Name | rex-xai JSON |
Version |
0.4.1
JSON |
| download |
home_page | None |
Summary | causal Responsibility-based eXplanations of black-box-classifiers |
upload_time | 2025-07-22 08:31:23 |
maintainer | None |
docs_url | None |
author | David Kelly |
requires_python | >=3.10 |
license | None |
keywords |
|
VCS |
 |
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# ReX: Causal *R*esponsibility *EX*planations for image classifiers

<!--- BADGES: START --->
[](https://rex-xai.readthedocs.io/en/latest/)
[](https://github.com/ReX-XAI/ReX/actions/workflows/test-package-and-comment.yml)
[](https://github.com/ReX-XAI/ReX.jl/blob/main/LICENSE)
<!--- BADGES: END --->
---
ReX is a causal explainability tool for image classifiers. It also works on tabular and 3D data.
Given an input image and a classifier, ReX calculates a causal responsibility map across the data and identifies a minimal, sufficient, explanation.
  
ReX is black-box, that is, agnostic to the internal structure of the classifier.
ReX finds single explanations, non-contiguous explanations (for partially obscured images), multiple independent explanations, contrastive explanations and lots of other things!
It has a host of options and parameters, allowing you to fine tune it to your data.
For background information and detailed usage instructions, see our [documentation](https://rex-xai.readthedocs.io/en/latest/).
<!--inclusion-marker-start-do-not-remove-->
## Installation
ReX can be installed using `pip`.
We recommend creating a virtual environment to install ReX.
ReX has been tested using versions of Python >= 3.10.
The following instructions assume `conda`:
```bash
conda create -n rex python=3.13
conda activate rex
pip install rex_xai
```
This should install an executable `rex` in your path.
To check that ReX is installed correctly, run:
```bash
ReX --help
```
To build from source, clone the repository and run:
```bash
git clone git@github.com:ReX-XAI/ReX.git
cd ReX
conda create -n rex python=3.13
conda activate rex
pip install .
```
> **Note:**
>
> By default, `onnxruntime` will be installed.
> If you wish to use a GPU, you should uninstall `onnxruntime` and install `onnxruntime-gpu` instead.
> You can alternatively clone the project and edit the `pyproject.toml` to read "onnxruntime-gpu >= 1.17.0" rather than "onnxruntime >= 1.17.0".
If you want to use ReX with 3D data, you will need to install some optional extra dependencies:
```bash
pip install 'rex_xai[3D]'
```
<!--inclusion-marker-end-do-not-remove-->
## Feedback
Bug reports, questions, and suggestions for enhancements are welcome - please [check the GitHub Issues](https://github.com/ReX-XAI/ReX/issues) to see if there is already a relevant issue, or [open a new one](https://github.com/ReX-XAI/ReX/issues/new)!
## How to Contribute
Your contributions are highly valued and welcomed. To get started, please review the guidelines outlined in the [CONTRIBUTING.md](/CONTRIBUTING.md) file. We look forward to your participation!
