pytorch-widedeep
autogluon
| pytorch-widedeep | autogluon | |
|---|---|---|
| 7 | 8 | |
| 1,238 | 7,124 | |
| - | 1.6% | |
| 8.5 | 9.6 | |
| 6 days ago | 8 days ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch-widedeep
-
why can't I import pytorch-widedeep ?
Ask the dev https://github.com/jrzaurin/pytorch-widedeep/issues
-
[P] pytorch-widedeep model alert: TabPerceiver and TabFastFormer are now available in the library
New DL models for Tabular Data and functionalities added to the pytorch-widedeep library
-
[P] pytorch-widedeep model alert: SAINT and the FT-Transformer are now available in the library
🚨MODEL ALERT! 🚨New DL models for Tabular Data added to the pytorch-widedeep library . SAINT by Gowthami Somepalli and collaborators (paper: https://arxiv.org/abs/2106.01342) and the FT-Transformer which was already used at the SAINT paper but officially introduced by Yury Gorishniy and collaborators (paper: https://arxiv.org/abs/2106.11959). More functionalities coming soon to the [library](https://github.com/jrzaurin/pytorch-widedeep)
-
How to do K-Fold Cross Validation for hyperparameter tuning on pytorch-widedeep ?
Now in pytorch-widedeep (https://github.com/jrzaurin/pytorch-widedeep) the recommended path for training a single model is:
-
[P] pytorch-widedeep v1.0: deep learning for tabular data that you can combine with images and text
Main repo
- Pytorch-widedeep v1.0: deep learning for tabular data
-
[P] pytorch-widedeep, deep learning for tabular data: Deep Learning vs LightGBM
A thorough comparison between Deep Learning algorithms for tabular data (using pytorch-widedeep ) and LightGBM for classification and regression problems.
autogluon
-
pip install remyxai - easiest way to create custom vision models
This seems not very convincing. There are other popular frameworks that provide AutoML with existing datasets (eg https://github.com/autogluon/autogluon)
- autogluon: NEW Data - star count:5070.0
-
[D] Where is AutoML for NNs?
https://github.com/awslabs/autogluon works well for image/text/tabular data
- k-fold bagging in Autogluon - Tabular
-
What will the data science job market be like in 5 years?
Some AutoML is getting pretty good, AutoGluon is very solid for tabular data. That being said you still need to have your data in tabular format and deployment still requires some effort.
What are some alternatives?
tabnet - PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
FLAML - A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
alibi-detect - Algorithms for outlier, adversarial and drift detection
autokeras - AutoML library for deep learning
rtdl - Research on Tabular Deep Learning (Python package & papers) [Moved to: https://github.com/Yura52/rtdl]
auto-sklearn - Automated Machine Learning with scikit-learn
torchio - Medical imaging toolkit for deep learning
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
scrambpy - Scramb.py is a region based JPEG Image Scrambler and Descrambler written in Python for End-to-End-Encrypted (E2EE) Image distribution through unaware channels.
imbalanced-regression - [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
LAVIS - LAVIS - A One-stop Library for Language-Vision Intelligence