wrong link for VAE CF generation in Readme

interpretml / DiCE

Generate Diverse Counterfactual Explanations for any machine learning model.

https://interpretml.github.io/DiCE/

MIT License

1.37k stars 190 forks source link

Open giandos200 opened 2 years ago

giandos200 commented 2 years ago

Link mistake in VAE method:

Gradient-based methods

An explicit loss-based method described in Mothilal et al. (2020) (Default for deep learning models).
A Variational AutoEncoder (VAE)-based method described in Mahajan et al. (2019) (see the BaseVAE notebook).

that should be:

https://github.com/interpretml/DiCE/blob/master/docs/source/notebooks/DiCE_getting_started_feasible.ipynb

giandos200 commented 2 years ago

line 51 of file feasible_base_vae.py and line 50 of file feasible_model_approx.py the base_model_dir get error:

self.base_model_dir = '../../../dice_ml/utils/sample_trained_models/'

i've resolved with:

import os
self.base_model_dir = ('/').join(os.path.dirname(__file__).split('/')[:-1]+['utils','sample_trained_models',''])

i don't know if is the best way of doing it, (probably not)!