deel-ai / influenciae
π Influenciae is a Tensorflow Toolbox for Influence Functions
β61Updated 11 months ago
Alternatives and similar repositories for influenciae:
Users that are interested in influenciae are comparing it to the libraries listed below
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ94Updated last week
- Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.β56Updated 3 weeks ago
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β29Updated last month
- β28Updated 11 months ago
- π Xplique is a Neural Networks Explainability Toolboxβ674Updated 5 months ago
- π Puncc is a python library for predictive uncertainty quantification using conformal prediction.β316Updated 2 months ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ34Updated 11 months ago
- β13Updated 2 years ago
- π Overcomplete is a Vision-based SAE Toolboxβ42Updated this week
- π Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)β27Updated 2 years ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computationβ117Updated last week
- β10Updated 4 months ago
- Conformal prediction for uncertainty quantification in image segmentationβ21Updated 3 months ago
- OpenXAI : Towards a Transparent Evaluation of Model Explanationsβ240Updated 7 months ago
- Launching and monitoring Slurm experiments in Pythonβ17Updated this week
- A toolkit for quantitative evaluation of data attribution methods.β43Updated last week
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β62Updated last year
- LENS Projectβ47Updated last year
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotligβ¦β146Updated 2 years ago
- Specificy, execute and monitor performances of active learning pipelines.β22Updated 5 months ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true claβ¦