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
GirlfriendGPT
NSFW AI chat platform with customizable characters, AI image generation, and voice chat. Explore roleplay and intimate interactions with AI companions.
View Details
xMates AI
xMates AI is a next-generation AI chat app powered by large language models, offering human-like interactions and roleplaying with customizable AI characters.
View Details
Wan 2.2 Animate
Wan 2.2 Animate is a free online AI tool that transforms any character with advanced AI-powered animations, precise facial expressions, and dynamic body movements without registration.
View Details
Promptix
Promptix is a macOS app that lets you run AI in any application with a hotkey. It helps you write faster, translate, polish text, and use custom prompts.
View Details
BestStock AI
BestStock AI is an AI-powered financial analysis platform, automating data processing and delivering predictive insights across financial instruments.
View DetailsGempix2 AI
Gempix2 AI is a free online AI photo and image editor, powered by NanoBanana 2 technology, offering advanced tools for professional-quality visual transformations.
View Details
AI Animate Image
AI Animate Image revolutionizes how you create animated content from static images. Our advanced AI image animator turns photos into animation with stunning realism.
View Details
Wan 2.2
Wan 2.2 is an open-source AI video generation tool using MoE architecture, transforming text or images into professional 720P cinematic videos.
View Details
Soora2
Soora2 is a global Sora 2 AI video generation platform offering text-to-video, image-to-video, and AI editing tools without watermarks.
View Details