{"id":13434249,"url":"https://github.com/datamllab/xdeep","last_synced_at":"2025-03-17T14:31:02.259Z","repository":{"id":62589829,"uuid":"175529897","full_name":"datamllab/xdeep","owner":"datamllab","description":null,"archived":false,"fork":false,"pushed_at":"2020-05-17T20:40:42.000Z","size":13034,"stargazers_count":42,"open_issues_count":3,"forks_count":8,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-04-25T23:42:51.777Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/datamllab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-03-14T01:58:29.000Z","updated_at":"2023-12-22T21:12:45.000Z","dependencies_parsed_at":"2022-11-03T17:57:01.908Z","dependency_job_id":null,"html_url":"https://github.com/datamllab/xdeep","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamllab%2Fxdeep","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamllab%2Fxdeep/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamllab%2Fxdeep/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datamllab%2Fxdeep/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datamllab","download_url":"https://codeload.github.com/datamllab/xdeep/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244050093,"owners_count":20389639,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T02:01:51.058Z","updated_at":"2025-03-17T14:31:02.247Z","avatar_url":"https://github.com/datamllab.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","Acceleration of Feature Interaction Detection","Technical Resources"],"sub_categories":["Reinforcement Method","Open Source/Access Responsible AI Software Packages"],"readme":"# XDeep \n## -- *for interpretable deep learning developers*\n\n[![Codacy Badge](https://api.codacy.com/project/badge/Grade/2c0aff755250450c90ba167987aaebe5)](https://www.codacy.com/manual/nacoyang/xdeep?utm_source=github.com\u0026amp;utm_medium=referral\u0026amp;utm_content=datamllab/xdeep\u0026amp;utm_campaign=Badge_Grade)\n[![Build Status](https://travis-ci.com/datamllab/xdeep.svg?branch=master)](https://travis-ci.com/datamllab/xdeep)\n\nXDeep is an open source Python library for **Interpretable Machine Learning**. It is developed by [DATA Lab](http://faculty.cs.tamu.edu/xiahu/index.html) at Texas A\u0026M University. The goal of XDeep is to provide easily accessible interpretation tools for people who want to figure out how deep models work. XDeep provides a variety of methods to interpret a model both locally and globally.\n\n## Installation\n\nTo install the package, please use the pip installation as follows (https://pypi.org/project/x-deep/): \n\n    pip install x-deep\n\n**Note**: currently, XDeep is only compatible with: **Python 3.6**.\n\n## Example\n\nHere is a short example of using the package.\n\n```python\nimport torchvision.models as models\nfrom xdeep.xlocal.gradient.explainers import *\n\n# load the input image \u0026 target deep model\nimage = load_image('input.jpg')\nmodel = models.vgg16(pretrained=True)\n\n# build the xdeep explainer\nmodel_explainer = ImageInterpreter(model)\n\n# generate the local interpretation\nmodel_explainer.explain(image, method_name='gradcam', target_layer_name='features_29', viz=True) \n```\n\nFor detailed tutorial, please check the docs directory of this repository [here](https://github.com/datamllab/xdeep/tree/master/docs).\n\n## Sample Results\n\n\u003cimg src=\"https://github.com/datamllab/xdeep/blob/master/result_img/ensemble_fig.png\" width=\"100%\" height=\"100%\"\u003e\n\n## Cite this work\n\nFan Yang, Zijian Zhang, Haofan Wang, Yuening Li, Xia Hu \"XDeep: An Interpretation Tool for Deep Neural Networks.\" arXiv:1911.01005, 2019. ([Download](https://arxiv.org/abs/1911.01005))\n\nBiblatex entry:\n\n    @article{yang2019xdeep,\n             title={XDeep: An Interpretation Tool for Deep Neural Networks},\n             author={Yang, Fan and Zhang, Zijian and Wang, Haofan and Li, Yuening and Hu, Xia},\n             journal={arXiv preprint arXiv:1911.01005},\n             year={2019}\n            }\n\n## DISCLAIMER\n\nPlease note that this is a **pre-release** version of the XDeep which is still undergoing final testing before its official release. The website, its software and all contents found on it are provided on an\n“as is” and “as available” basis. XDeep does **not** give any warranties, whether express or implied, as to the suitability or usability of the website, its software or any of its content. XDeep will **not** be liable for any loss, whether such loss is direct, indirect, special or consequential, suffered by any party as a result of their use of the libraries or content. Any usage of the libraries is done at the user’s own risk and the user will be solely responsible for any damage to any computer system or loss of data that results from such activities. Should you encounter any bugs, glitches, lack of functionality or\nother problems on the website, please let us know immediately so we\ncan rectify these accordingly. Your help in this regard is greatly appreciated. \n\n## Contact\n\nPlease send emails to *nacoyang@tamu.edu* if you have any issues for this project. Thanks.\n\n## Acknowledgements\n\nThe authors gratefully acknowledge the XAI program of the Defense Advanced Research Projects Agency (DARPA) administered through grant N66001-17-2-4031; the Texas A\u0026M College of Engineering, and Texas A\u0026M. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatamllab%2Fxdeep","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatamllab%2Fxdeep","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatamllab%2Fxdeep/lists"}