What-If Tool
Visually probe the behavior of trained machine learning models, without coding.Using WIT, you can test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data, and for different ML fairness metrics
Category
Machine Learning,Predictive Models,artificial intelligence
Industry
This is a super useful tool to assess the performance of the models without coding. WIT visually displays how model behavior changes over time and over different subsets of data. You can also compare the performance of two models to see which one works best.
Model probing, from within any workflow
Platforms and Integrations
Compatible models
and frameworks
TF Estimators
Models served by TF serving
Cloud AI Platform Models
Models that can be wrapped in a python function
Supported data and task types
Binary classification
Multi-class classification
Regression
Tabular, Image, Text data
Free
No items found.