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
adly.news is a free platform that simplifies newsletter advertising, connecting businesses with engaged audiences through ad slots, offering bidding, negotiation, and messaging.
View Details
CrePal
CrePal is the world's first AI Video Creation Agent, transforming ideas into stunning videos with cutting-edge AI models for planning, imaging, and video generation.
View Details
Yolly AI
Yolly AI is an all-in-one AI video & photo generator that lets you turn a single text prompt into cinema-grade 4K videos or high-resolution images.
View Details
Seedance 1.5
Seedance 1.5 is a next-generation AI video creation tool transforming ideas into stunning 1080p videos with multi-shot narratives, physics-accurate motion, and cinematic quality.
View Details
Unblur Image Online Free
Unblur Image Online Free instantly restores sharpness to blurry photos using AI. Upload JPG, PNG, or WEBP files for clear images in seconds, completely free and no sign-up needed.
View Details
DeVoice
DeVoice is an AI-powered audio and video tool that offers unlimited, accurate transcription, AI rap generation, and background noise removal capabilities.
View Details
DeepSwapAI
DeepSwapAI is a professional AI face swap platform for developers, offering enterprise-grade face exchange technology with RESTful API, SDKs, and batch processing.
View DetailsFace Swap AI
Face Swap AI is a free AI tool for instant face swapping in photos and videos, delivering stunning HD results without signup or watermarks for creative projects.
View Details
StoryShort
StoryShort is an AI creation tool that helps you create viral faceless videos on auto-pilot, generating engaging content in minutes.
View Details
AIhumanize
AIhumanize is an advanced AI humanizer tool that transforms AI-written text into natural, authentic writing, helping you bypass all major AI detectors.
View Details
LoveGen AI
LoveGen AI is an all-in-one platform integrating major image and video AI models, enabling creation from text, visual enhancement, and video generation.
View Details