Patrick Knab's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
GLIME-General-Stable-and-Local-LIME-Explanation
GLIME is a post-hoc explanation method which is proved to be much more stable and faithful than LIME.
voice-cloning-AI
Voice cloning AI (deepfake for voice). Using cloned voice from only 5-10 seconds of targeted voice.
TimeSeries_Seq2Seq
This repo aims to be a useful collection of notebooks/code for understanding and implementing seq2seq neural networks for time series forecasting. Networks are constructed with keras/tensorflow.
Pytorch-LRP
Basic LRP implementation in PyTorch
lrp_toolbox
The LRP Toolbox provides simple and accessible stand-alone implementations of LRP for artificial neural networks supporting Matlab and Python. The Toolbox realizes LRP functionality for the Caffe Deep Learning Framework as an extension of Caffe source code published in 10/2015.
Lime-For-Time
Application of the LIME algorithm by Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin to the domain of time series classification
Layerwise-Relevance-Propagation
Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers
Tools-to-Design-or-Visualize-Architecture-of-Neural-Network
Tools to Design or Visualize Architecture of Neural Network
keras-grad-cam
An implementation of Grad-CAM with keras