Skip to content

Commit

Permalink
Readme: Prepare for release v0.1.3
Browse files Browse the repository at this point in the history
Update readme and bump version in setup.cfg.
  • Loading branch information
rodrigobdz committed Jul 9, 2022
1 parent a9b66af commit a4e0b8f
Show file tree
Hide file tree
Showing 2 changed files with 13 additions and 5 deletions.
16 changes: 12 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@

Implementation of Layer-wise Relevance Propagation (LRP) algorithm together with quantitative evaluation metrics to compare heatmap explanations objectively.

Special thanks to Dr. Grégoire Montavon for his insights, which shaped the development of this project.

## Features

Explainability:
Expand Down Expand Up @@ -77,12 +79,14 @@ python3 -m pip install lrp-pf-auc

The PyPI distribution `lrp-pf-auc` provides the following two packages: `lrp` and `pf`.

The package name refers to Layer-wise Relevance Propagation (LRP), Pixel Flipping (PF), and Area Under the Curve (AUC) respectively.
The name `lrp-pf-auc` stands for Layer-wise Relevance Propagation (LRP), Pixel Flipping (PF), and Area Under the Curve (AUC) respectively.

## Usage

Refer to [demo.ipynb](https://github.com/rodrigobdz/lrp/blob/main/demo.ipynb) for an example of Layer-wise Relevance Propagation (LRP), Pixel-Flipping (PF) and Area under the Curve (AUC).

Feel free to check out the Jupyter notebooks under [experiments/notebooks](https://github.com/rodrigobdz/lrp/tree/main/experiments/notebooks) for a chronological overview of the project.

## Related Projects

- Sequential LRP implementation: [gmontavon/lrp-tutorial](https://git.tu-berlin.de/gmontavon/lrp-tutorial)
Expand All @@ -100,18 +104,18 @@ Cite as:

- Plaintext:

> Rodrigo Bermúdez Schettino. (2022). rodrigobdz/lrp: v0.1.2 (v0.1.2). Zenodo. https://doi.org/10.5281/zenodo.6814117
> Rodrigo Bermúdez Schettino. (2022). rodrigobdz/lrp: v0.1.3 (v0.1.3). Zenodo. https://doi.org/10.5281/zenodo.6814117
- BibTeX:

```text
@software{rodrigo_bermudez_schettino_2022_6814117,
author = {Rodrigo Bermúdez Schettino},
title = {rodrigobdz/lrp: v0.1.2},
title = {rodrigobdz/lrp: v0.1.3},
month = jul,
year = 2022,
publisher = {Zenodo},
version = {v0.1.2},
version = {v0.1.3},
doi = {10.5281/zenodo.6814117},
url = {https://doi.org/10.5281/zenodo.6814117}
}
Expand All @@ -121,6 +125,10 @@ Cite as:

- The structure of this readme is based on [minimal-readme](https://github.com/rodrigobdz/minimal-readme)

- The `lrp` package uses [two customized files](https://github.com/rodrigobdz/lrp/tree/main/lrp/zennit) originally from [chr5tphr/zennit](https://github.com/chr5tphr/zennit).

- The syntax for defining custom composites originates is inspired by [this discussion](https://github.com/chr5tphr/zennit/issues/76) on `zennit`'s repo.

This implementation is based on insights from:

- LRP overview paper
Expand Down
2 changes: 1 addition & 1 deletion setup.cfg
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[metadata]
name = lrp_pf_auc
version = 0.1.2
version = 0.1.3
description = Explain Neural Networks using Layer-wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.
long_description = file: README.md
long_description_content_type = text/markdown
Expand Down

0 comments on commit a4e0b8f

Please sign in to comment.