Captum
AI ModelsTags
Website
Free
AI Developer Tools
AI Models
Open Source AI Models
AI Research Tool
Introduction
Captum is a PyTorch library for model interpretability. It provides tools and techniques to understand and attribute the predictions of PyTorch models across various modalities, including vision and text. Captum supports most PyTorch models and allows for easy implementation and benchmarking of new interpretability algorithms.
How To Use
Install Captum via conda or pip. Import necessary libraries like numpy, torch, and IntegratedGradients from captum.attr. Define and prepare your PyTorch model. Instantiate an interpretability algorithm (e.g., IntegratedGradients). Apply the algorithm to your input data and baseline to obtain attributions and convergence delta.
Pricing
| Packages | Pricing | Features |
|---|---|---|
| Free Edition | Free | Unlimited public repositories, limited private repositories |
| Team Edition | $4/user/month | Unlimited private repositories, basic features |
| Enterprise Edition | $21/user/month | Advanced security and auditing features |