Raw data
{
"_id": null,
"home_page": null,
"name": "rex-xai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": null,
"author": "David Kelly",
"author_email": "dkellino@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/5e/af/b36be9d41665cd80143ec3da941c0ec4b2e45e57eb00a647b358b67d9fe5/rex_xai-0.4.1.tar.gz",
"platform": null,
"description": "# ReX: Causal *R*esponsibility *EX*planations for image classifiers\n\n\n\n<!--- BADGES: START --->\n\n[](https://rex-xai.readthedocs.io/en/latest/)\n[](https://github.com/ReX-XAI/ReX/actions/workflows/test-package-and-comment.yml)\n[](https://github.com/ReX-XAI/ReX.jl/blob/main/LICENSE)\n\n<!--- BADGES: END --->\n\n---\n\nReX is a causal explainability tool for image classifiers. It also works on tabular and 3D data.\n\nGiven an input image and a classifier, ReX calculates a causal responsibility map across the data and identifies a minimal, sufficient, explanation.\n\n  \n\nReX is black-box, that is, agnostic to the internal structure of the classifier.\nReX finds single explanations, non-contiguous explanations (for partially obscured images), multiple independent explanations, contrastive explanations and lots of other things!\nIt has a host of options and parameters, allowing you to fine tune it to your data.\n\nFor background information and detailed usage instructions, see our [documentation](https://rex-xai.readthedocs.io/en/latest/).\n\n<!--inclusion-marker-start-do-not-remove-->\n\n## Installation\n\nReX can be installed using `pip`.\nWe recommend creating a virtual environment to install ReX.\nReX has been tested using versions of Python >= 3.10.\nThe following instructions assume `conda`:\n\n```bash\nconda create -n rex python=3.13\nconda activate rex\npip install rex_xai\n```\n\nThis should install an executable `rex` in your path.\nTo check that ReX is installed correctly, run:\n\n```bash\nReX --help\n```\n\nTo build from source, clone the repository and run:\n\n```bash\ngit clone git@github.com:ReX-XAI/ReX.git\ncd ReX\nconda create -n rex python=3.13\nconda activate rex\npip install .\n```\n\n> **Note:**\n>\n> By default, `onnxruntime` will be installed.\n> If you wish to use a GPU, you should uninstall `onnxruntime` and install `onnxruntime-gpu` instead.\n> You can alternatively clone the project and edit the `pyproject.toml` to read \"onnxruntime-gpu >= 1.17.0\" rather than \"onnxruntime >= 1.17.0\".\n\nIf you want to use ReX with 3D data, you will need to install some optional extra dependencies:\n\n```bash\npip install 'rex_xai[3D]'\n```\n\n<!--inclusion-marker-end-do-not-remove-->\n\n## Feedback\n\nBug reports, questions, and suggestions for enhancements are welcome - please [check the GitHub Issues](https://github.com/ReX-XAI/ReX/issues) to see if there is already a relevant issue, or [open a new one](https://github.com/ReX-XAI/ReX/issues/new)!\n\n## How to Contribute\n\nYour contributions are highly valued and welcomed. To get started, please review the guidelines outlined in the [CONTRIBUTING.md](/CONTRIBUTING.md) file. We look forward to your participation!\n\n",
"bugtrack_url": null,
"license": null,
"summary": "causal Responsibility-based eXplanations of black-box-classifiers",
"version": "0.4.1",
"project_urls": {
"Bug Tracker": "https://github.com/ReX-XAI/ReX/issues",
"Documentation": "https://rex-xai.readthedocs.io/",
"Homepage": "https://rex-xai.readthedocs.io//",
"Repository": "https://github.com/ReX-XAI/ReX"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "657ba83c304d13edecb85420bc152b9db33fafd50eabbf12657d01ef3ca8f76f",
"md5": "136d1382a633ac4ac6fcf7bae4e8e79b",
"sha256": "62b30b3f7e7e17c6f3e1c8c04c6233449c4057a0c8b6be917b3020e1395e2ae9"
},
"downloads": -1,
"filename": "rex_xai-0.4.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "136d1382a633ac4ac6fcf7bae4e8e79b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 58667,
"upload_time": "2025-07-22T08:31:21",
"upload_time_iso_8601": "2025-07-22T08:31:21.344746Z",
"url": "https://files.pythonhosted.org/packages/65/7b/a83c304d13edecb85420bc152b9db33fafd50eabbf12657d01ef3ca8f76f/rex_xai-0.4.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "5eafb36be9d41665cd80143ec3da941c0ec4b2e45e57eb00a647b358b67d9fe5",
"md5": "828593e3f70634294c0e51f707d3fc2d",
"sha256": "e2cb9d97e6b85cad0c3c9ae02b5d6079c0e2d6fe5997924970ecbdb9c29d9762"
},
"downloads": -1,
"filename": "rex_xai-0.4.1.tar.gz",
"has_sig": false,
"md5_digest": "828593e3f70634294c0e51f707d3fc2d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 49793,
"upload_time": "2025-07-22T08:31:23",
"upload_time_iso_8601": "2025-07-22T08:31:23.222293Z",
"url": "https://files.pythonhosted.org/packages/5e/af/b36be9d41665cd80143ec3da941c0ec4b2e45e57eb00a647b358b67d9fe5/rex_xai-0.4.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-22 08:31:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ReX-XAI",
"github_project": "ReX",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "rex-xai"
}