Captum · Model Interpretability for PyTorch
Interpret models in PyTorch
Score
60
User Rating
3.0
Free/Trial Support
Supported
Starting Price
--
Last Updated
Aug 14, 2026
Overview
What is Captum · Model Interpretability for PyTorch?
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.
What is Captum · Model Interpretability for PyTorch used for?
Tags
Top Features
- Multi-modal interpretability support
- Built on PyTorch
- Extensible and open source
How to use Captum · Model Interpretability for PyTorch?
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.
Alternative Tools
No alternative tools found
Pros & Cons
No Data
Use Cases
- Understanding feature importance in image classification models
- Analyzing the influence of words in text classification models
Captum · Model Interpretability for PyTorch Pricing
Free PlanSubscription Plan
No detailed pricing information available
User Reviews
3.0
out of 5
3.0
No reviews yet
Be the first to review this tool!