sebastian-lapuschkin / 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.
☆330Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for lrp_toolbox
- ☆99Updated 6 years ago
- Layer-wise Relevance Propagation (LRP) for LSTMs.☆222Updated 4 years ago
- Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers☆97Updated 6 years ago
- A toolbox to iNNvestigate neural networks' predictions!☆1,268Updated 11 months ago
- A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also in…☆734Updated 4 years ago
- Basic LRP implementation in PyTorch☆166Updated 3 months ago
- Attributing predictions made by the Inception network using the Integrated Gradients method☆598Updated 2 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆127Updated 3 years ago
- Detect model's attention☆155Updated 4 years ago
- A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).☆127Updated 3 years ago
- PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation☆334Updated 2 years ago
- Layerwise Relevance Propagation with Deep Taylor Series in TensorFlow☆71Updated 7 years ago
- Public facing deeplift repo☆827Updated 2 years ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆202Updated 4 months ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆125Updated 3 years ago
- Understanding Deep Networks via Extremal Perturbations and Smooth Masks☆344Updated 4 years ago
- ☆109Updated last year
- Tensorflow tutorial for various Deep Neural Network visualization techniques☆344Updated 4 years ago
- ☆131Updated 5 years ago
- Towards Automatic Concept-based Explanations☆157Updated 6 months ago
- Code for all experiments.☆307Updated 3 years ago
- Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).☆955Updated 8 months ago
- This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpreta…☆341Updated 2 years ago
- Full-gradient saliency maps☆203Updated last year
- ☆906Updated last year
- ☆48Updated 4 years ago
- ☆565Updated last year
- Pytorch implementation of various neural network interpretability methods☆111Updated 2 years ago
- Code for the TCAV ML interpretability project☆632Updated 3 months ago
- Implementations of some popular Saliency Maps in Keras☆165Updated 5 years ago