Skip to content

The first public PyTorch implementation of Attentive Recurrent Comparators

License

Notifications You must be signed in to change notification settings

Raverss/arc-pytorch

 
 

Repository files navigation

arc-pytorch

PyTorch implementation of Attentive Recurrent Comparators by Shyam et al.

A blog explaining Attentive Recurrent Comparators

This is repository for testing ARC on custom (digits) dataset.

How to run?

Download data

Download our data and unzip two folders into data folder of this repository.

Train

python train.py --cuda

The training should achieve around 85%+ accuracy on test data.

Visualize

python viz.py --cuda --load name_of_model --same

Run with exactly the same parameters as train.py and specify the model to load. The script dumps images to a directory in visualization. The name of directory is taken from --name parameter if specified, else name is a function of the parameters of network. name_of_model should be in data folder.

Test accuracy of model

python test_model.py --cuda --load name_of_model

name_of_model should be in data folder.

About

The first public PyTorch implementation of Attentive Recurrent Comparators

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%