https://github.com/PAIR-code/what-if-tool

Source code/webpage/demos for the What-If Tool
https://github.com/PAIR-code/what-if-tool

colaboratory jupyterlab-extension machine-learning ml-fairness tensorboard visualization

Last synced: 3 months ago
JSON representation

Source code/webpage/demos for the What-If Tool

• Host: GitHub
• URL: https://github.com/PAIR-code/what-if-tool
• Owner: PAIR-code
• License: apache-2.0
• Created: 2018-09-07T20:26:10.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2024-09-11T20:07:00.000Z (5 months ago)
• Last Synced: 2024-10-15T11:01:30.807Z (3 months ago)
• Topics: colaboratory, jupyterlab-extension, machine-learning, ml-fairness, tensorboard, visualization
• Language: HTML
• Homepage: https://pair-code.github.io/what-if-tool
• Size: 204 MB
• Stars: 910
• Watchers: 29
• Forks: 170
• Open Issues: 90
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-jupyter-resources - GitHub - 52% open · ⏱️ 05.01.2022): (交互式小部件和可视化)
• best-of-jupyter - GitHub - 61% open · ⏱️ 01.02.2024): (Interactive Widgets & Visualization)
• StarryDivineSky - PAIR-code/what-if-tool - If Tool(WIT) 是一个用于深入理解黑盒分类或回归机器学习模型的工具，它提供了一个易于使用的界面，可以对大量示例进行推理并以多种方式可视化结果。用户可以手动或以编程方式编辑示例，并重新运行模型以查看更改带来的结果。WIT 还包含用于调查模型性能和公平性的工具，并能够在数据集子集上进行分析。WIT 的目标是为用户提供一个简单、直观且强大的方式，让他们无需编写任何代码即可通过可视化界面与训练好的机器学习模型进行交互。WIT 可以通过 TensorBoard 访问，也可以作为 Jupyter 或 Colab 笔记本的扩展使用。该项目提供了一系列Web 和 Colab 演示，用户可以轻松上手体验。 (其他_机器学习与深度学习)
• AwesomeResponsibleAI - What-If Tool
• Awesome-explainable-AI - https://github.com/PAIR-code/what-if-tool - code/what-if-tool?style=social) (Python Libraries(sort in alphabeta order) / Evaluation methods)
• awesome-python-machine-learning-resources - GitHub - 52% open · ⏱️ 05.01.2022): (模型的可解释性)
• awesome-xai - PAIR-code/what-if-tool - A tool for Tensorboard or Notebooks which allows investigating model performance and fairness. (Repositories / Critiques)