Stars
Code for the Proceedings of the National Academy of Sciences 2020 article, "Understanding the Role of Individual Units in a Deep Neural Network"
Implementation of a list sweeper: instead of the cartesian product, sweep over the zipped list
Algorithm and data structure articles for https://cp-algorithms.com (based on https://e-maxx.ru)
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.
A platform for managing machine learning experiments
moai is a PyTorch-based AI Model Development Kit (MDK) created to improve data-driven model workflows, design and reproducibility.
CoRelAy is a tool to compose small-scale (single-machine) analysis pipelines.
ViRelAy is a visualization tool for the analysis of data as generated by CoRelAy.
A python library for self-supervised learning on images.
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
Image restoration with neural networks but without learning.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
The pretrained models trained on Moments in Time Dataset
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
A toolbox to iNNvestigate neural networks' predictions!
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization
IBD: Interpretable Basis Decomposition for Visual Explanation
getos.c is an Open Source script that tries to fingerprint the operating system of a remote host using the default TTL reply of ping.
Open Source Chrome/Edge extension that changes the CSS style of a website for better reading experience.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
Hydra is a framework for elegantly configuring complex applications
Configuration classes enabling type-safe PyTorch configuration for Hydra apps
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …
This repository contains the main code which performs learning and construction of the memory
'Robust Semantic Interpretability: Revisiting Concept Activation Vectors' Official Implementation
FSL-Mate: A collection of resources for few-shot learning (FSL).