From 9b1c1bb81eeccdc913593a8748bf06992b912a83 Mon Sep 17 00:00:00 2001 From: annahedstroem Date: Tue, 18 Oct 2022 16:24:51 +0200 Subject: [PATCH] updated documentation --- CONTRIBUTING.md | 2 -- docs/source/docs_dev/CONTRIBUTING.md | 2 -- docs/source/getting_started/getting_started_example.md | 8 ++++---- docs/source/index.md | 5 ++--- 4 files changed, 6 insertions(+), 11 deletions(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index ee087ed29..f9dcb0b5b 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -8,8 +8,6 @@ In this guide, you will get an overview of the workflow and best practices for c **Questions.** If you have any developer-related questions, please [open an issue](https://github.com/understandable-machine-intelligence-lab/Quantus/issues/new/choose) or write us at [anna.hedstroem@tu-berlin.de](mailto:anna.hedstroem@tu-berlin.de). - - ## Table of Contents - [Reporting Bugs](#reporting-bugs) diff --git a/docs/source/docs_dev/CONTRIBUTING.md b/docs/source/docs_dev/CONTRIBUTING.md index c9d595d76..036ee97fe 100644 --- a/docs/source/docs_dev/CONTRIBUTING.md +++ b/docs/source/docs_dev/CONTRIBUTING.md @@ -8,8 +8,6 @@ In this guide, you will get an overview of the workflow and best practices for c **Questions.** If you have any developer-related questions, please [open an issue](https://github.com/understandable-machine-intelligence-lab/Quantus/issues/new/choose) or write us at [anna.hedstroem@tu-berlin.de](mailto:anna.hedstroem@tu-berlin.de). - - ## Table of Contents - [Reporting Bugs](#reporting-bugs) diff --git a/docs/source/getting_started/getting_started_example.md b/docs/source/getting_started/getting_started_example.md index 5408312e7..7680cc9e6 100644 --- a/docs/source/getting_started/getting_started_example.md +++ b/docs/source/getting_started/getting_started_example.md @@ -2,7 +2,7 @@ The following will give a short introduction to how to get started with Quantus. -**Note**: This example is based on the [PyTorch](https://pytorch.org/) framework, but we also support +Note that this example is based on the [PyTorch](https://pytorch.org/) framework, but we also support [Tensorflow](https://www.tensorflow.org), which would differ only in the {ref}`preliminaries ` (i.e., the model and data loading), as well as in the available XAI libraries. @@ -101,8 +101,8 @@ in `quantus.explain` are limited --- `quantus.explain` is a wrapper around [Cap [tf.explain](https://github.com/sicara/tf-explain) but does not support every explanation method offered in the respective libraries. -If you want to use Quantus to evaluate any other explanation method (e.g., your newly built explanation function), -you can simply provide your own function (`callable`, see also {ref}`extending quantus `). +If you want to use Quantus to evaluate any arbitrary explanation method (e.g., your newly built explanation function), +you can simply provide your own function (`callable`, see also {ref}`Extending quantus `). Examples of how to use `quantus.explain` or your own customised explanation function are included in the next section. ![drawing](../assets/mnist_example.png) @@ -118,7 +118,7 @@ To gather quantitative evidence for the quality of the different explanation met ### Quantus metrics Quantus implements XAI evaluation metrics from different categories, -e.g., Faithfulness, Localisation, Robustness, etc., which all inherit from the base `quantus.Metric` class. +e.g., Faithfulness, Localisation and Robustness etc which all inherit from the base `quantus.Metric` class. To apply a metric to your setting (e.g., [Max-Sensitivity](https://arxiv.org/abs/1901.09392)) it first needs to be instantiated: diff --git a/docs/source/index.md b/docs/source/index.md index a43b90e8a..e64558def 100644 --- a/docs/source/index.md +++ b/docs/source/index.md @@ -25,12 +25,12 @@ Quantus can be installed from PyPI (this way assumes that you have either [PyTor pip install quantus ``` -For a more in-depth guide on how to install Quantus, read more {doc}`here `. This includes instructions for how to install a desired deep learning framework such as PyTorch or tensorflow together with Quantus. +For a more in-depth guide on how to install Quantus, read more [here](https://quantus.readthedocs.io/en/latest/getting_started/installation.html). This includes instructions for how to install a desired deep learning framework such as PyTorch or tensorflow together with Quantus. # Contents ```{toctree} -:caption: # Installation +:caption: Installation :maxdepth: 1 getting_started/installation @@ -47,7 +47,6 @@ getting_started/getting_started_example :caption: API Reference :maxdepth: 1 -docs_api/modules docs_api/quantus ```