
- Running latexocr in WSL2 ubuntu
- [FR] `model(file)` copies the predicted latex to the clipboard
- Python version not mentioned as a dependency
- Where is latex code stored and how do I capture it in a variable to post process it?
- Does the formula font have an effect when inserting an image?
- Screenshot doesn't work with grim on wayland HOT 1
- [bug] - Hugging Face Running Error
- AttributeError: module 'numpy' has no attribute 'float'. HOT 2
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 latex-ocr.