sebastian-lapuschkin / lrp_toolboxLinks
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.
☆334Updated 3 years ago
Alternatives and similar repositories for lrp_toolbox
Users that are interested in lrp_toolbox are comparing it to the libraries listed below
Sorting:
- ☆100Updated 7 years ago
- A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also in…☆754Updated 4 years ago
- Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers☆99Updated 7 years ago
- A toolbox to iNNvestigate neural networks' predictions!☆1,303Updated 4 months ago
- Layer-wise Relevance Propagation (LRP) for LSTMs.☆225Updated 5 years ago
- Attributing predictions made by the Inception network using the Integrated Gradients method☆634Updated 3 years ago
- Code for the TCAV ML interpretability project☆642Updated 2 months ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆128Updated 4 years ago
- Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).☆982Updated last year
- ☆112Updated 2 years ago
- Detect model's attention☆168Updated 5 years ago
- Full-gradient saliency maps☆212Updated 2 years ago
- Code for all experiments.☆318Updated 4 years ago
- PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation☆338Updated 3 years ago
- ☆134Updated 6 years ago
- Tensorflow tutorial for various Deep Neural Network visualization techniques☆346Updated 5 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆129Updated 3 years ago
- Towards Automatic Concept-based Explanations☆160Updated last year
- ☆51Updated 4 years ago
- implements some LRP rules to get explanations for Resnets and Densenet-121, including batchnorm-Conv canonization and tensorbiased layers…☆25Updated last year
- Basic LRP implementation in PyTorch☆171Updated last year
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆229Updated 3 weeks ago
- This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpreta…☆372Updated 3 years ago
- Implementations of some popular Saliency Maps in Keras☆166Updated 6 years ago
- Public facing deeplift repo☆862Updated 3 years ago
- Keras implementation for DASP: Deep Approximate Shapley Propagation (ICML 2019)☆61Updated 6 years ago
- Layerwise Relevance Propagation with Deep Taylor Series in TensorFlow☆72Updated 8 years ago
- ☆121Updated 3 years ago
- This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.☆185Updated 3 years ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆347Updated 5 years ago