<hr/>
[](https://pypi.org/project/xaitk-saliency/)
[](https://xaitk-saliency.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/XAITK/xaitk-saliency/actions/workflows/ci-unittests.yml)
[](https://github.com/XAITK/xaitk-saliency/actions/workflows/ci-example-notebooks.yml)
[](https://codecov.io/gh/XAITK/xaitk-saliency)
[](https://lgtm.com/projects/g/XAITK/xaitk-saliency/context:python)
# XAITK - Saliency
The `xaitk-saliency` package is an open source, Explainable AI (XAI) framework
for visual saliency algorithm interfaces and implementations, built for
analytics and autonomy applications.
See [here](https://xaitk-saliency.readthedocs.io/en/latest/introduction.html)
for a more formal introduction to the topic of XAI and visual saliency
explanations.
This framework is a part of the [Explainable AI Toolkit (XAITK)](
https://xaitk.org).
## Supported Algorithms
The `xaitk-saliency` package provides saliency algorithms for a wide range of image understanding
tasks, including image classification, image similarity, object detection, and reinforcement learning.
The current list of supported saliency algorithms can be found [here](
https://xaitk-saliency.readthedocs.io/en/latest/introduction.html#saliency-algorithms).
## Target Audience
This toolkit is intended to help data scientists and developers who want to
add visual saliency explanations to their workflow or product.
Functionality provided here is both directly accessible for targeted
experimentation, and through [Strategy](
https://en.wikipedia.org/wiki/Strategy_pattern) and [Adapter](
https://en.wikipedia.org/wiki/Adapter_pattern) patterns to allow for
modular integration into systems and applications.
## Installation
Install the latest release via pip:
```bash
pip install xaitk-saliency
```
Some plugins may require additional dependencies in order to be utilized at
runtime.
Such details are described [here](
https://xaitk-saliency.readthedocs.io/en/latest/implementations.html).
See [here for more installation documentation](
https://xaitk-saliency.readthedocs.io/en/latest/installation.html).
## Getting Started
We provide a number of examples based on Jupyter notebooks in the `./examples/`
directory to show usage of the `xaitk-saliency` package in a number of
different contexts.
Contributions are welcome!
See the [CONTRIBUTING.md](./CONTRIBUTING.md) file for details.
## Documentation
Documentation snapshots for releases as well as the latest master are hosted on
[ReadTheDocs](https://xaitk-saliency.readthedocs.io/en/latest/).
The sphinx-based documentation may also be built locally for the most
up-to-date reference:
```bash
# Install dependencies
poetry install
# Navigate to the documentation root.
cd docs
# Build the docs.
poetry run make html
# Open in your favorite browser!
firefox _build/html/index.html
```
## XAITK Saliency Demonstration Tool
This [associated project](https://github.com/XAITK/xaitk-saliency-web-demo)
provides a local web-application that provides a demonstration of visual
saliency generation in a user-interface.
This provides an example of how visual saliency, as generated by this package,
can be utilized in a user-interface to facilitate model and results
exploration.
This tool uses the [trame framework](https://kitware.github.io/trame/).
| ![image1] | ![image2] | ![image3] | ![image4] |
|:---------:|:---------:|:---------:|:---------:|
[image1]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-classification-rise-4.jpg
[image2]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-classification-sliding-window.jpg
[image3]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-detection-retina.jpg
[image4]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-similarity-1.jpg
Raw data
{
"_id": null,
"home_page": "https://github.com/XAITK/xaitk-saliency",
"name": "xaitk-saliency",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<4.0",
"maintainer_email": "",
"keywords": "",
"author": "Kitware, Inc.",
"author_email": "xaitk@kitware.com",
"download_url": "https://files.pythonhosted.org/packages/70/a0/e933c8b6174a69ae06e0f7627647803eaff255b61f260dffed568b62d0c7/xaitk_saliency-0.7.0.tar.gz",
"platform": null,
"description": "\n\n<hr/>\n\n[](https://pypi.org/project/xaitk-saliency/)\n\n[](https://xaitk-saliency.readthedocs.io/en/latest/?badge=latest)\n[](https://github.com/XAITK/xaitk-saliency/actions/workflows/ci-unittests.yml)\n[](https://github.com/XAITK/xaitk-saliency/actions/workflows/ci-example-notebooks.yml)\n[](https://codecov.io/gh/XAITK/xaitk-saliency)\n[](https://lgtm.com/projects/g/XAITK/xaitk-saliency/context:python)\n\n# XAITK - Saliency\nThe `xaitk-saliency` package is an open source, Explainable AI (XAI) framework\nfor visual saliency algorithm interfaces and implementations, built for\nanalytics and autonomy applications.\n\nSee [here](https://xaitk-saliency.readthedocs.io/en/latest/introduction.html)\nfor a more formal introduction to the topic of XAI and visual saliency\nexplanations.