Skip to content

Pytorch implementation for VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain - NeurIPS 2020

License

Notifications You must be signed in to change notification settings

moonchangin/VIME_pytorch

Repository files navigation

VIME_pytorch

A PyTorch implementation of VIME.

Acknowledgement

This work is based on the paper by Jinsung Yoon, Yao Zhang, James Jordon, and Mihaela van der Schaar titled "VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain," presented at Neural Information Processing Systems (NeurIPS) in 2020.

Link to the paper

Motivation

The original codebase for "VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain" was implemented using outdated versions of Keras (2.3.1) and TensorFlow (1.15.0). Our aim is to modernize the implementation by transitioning to a more recent version of PyTorch.

Requirements

Install these packages using conda:

conda install scikit-learn numpy pandas pytorch torchvision -c pytorch

Test Run

To test the implementation, run the following command:

python semi_pytorch_mnist_test.py

About

Pytorch implementation for VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain - NeurIPS 2020

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages