Reverse Dependencies of captum

The following projects have a declared dependency on captum:

• ADGT — Model interpretability for PyTorch
• amuletml — Amulet is a Python machine learning (ML) package to evaluate the susceptibility of different risks to security, privacy, and fairness.
• armory-examples — TwoSix Armory Adversarial Robustness Library Examples
• armory-library — TwoSix Armory Adversarial Robustness Evaluation Library
• AttentionMOI — A Denoised Multi-omics Integration Framework for Cancer Subtype Classification and Survival Prediction.
• AttentionOdorify — Attention based BiLSTM model for Olfactory Analysis
• azureml-automl-dnn-vision — AutoML DNN Vision Models
• beexai — BEExAI: Benchmark to Evaluate Explainable AI
• bias-lens — A library for bias detection and explainable AI methods in NLP models.
• biome-text — Biome-text is a light-weight open source Natural Language Processing toolbox built with AllenNLP
• cabrnet — Generic library for prototype-based classifiers
• chemprobe — A package for chemprobe
• codeflare-torchx — TorchX SDK and Components
• coolstuff — ML-analysis
• DeepLocRNA — Predicting RNA localization based on RBP binding information
• DeepMuon — Interdisciplinary Deep Learning Platform
• denseig — This package contains the required tools to run dense retriever explainability analysis using integrated gradients.
• dive-into-graphs — DIG: Dive into Graphs is a turnkey library for graph deep learning research.
• dnn-cool — DNN.Cool: Multi-task learning for Deep Neural Networks (DNN).
• dynamask — Dynamask - Explaining Time Series Predictions with Dynamic Masks
• ecco — Visualization tools for NLP machine learning models.
• eir-dl — Deep learning framework for genomics and multi-modal data
• EvalXAI — NLP Explainability Benchmarking Framework
• fastai — fastai simplifies training fast and accurate neural nets using modern best practices
• fastAIcourse — fastAIcourse
• ferret-xai — A python package for benchmarking interpretability approaches.
• flexynesis — A deep-learning based multi-omics bulk sequencing data integration suite with a focus on (pre-)clinical endpoint prediction.
• foxai — Model Interpretability for PyTorch.
• fundus-image-toolbox — A toolbox for fundus image analysis
• giotto-deep — Toolbox for Deep Learning and Topological Data Analysis.
• gReLU — gReLU is a python library to train, interpret, and apply deep learning models to DNA sequences
• hiclip — no summary
• imgraph — Graph Neural Network Library Built On Top Of PyTorch and PyTorch Geometric
• incx — no summary
• inseq — Interpretability for Sequence Generation Models 🔍
• intel-xai — Intel® Explainable AI Tools
• joltml — joltml unravels the dark side of machine learning models
• lbster — Language models for Biological Sequence Transformation and Evolutionary Representation.
• lfxai — A framework to explain the latent representations of unsupervised black-box models with the help of usual feature importance and example-based methods.
• liver-ct-segmentation-package — Prediction package for U-Net models trained on the LiTS dataset.
• metaquantus — MetaQuantus is a XAI performance tool for identifying reliable metrics.
• meteors — Explanations of models for Hyperspectral data
• miidl — A Python package for microbial biomarkers identification powered by interpretable deep learning
• mirzai — Prediction of Exchangeable Potassium in Soil through Mid-Infrared Spectroscopy and Deep Learning: from Prediction to Explainability, Albinet et al., 2022
• moleculex — MoleculeX: a new and rapidly growing suite of machine learning methods and software tools for molecule exploration
• neuralprophet — NeuralProphet is an easy to learn framework for interpretable time series forecasting.
• newAI — newAi
• Nubilum — An explainability library for instance segmentation in point clouds
• patchviz — Patch Viz: A library to test how well your model holds up against adversarial attacks
• PerturbNet — PerturbNet
• physioex — A python package for explainable sleep staging via deep learning
• pnpxai — XAI Recommendation Toolkit
• proteinworkshop — no summary
• pyg-nightly — Graph Neural Network Library for PyTorch
• pytorch-tabular — A standard framework for using Deep Learning for tabular data
• quantus — A metrics toolkit to evaluate neural network explanations.
• quarks2-fractal — Integrated image classification and semantic segmentation package
• rld — A development tool for evaluation and interpretability of reinforcement learning agents.
• root-tissue-seg-package — An mlf-core prediction package for root tissue segmentation.
• scCAMEL — scCAMEL: single cell Cross- Annotation and Multimodal Estimation on Lineage trajectory;License: GPL version 3;Developed by: Yizhou Hu, Patrik Ernfors lab, MBB, Karolinska Institutet;Tutorials and other informations in :https://sccamel.readthedocs.io/
• scce — a Single-cell method for predicting Chromatin Conformation based on gene Expression
• scimilarity — Single cell embedding into latent space and retrieving with kNN.
• scReGAT — A GAT-based computational framework to predict long-range gene regulatory relationships
• scSHARP — scSHARP tool for single cell consensus classification
• scvi-tools — Deep probabilistic analysis of single-cell omics data.
• seqexplainer — Interpreting sequence-to-function machine learning models
• shapeaxi — Shape Analysis Exploration and Interpretability
• simplexai — SimplEx - Explaining Latent Representations with a Corpus of Examples
• slime-nlp — SLIME - Statistical and Linguistic Insights for Model Explanation
• sportsml — ML for sports
• spotGUI — spotgui - GUI for the Sequential Parameter Optimization in Python
• spotPython — spotpython - Sequential Parameter Optimization in Python
• tabensemb — A framework to ensemble model bases and evaluate various models for tabular predictions.
• thermostat-datasets — Collection of NLP model explanations and accompanying analysis tools
• time-interpret — Model interpretability library for PyTorch with a focus on time series.
• TimeSeriesML — TimeSeriesML
• torch-geometric — Graph Neural Network Library for PyTorch
• torchFastText — An implementation of the https://github.com/facebookresearch/fastText supervised learning algorithm for text classification using Pytorch.
• torchx — TorchX SDK and Components
• torchx-applovin — TorchX SDK and Components
• torchx-nightly — TorchX SDK and Components
• trame-sandtank-xai — AI/XAI exploration in the context of ParFlow simulation code
• transformers-interpret — Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
• transformers-visualizer — Explain your 🤗 transformers without effort! Display the internal behavior of your model.
• transmep — Transfer learning for Mutation Effect Prediction
• tsCaptum — A Captum wrapper for Time Series XAI
• TSInterpret — todo
• xai-evals — A package for model explainability and explainability comparision for tabular data
• xaiev — Add your description here