Comments (5)
Since this is a GAN, does it make sense to stop early when the loss is stable? If both the generator and discriminator are improving at the same rate, shouldn't it stay stable?
from ctgan.
In my forked ctgan repo, i added a couple new features that were of interest to me including logging, gpu_stats, early_stopping and patience.
any feedback appreciated.
e.g.
ctgan.fit(data, discrete_columns, epochs=500, early_stopping=True, gpu_stats=False, patience=40, logging=True)
https://github.com/oregonpillow/CTGAN/blob/master/ctgan/synthesizer.py
from ctgan.
I implemented early stopping as well here https://github.com/Diyago/GAN-for-tabular-data/blob/master/ctgan/synthesizer.py#L262
from ctgan.
@oregonpillow @Diyago I came upon this while reviewing old issues. Since it seems that there are already a couple of implementations out there, please feel free to open a PR against this issue to contribute your versions! We can then discuss a bit more the details over the proposed code.
from ctgan.
As @Baukebrenninkmeijer mentioned, using the discriminator/generator losses to decide whether a GAN has converged is an open research question, so we won't be implementing it at this time.
from ctgan.
Related Issues (20)
- Return loss values as float values not PyTorch objects
- Transition from using setup.py to pyproject.toml to specify project metadata
- Remove bumpversion and use bump-my-version
- Switch to using ruff for Python linting and code formatting
- Add dependency checker
- Remove scikit-learn dependency
- CTGAN using deprecated 'sklearn' HOT 2
- Replace integration test that uses the iris demo data
- Add bandit workflow
- Feature Request: More verbose logging HOT 3
- Fix minimum version workflow when pointing to github branch
- Deployment requirements based on libtorch or ONNX HOT 4
- How to load this model directly to generate data after saving it HOT 4
- Cleanup automated PR workflows
- Remove FutureWarning: Setting an item of incompatible dtype is deprecated
- Only run unit and integration tests on oldest and latest python versions for macos
- [HELP] CTGAN has Reproducibility? HOT 8
- Add support for numpy 2.0.0
- Cap numpy to less than 2.0.0 until CTGan supports
- Lossvalues are good, but the quality of the synthetic data is bad... How?? HELP WANTED HOT 1
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 ctgan.