Captum
Click to visit website
About
Captum is an open-source model interpretability library built on PyTorch, designed to help users understand the predictions of their AI models. It supports interpretability across various modalities, including vision and text, and integrates seamlessly with most PyTorch models with minimal modifications. Captum offers a generic and extensible framework for interpretability research, making it easy to implement and benchmark new algorithms. It provides a range of attribution methods to explain how important each input value is to a particular output scalar value, aiding in debugging and improving model understanding.
Platform
Features
• built on pytorch
• multi-modal support
• extensible for research
FAQs
How do I set the target parameter to an attribution method?
Target selects a scalar output value. For 2D output (N x classes), pass an integer (0,1,2) or tensor ([0,1,0,0]). For >2D, pass a tuple of indices (2,3,2) or a list of tuples.
I am facing Out-Of-Memory (OOM) errors when using Captum. How do I resolve this?
Reduce `n_steps` or use `internal_batch_size` for methods with this arg. For perturbation methods, reduce `perturbations_per_eval`. For others, try smaller input batch sizes.
I am using a perturbation based method, and attributions are taking too long to compute. How can I speed it up?
Increase `perturbations_per_eval` if memory allows. You can also use PyTorch's `DataParallel` or `DistributedDataParallel` if multiple GPUs are available to speed up computations.
Are SmoothGrad or VarGrad supported in Captum?
Yes, SmoothGrad and VarGrad are supported through `NoiseTunnel` in Captum. This functionality can be used with any attribution algorithm available within the Captum library.
How do I use Captum with BERT models?
Captum provides a dedicated tutorial demonstrating the usage of Integrated Gradients specifically for BERT models. Refer to the documentation's "Bert SQUAD Interpret" tutorial for details.
My model inputs or outputs token indices, and when using Captum I see errors relating to gradients, how do I resolve this?
Replace embedding layer with `InterpretableEmbedding` or use `LayerIntegratedGradients` for input token indices. For output token indices, attribute with respect to token score/probability.
Can my model use functional non-linearities (E.g. nn.functional.ReLU) or can reused modules be used with Captum?
Most methods work, but DeepLift-based/Guided Backprop/Deconvolution require `torch.nn.ReLU` modules, not functional ones, and don't reuse modules to avoid issues with multipliers.
Do JIT models, DataParallel models, or DistributedDataParallel models work with Captum?
Yes, all are supported. JIT models do not support hooks, so layer/neuron attribution, DeepLift, Guided Backprop, and Deconvolution are not supported with JIT models.
I am working on a new interpretability or attribution method and would like to add it to Captum. How do I proceed?
Captum offers an "Awesome List" for external projects and considers new algorithms for its `contrib` package. Proposals are reviewed case-by-case based on publication, evaluation, etc.
How can I resolve cudnn RNN backward error for RNN or LSTM network?
To resolve "cudnn RNN backward can only be called in training mode" in eval mode for RNN/LSTM, set `torch.backends.cudnn.enabled=False`. CuDNN doesn't support gradient computation in eval mode.
Job Opportunities
There are currently no job postings for this AI tool.
Ratings & Reviews
No ratings available yet. Be the first to rate this tool!
Alternatives
Interpretable AI
Interpretable AI is a suite of software modules providing comprehensive tools for interpretable machine learning, including optimal trees, imputation, and feature selection.
View DetailsFeatured Tools
adly.news
Connect with engaged niche audiences or monetize your subscriber base through an automated marketplace featuring verified metrics and secure Stripe payments.
View Details
EveryDev.ai
Accelerate your development workflow by discovering cutting-edge AI tools, staying updated on industry news, and joining a community of builders shipping with AI.
View Details
Whisk AI
Create professional 4K artwork by blending subject, scene, and style images using advanced AI. Perfect for designers and marketers needing fast, custom visuals.
View Details
APIPASS
Access hundreds of leading AI models like Kling, Runway, and Claude through a single unified API to build scalable image and video generation applications.
View Details
VO4 AI
Transform text prompts and static images into professional, watermark-free cinematic videos for social media and marketing using advanced AI motion technology.
View Details
Seedance 2.0
Generate broadcast-quality 4K videos from simple text prompts with precise text rendering, high-fidelity visuals, and batch processing for content creators.
View Details
BeatViz
Create professional, rhythm-synced music videos instantly with AI-powered visual generation, ideal for independent artists, social media creators, and marketers.
View Details
Seedance 2.0
Generate cinematic 1080p videos from text or images using advanced motion synthesis and multi-shot storytelling for marketing, social media, and creators.
View Details
Seedream 5.0
Transform text descriptions into high-resolution 4K visuals and edit photos using advanced AI models designed for digital artists and e-commerce businesses.
View Details
Seedream 5.0
Generate professional 4K AI images and edit visuals using natural language commands with high-speed processing for marketers, artists, and e-commerce brands.
View Details
Kaomojiya
Enhance digital messages with thousands of unique Japanese kaomoji across 491 categories, featuring one-click copying and AI-powered custom generation.
View Details
VO4 AI
Transform text prompts and static images into professional 1080p cinematic videos with advanced multi-shot storytelling, motion synthesis, and Full HD output.
View Details