The rAI-toolbox is designed to enable methods for evaluating and enhancing both the
robustness and the explainability of AI models in a way that is scalable and that
composes naturally with other popular ML frameworks.
A key design principle of the rAI-toolbox is that it adheres strictly to the APIs
specified by the PyTorch machine learning framework. For example, the rAI-toolbox frames
adversarial training workflows solely in terms of the `torch.nn.Optimizer` and
`torch.nn.Module` APIs. This makes it trivial to leverage other libraries and
frameworks from the PyTorch ecosystem to bolster your responsible AI R&D. For
instance, one can naturally leverage the rAI-toolbox together with
PyTorch Lightning to perform distributed adversarial training.
Raw data
{
"_id": null,
"home_page": "https://github.com/mit-ll-responsible-ai/responsible-ai-toolbox",
"name": "rai-toolbox",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "machine learning robustness pytorch responsible AI",
"author": "Ryan Soklaski, Justin Goodwin, Olivia Brown, Michael Yee",
"author_email": "ryan.soklaski@ll.mit.edu",
"download_url": "https://files.pythonhosted.org/packages/50/5c/984495d9ea9889f67f1afba2d91d32bcd13621e8bee117aa84c8464efd8c/rai_toolbox-0.2.1.tar.gz",
"platform": null,
"description": "\nThe rAI-toolbox is designed to enable methods for evaluating and enhancing both the\nrobustness and the explainability of AI models in a way that is scalable and that\ncomposes naturally with other popular ML frameworks.\n\nA key design principle of the rAI-toolbox is that it adheres strictly to the APIs\nspecified by the PyTorch machine learning framework. For example, the rAI-toolbox frames\nadversarial training workflows solely in terms of the `torch.nn.Optimizer` and\n`torch.nn.Module` APIs. This makes it trivial to leverage other libraries and\nframeworks from the PyTorch ecosystem to bolster your responsible AI R&D. For\ninstance, one can naturally leverage the rAI-toolbox together with\nPyTorch Lightning to perform distributed adversarial training.\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "PyTorch-centric library for evaluating and enhancing the robustness of AI technologies",
"version": "0.2.1",
"project_urls": {
"Download": "https://github.com/mit-ll-responsible-ai/responsible-ai-toolbox/tarball/v0.2.1",
"Homepage": "https://github.com/mit-ll-responsible-ai/responsible-ai-toolbox"
},
"split_keywords": [
"machine",
"learning",
"robustness",
"pytorch",
"responsible",
"ai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7eacf8b5e3c314acd1ea5a4d5f14b529c0cf2c3e37356800ad35c892174aeebb",
"md5": "731bea49b9b2fdcff891ebcfd52e661e",
"sha256": "489c3d2724e0012febca29eacc5251eb8a0cecac37f3f266b0f79c7e41177285"
},
"downloads": -1,
"filename": "rai_toolbox-0.2.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "731bea49b9b2fdcff891ebcfd52e661e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 92789,
"upload_time": "2022-06-16T17:59:19",
"upload_time_iso_8601": "2022-06-16T17:59:19.968537Z",
"url": "https://files.pythonhosted.org/packages/7e/ac/f8b5e3c314acd1ea5a4d5f14b529c0cf2c3e37356800ad35c892174aeebb/rai_toolbox-0.2.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "505c984495d9ea9889f67f1afba2d91d32bcd13621e8bee117aa84c8464efd8c",
"md5": "b5a0006be5828e44d0f8c738a9bc1881",
"sha256": "f265d8ee88f4874da884d09cc9435c48131723d9e341a365101310ae04988a60"
},
"downloads": -1,
"filename": "rai_toolbox-0.2.1.tar.gz",
"has_sig": false,
"md5_digest": "b5a0006be5828e44d0f8c738a9bc1881",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 88136,
"upload_time": "2022-06-16T17:59:21",
"upload_time_iso_8601": "2022-06-16T17:59:21.218476Z",
"url": "https://files.pythonhosted.org/packages/50/5c/984495d9ea9889f67f1afba2d91d32bcd13621e8bee117aa84c8464efd8c/rai_toolbox-0.2.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-06-16 17:59:21",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "mit-ll-responsible-ai",
"github_project": "responsible-ai-toolbox",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "rai-toolbox"
}
JSON
