deel-ai / orthogoniumLinks
New implementations of old orthogonal layers unlock large scale training.
β19Updated last month
Alternatives and similar repositories for orthogonium
Users that are interested in orthogonium are comparing it to the libraries listed below
Sorting:
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ63Updated last year
- Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.β58Updated last week
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ97Updated 4 months ago
- β37Updated last month
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β32Updated this week
- πͺ Interpreto is an interpretability toolbox for LLMsβ34Updated this week
- β14Updated 3 months ago
- π Overcomplete is a Vision-based SAE Toolboxβ71Updated last week
- LENS Projectβ48Updated last year
- Certified robustness of deep neural networksβ19Updated 11 months ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ37Updated last year
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.β229Updated last week
- RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]β729Updated 4 months ago
- β12Updated 3 years ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorchβ337Updated last year
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β66Updated 2 years ago
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.β16Updated last month
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β18Updated last year
- β16Updated last week
- Certified robustness "for free" using off-the-shelf diffusion models and classifiersβ43Updated 2 years ago
- π Xplique is a Neural Networks Explainability Toolboxβ696Updated 10 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ131Updated last year
- Code for Spectral Norm of Convolutional Layers with Circular and Zero Paddings and Efficient Bound of Lipschitz Constant for Convolutionaβ¦β14Updated last year
- Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning)β¦β264Updated this week
- Python package to accelerate research on generalized out-of-distribution (OOD) detection.β12Updated last year
- Source Code of the ROAD benchmark for feature attribution methods (ICML22)β23Updated 2 years ago
- reference implementation for "explanations can be manipulated and geometry is to blame"β36Updated 3 years ago
- A toolkit for quantitative evaluation of data attribution methods.β53Updated 3 weeks ago
- Source code of "What can linearized neural networks actually say about generalization?β20Updated 3 years ago
- A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.β946Updated last year