\n\nThis framework is a part of the [Explainable AI Toolkit (XAITK)](\nhttps://xaitk.org).\n\n## Supported Algorithms\nThe `xaitk-saliency` package provides saliency algorithms for a wide range of image understanding\ntasks, including image classification, image similarity, object detection, and reinforcement learning.\nThe current list of supported saliency algorithms can be found [here](\nhttps://xaitk-saliency.readthedocs.io/en/latest/introduction.html#saliency-algorithms).\n\n## Target Audience\nThis toolkit is intended to help data scientists and developers who want to\nadd visual saliency explanations to their workflow or product.\nFunctionality provided here is both directly accessible for targeted\nexperimentation, and through [Strategy](\nhttps://en.wikipedia.org/wiki/Strategy_pattern) and [Adapter](\nhttps://en.wikipedia.org/wiki/Adapter_pattern) patterns to allow for\nmodular integration into systems and applications.\n\n## Installation\nInstall the latest release via pip:\n```bash\npip install xaitk-saliency\n```\n\nSome plugins may require additional dependencies in order to be utilized at\nruntime.\nSuch details are described [here](\nhttps://xaitk-saliency.readthedocs.io/en/latest/implementations.html).\n\nSee [here for more installation documentation](\nhttps://xaitk-saliency.readthedocs.io/en/latest/installation.html).\n\n## Getting Started\nWe provide a number of examples based on Jupyter notebooks in the `./examples/`\ndirectory to show usage of the `xaitk-saliency` package in a number of\ndifferent contexts.\n\nContributions are welcome!\nSee the [CONTRIBUTING.md](./CONTRIBUTING.md) file for details.\n\n## Documentation\nDocumentation snapshots for releases as well as the latest master are hosted on\n[ReadTheDocs](https://xaitk-saliency.readthedocs.io/en/latest/).\n\nThe sphinx-based documentation may also be built locally for the most\nup-to-date reference:\n```bash\n# Install dependencies\npoetry install\n# Navigate to the documentation root.\ncd docs\n# Build the docs.\npoetry run make html\n# Open in your favorite browser!\nfirefox _build/html/index.html\n```\n\n## XAITK Saliency Demonstration Tool\nThis [associated project](https://github.com/XAITK/xaitk-saliency-web-demo)\nprovides a local web-application that provides a demonstration of visual\nsaliency generation in a user-interface.\nThis provides an example of how visual saliency, as generated by this package,\ncan be utilized in a user-interface to facilitate model and results\nexploration.\nThis tool uses the [trame framework](https://kitware.github.io/trame/).\n\n| ![image1] | ![image2] | ![image3] | ![image4] |\n|:---------:|:---------:|:---------:|:---------:|\n\n[image1]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-classification-rise-4.jpg\n[image2]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-classification-sliding-window.jpg\n[image3]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-detection-retina.jpg\n[image4]: https://github.com/XAITK/xaitk-saliency-web-demo/blob/main/gallery/xaitk-similarity-1.jpg\n",
"bugtrack_url": null,
"license": "BSD-3-Clause",
"summary": "Visual saliency map generation interfaces and baseline implementations for explainable AI.",
"version": "0.7.0",
"project_urls": {
"Documentation": "https://xaitk-saliency.readthedocs.io/",
"Homepage": "https://github.com/XAITK/xaitk-saliency",
"Repository": "https://github.com/XAITK/xaitk-saliency"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6cfcc9203142a5025ee7d827743c70a85cd8ccde35e35eaae86fe16082d72035",
"md5": "605fdc526cc5b7b41145a139716e311a",
"sha256": "226226e3ac3fc240528c6aaa6d09169c0780877b403d94309df20a823366dd65"
},
"downloads": -1,
"filename": "xaitk_saliency-0.7.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "605fdc526cc5b7b41145a139716e311a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<4.0",
"size": 54295,
"upload_time": "2023-06-19T06:57:22",
"upload_time_iso_8601": "2023-06-19T06:57:22.958156Z",
"url": "https://files.pythonhosted.org/packages/6c/fc/c9203142a5025ee7d827743c70a85cd8ccde35e35eaae86fe16082d72035/xaitk_saliency-0.7.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "70a0e933c8b6174a69ae06e0f7627647803eaff255b61f260dffed568b62d0c7",
"md5": "8273db760e252aee6442adbf9849861c",
"sha256": "1ffa1d0c7f49c795bb087d91fd67d344068f37aad0672588782dd2916942ca4b"
},
"downloads": -1,
"filename": "xaitk_saliency-0.7.0.tar.gz",
"has_sig": false,
"md5_digest": "8273db760e252aee6442adbf9849861c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<4.0",
"size": 34190,
"upload_time": "2023-06-19T06:57:24",
"upload_time_iso_8601": "2023-06-19T06:57:24.365690Z",
"url": "https://files.pythonhosted.org/packages/70/a0/e933c8b6174a69ae06e0f7627647803eaff255b61f260dffed568b62d0c7/xaitk_saliency-0.7.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-19 06:57:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "XAITK",
"github_project": "xaitk-saliency",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "xaitk-saliency"
}
JSON
