The Learning Interpretability Tool (LIT, formerly known as the Language Interpretability Tool) is a visual, interactive ML model-understanding tool that supports text, image, and tabular data. It can be run as a standalone server, or inside of notebook environments such as Colab, Jupyter, and Google Cloud Vertex AI notebooks.
Features
- Documentation available
- Local explanations via salience maps and rich visualization of model predictions
- Aggregate analysis including custom metrics, slicing and binning, and visualization of embedding spaces
- Counterfactual generation via manual edits or generator plug-ins to dynamically create and evaluate new examples
- Side-by-side mode to compare two or more models, or one model on a pair of examples
- Framework-agnostic and compatible with TensorFlow, PyTorch, and more
Categories
Machine LearningLicense
Apache License V2.0Follow Learning Interpretability Tool
You Might Also Like
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Learning Interpretability Tool!