{"id":15905735,"url":"https://github.com/episci/safeai","last_synced_at":"2025-03-21T01:31:54.863Z","repository":{"id":57463542,"uuid":"152261399","full_name":"EpiSci/SafeAI","owner":"EpiSci","description":"Reusable, Easy-to-use Uncertainty module package built with Tensorflow, Keras","archived":false,"fork":false,"pushed_at":"2018-12-31T02:04:34.000Z","size":197,"stargazers_count":14,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-13T13:22:46.045Z","etag":null,"topics":["bayesian-neural-networks","classification","models","tensorflow","uncertainty"],"latest_commit_sha":null,"homepage":"","language":"Python","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/EpiSci.png","metadata":{"files":{"readme":"README.md","changelog":"ChangeLog","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-10-09T14:03:04.000Z","updated_at":"2023-07-24T03:36:10.000Z","dependencies_parsed_at":"2022-09-14T16:40:38.713Z","dependency_job_id":null,"html_url":"https://github.com/EpiSci/SafeAI","commit_stats":null,"previous_names":["episysscience/safeai"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EpiSci%2FSafeAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EpiSci%2FSafeAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EpiSci%2FSafeAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EpiSci%2FSafeAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EpiSci","download_url":"https://codeload.github.com/EpiSci/SafeAI/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244721271,"owners_count":20498922,"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":["bayesian-neural-networks","classification","models","tensorflow","uncertainty"],"created_at":"2024-10-06T13:07:47.747Z","updated_at":"2025-03-21T01:31:54.576Z","avatar_url":"https://github.com/EpiSci.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SafeAI: Predictive Uncertainty DL Models\n[![EpiSci](https://img.shields.io/badge/Episys-Science-5fa9d3.svg)](http://www.episci.com/)\n[![CircleCI](https://circleci.com/gh/EpiSci/SafeAI.svg?style=svg)](https://circleci.com/gh/EpiSci/SafeAI)\n[![Maintainability](https://api.codeclimate.com/v1/badges/2d74bd6e1afde4373ddb/maintainability)](https://codeclimate.com/github/EpiSci/SafeAI/maintainability)\n[![Test Coverage](https://api.codeclimate.com/v1/badges/2d74bd6e1afde4373ddb/test_coverage)](https://codeclimate.com/github/EpiSci/SafeAI/test_coverage)  \n[![python](https://img.shields.io/badge/python-3.6_|2.7-blue.svg)](https://www.python.org/)\n[![tensorflow](https://img.shields.io/badge/tensorflow-1.10-ed6c20.svg)](https://www.tensorflow.org/)\n[![PyPI version shields.io](https://img.shields.io/pypi/v/safeai.svg)](https://pypi.python.org/pypi/safeai/)\n![GitHub](https://img.shields.io/github/license/mashape/apistatus.svg)\n\n\u003cimg src=./assets/SafeguardAI-logo.png width=\"490px\" height=\"210px\"\u003e  \n\nReusable, easy-to-use tensorflow uncertainty module package.  \nUnder active development.\n\n## Predictive Uncertainty in Deep Learning Models:\nConsidering deep learning workflow, uncertainty plays a critical role when applying in real\napplications and is essential property in a safety issue. Autonomous driving,\nrobotics, or critical decision-making, for instance, such domains are especially\ncaring for safety which is uncertainty in deep learning.  \n\nRecently, plenty of researches related to uncertainty is actively ongoing.\nIn this project, we leverage TensorFlow to additionally model uncertainty in standard\ndeep learning architectures. Essentially, we focus on reusability and easy-to-use that\nonly least numbers of parameters are necessary to run target functions.\n\n\n## Installation\n```bash\n# Install using pip\n$ pip install safeai\n\n# Or, install from source:\n$ git clone https://github.com/EpiSci/SafeAI \u0026\u0026\\\n$ cd SafeAI \u0026\u0026 pip install -e .\n```\n\n#### Tensorflow, Python version\nCurrently, SafeAI is being developed and tested with tensorflow version **1.10**,\nunder both python version **3.6** and **2.7**.  \n\n## SafeAI models\nSafeAI models are implemented -- [introducing overall concept of our code.]\n```python\nimport tensorflow as tf\nfrom safeai.models import confident_classifier\n\nMESSAGE = \"And Short, intuitive sample code goes here\"\n```\n\n## Run other examples \u0026 test code\nEvery python code in SafeAI was not meant to be directly run as a single script.\nPlease have them executed as a module, with [-m flag](https://docs.python.org/3.7/using/cmdline.html#cmdoption-m) \nfor testing and running the examples in the project.  \nAlso **they need to be run from project root folder**, not at `examples/` directory, nor `safeai/tests/`.\n```bash\n# Clone project, cd into project, install dependencies\n$ git clone https://github.com/EpiSci/SafeAI \u0026\u0026\\\n$ cd SafeAI \u0026\u0026 pip install -e .\n\n# To run the example:\n$ python -m examples.[script name without '.py'] # e.g.) python -m examples.joint_confident\n\n# To execute all tests\n$ python -m unittest discover\n```\n## List of predictive uncertainty models available:\n- **Joint Confident Classifier** [(safeai/models/joint_confident.py)](https://github.com/EpiSci/SafeAI/blob/master/safeai/models/joint_confident/joint_confident.py)  \n: *Training Confidence-Calibrated Classifier for Detecting Out-of-distribution Samples(2017)*  \nKimin Lee et al | [arxiv.org/abs](https://arxiv.org/abs/1711.09325) | [Author's repository](https://github.com/alinlab/Confident_classifier)  \n\n- List other models in the same form as above\n\n## Contribute to project:\nWe appreciate your interest in this project!  \nBefore making an issue, please consider reading [Our contribution guideline.](https://github.com/EpiSci/SafeAI/blob/master/CONTRIBUTING.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fepisci%2Fsafeai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fepisci%2Fsafeai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fepisci%2Fsafeai/lists"}