DEEL

Craft

👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)

deel-lip

Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers

deel-torchlip

Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see https://github.com/deel-ai/deel-lip

FairSense

This library allow to compute global sensitivity indices in the context of fairness measurements.

influenciae

👋 Influenciae is a Tensorflow Toolbox for Influence Functions

LARD

A runway dataset and a generator of synthetic aerial images with automatic labeling.

lipdp

Lipdp leverages Lipchitz constraints to train differentially private networks without clipping.

oodeel

Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.

puncc

👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.

xplique

👋 Xplique is a Neural Networks Explainability Toolbox

deel-ai/xplique

👋 Xplique is a Neural Networks Explainability Toolbox

deel-ai/puncc

👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.

deel-ai/deel-lip

Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers

deel-ai/LARD

A runway dataset and a generator of synthetic aerial images with automatic labeling.

deel-ai/influenciae

👋 Influenciae is a Tensorflow Toolbox for Influence Functions

deel-ai/oodeel

Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.

deel-ai/Craft

👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)

deel-ai/deel-torchlip

Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see https://github.com/deel-ai/deel-lip

deel-ai/FairSense

This library allow to compute global sensitivity indices in the context of fairness measurements.

deel-ai/lipdp

Lipdp leverages Lipchitz constraints to train differentially private networks without clipping.

deel-ai/deel_dataset_manager

deel-ai/hijacking-acas

Experiment results for the ERTS2022 article

deel-ai/relu-prime

deel-ai/deel-with-augmentation

This repository contains the work of Vuong Nguyen that was conducted during his apprenticeship with the DEEL team. Namely, Vuong conducted several experiments to challenge generative data augmentation techniques from a Fairness perspective. He worked under the supervision of Lucas Hervier and Agustin Picard.