Need help with choicenet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

sjchoi86
127 Stars 9 Forks MIT License 30 Commits 0 Opened issues

Description

Implementation of ChoiceNet

Services available

!
?

Need anything else?

Contributors list

# 14,919
HTML
Python
Jupyter...
Tensorf...
19 commits

ChoiceNet

TensorFlow Implementation of ChoiceNet on regression tasks.

Summarized result:

Classification / Regression

Paper: arxiv

Classification (MNIST) Result


Error type: [Permutation]
name Result
Outlier Rate: 25.0%
Outlier Rate: 45.0%
Outlier Rate: 47.5%

Error type: [Random Shuffle]
name Result
Outlier Rate: 50.0%
Outlier Rate: 90.0%
Outlier Rate: 95.0%

Error type: [Label Bias]
name Result
Outlier Rate: 25.0%
Outlier Rate: 45.0%
Outlier Rate: 47.5%

Regression Result


Reference Function: [cosexp]
name Training Data Multi-Layer Perceptron Mixture Density Network ChoiceNet
oRate: 0.0%
oRate: 10.0%
oRate: 30.0%
oRate: 50.0%
oRate: 60.0%
oRate: 70.0%

Reference Function: [linear]
name Training Data Multi-Layer Perceptron Mixture Density Network ChoiceNet
oRate: 0.0%
oRate: 10.0%
oRate: 30.0%
oRate: 50.0%
oRate: 60.0%
oRate: 70.0%

Reference Function: [step]
name Training Data Multi-Layer Perceptron Mixture Density Network ChoiceNet
oRate: 0.0%
oRate: 10.0%
oRate: 30.0%
oRate: 50.0%
oRate: 60.0%
oRate: 70.0%

HowTo?

  • run code/mainregrun.ipynb
  • Properly modify followings based on the working environment:
    python
    nWorker = 16
    maxGPU  = 8
    
  • (I was using 16 CPUs / 8 TESLA P40s / 96GB RAM.)

Requirements

  • Python3
  • TF 1.4>=

Contact

This work was done in Kakao Brain.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.