pytorch tabular provides a unified framework for deep learning models on tabular data.
Open source
24 alternativesCaptum
Captum explains model behavior and supports interpretability analysis for PyTorch systems.
About Captum
Captum is an open source interpretability library for PyTorch. It implements attribution methods including integrated gradients, saliency maps, SmoothGrad, VarGrad, TCAV, and TracIn, and provides adversarial attacks and minimal input perturbation for counterfactual analysis. It can examine input features as well as neurons, layers, concepts, and training examples, and integrates with models built with libraries such as torchvision and torchtext.
Installation requires Python 3.10 or later and PyTorch 2.3 or later, with release installs via pip.
Key features
- Integrated Gradients attribution for PyTorch models
- Saliency maps, SmoothGrad and VarGrad implementations
- Concept-based explanation with Testing with Concept Activation Vectors
- Training-example influence analysis with TracIn
- Adversarial attacks and minimal input perturbation for counterfactuals
- Layer conductance and neuron conductance analysis
Best for: Model developers and interpretability researchers working with PyTorch models who need to analyze feature, concept, or training-example influence.
Good for
- Covers input, neuron, layer, concept, and training-example analysis in one library
- Integrates with models built with torchvision, torchtext, and other domain libraries
- Supports benchmarking new methods against included algorithms
Watch out for
- Requires Python 3.10 or later and PyTorch 2.3 or later
- Designed for PyTorch models, not other frameworks
Captum at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Captum alternatives
Tools and sites you could use instead, ranked by how closely they match.
PyTorch Frame provides a library for applying deep learning models to tabular data.
Open source
24 alternatives
Python package which helps to debug machine learning classifiers and explain their predictions.
Open source
24 alternatives
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Open source
24 alternatives
This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.
Open source
24 alternatives
PyTorch Geometric provides graph neural network tools and libraries for PyTorch projects.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
Captum FAQ
What is required to install Captum?
Python 3.10 or later and PyTorch 2.3 or later. The release version installs with pip install captum.
Which models does Captum work with?
PyTorch models, including models built with domain-specific libraries such as torchvision and torchtext.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.